Compare commits
36 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 459e7fa602 | |||
| cc6e85cd9b | |||
| 0b1d9e2b15 | |||
| 10acaec33d | |||
| 1fcb17730e | |||
| d75c4e8e39 | |||
| 263ec2917b | |||
| be171304f5 | |||
| 4aec3061d5 | |||
| e643d38f58 | |||
| 6bf2a84ccd | |||
| 75da6767d3 | |||
| 8ac88ee536 | |||
| 0a8784cc1b | |||
| 7156b25957 | |||
| 022accfa7b | |||
| c457520ae4 | |||
| 9ca931e148 | |||
| c77ff913f0 | |||
| 4a3551254f | |||
| 0b7489f74d | |||
| 3dac5d3b44 | |||
| a99f2473b6 | |||
| ca46a93171 | |||
| 85a2b95428 | |||
| 75dec016eb | |||
| a0a9d5f5e4 | |||
| fc1e1487c7 | |||
| af07a2329a | |||
| 5fbe353836 | |||
| a3c92b68dc | |||
| 9ce83d5fdc | |||
| e62208d8e3 | |||
| 0205b81319 | |||
| 387ac4ab2c | |||
| 5c1b9816d4 |
@@ -104,8 +104,8 @@ id = "worldtree-conversation-api-openapi-v2"
|
||||
canonical_source = "Worldtree"
|
||||
canonical_path = "docs/conversation-api-openapi.json"
|
||||
consumer_path = "docs/conversation-api-openapi.json"
|
||||
pinned_sha256_16 = "dbdf4e24c8b06c92"
|
||||
pinned_at = "2026-06-30T22:25:56+00:00"
|
||||
pinned_sha256_16 = "36148179601453a0"
|
||||
pinned_at = "2026-07-06T16:09:05+00:00"
|
||||
|
||||
[[pins]]
|
||||
id = "worldtree-conversation-api-sse-events-v1"
|
||||
@@ -120,6 +120,41 @@ id = "worldtree-conversation-api-spec-v1"
|
||||
canonical_source = "Worldtree"
|
||||
canonical_path = "docs/conversation-api-spec.md"
|
||||
consumer_path = "docs/conversation-api-spec.md"
|
||||
pinned_sha256_16 = "2d111a3b8322b7d1"
|
||||
pinned_at = "2026-06-30T22:25:56+00:00"
|
||||
pinned_sha256_16 = "c656a789caceef14"
|
||||
pinned_at = "2026-07-06T16:51:09+00:00"
|
||||
tolerate_drift = true # prose reference; OpenAPI+SSE are the gates
|
||||
|
||||
# Worldtree persona render canons (d2) — the deterministic affect->NL the agent is
|
||||
# context-injected. The web persona pane renders mood + relationship-directive BYTE-EXACT
|
||||
# from these (via the flat src/ratatoskr/web/static/persona_render_canon.json, regenerated
|
||||
# by scripts/build_persona_canon.py). Drift here => rerun that regen with Worldtree's venv.
|
||||
[[pins]]
|
||||
id = "worldtree-persona-mood-render-canon-v1"
|
||||
canonical_source = "Worldtree"
|
||||
canonical_path = "core/persona/canon/d2-mood-render-canon-v1.json"
|
||||
consumer_path = "docs/vendor/worldtree-persona-canon/d2-mood-render-canon-v1.json"
|
||||
pinned_sha256_16 = "e2f124fed3ee8d42"
|
||||
pinned_at = "2026-07-01T21:00:00+00:00"
|
||||
|
||||
[[pins]]
|
||||
id = "worldtree-persona-d2-render-canon-v1"
|
||||
canonical_source = "Worldtree"
|
||||
canonical_path = "core/persona/canon/d2-render-canon-v1.json"
|
||||
consumer_path = "docs/vendor/worldtree-persona-canon/d2-render-canon-v1.json"
|
||||
pinned_sha256_16 = "606bba5fdcc60b6b"
|
||||
pinned_at = "2026-07-01T21:00:00+00:00"
|
||||
|
||||
# Worldtree affect-egress consumer reference — the authoritative DELIVERED-on-wire vs
|
||||
# HIDDEN (system-prompt-only) classification for the Tier-3 affect surface ratatoskr
|
||||
# consumes, + the reconstruction rules. The web console's "context injection" panel
|
||||
# reconstructs the hidden strings from this + the d2 canons. tolerate_drift: prose
|
||||
# reference (the render-canon JSONs are the strict gates). worldtree-dev co-signs +
|
||||
# pings ratatoskr-dev on any change (esp. the pending we-framing conditional).
|
||||
[[pins]]
|
||||
id = "worldtree-affect-egress-consumer-reference-v1"
|
||||
canonical_source = "Worldtree"
|
||||
canonical_path = "docs/affect-egress-consumer-reference.md"
|
||||
consumer_path = "docs/vendor/worldtree-persona-canon/affect-egress-consumer-reference.md"
|
||||
pinned_sha256_16 = "d959134037efae83"
|
||||
pinned_at = "2026-07-07T06:09:24+00:00"
|
||||
tolerate_drift = true # prose reference; the d2 render-canon JSONs are the gates
|
||||
|
||||
@@ -121,3 +121,7 @@ graphify-out/*
|
||||
*.db
|
||||
*.db-shm
|
||||
*.db-wal
|
||||
|
||||
# Node deps (Playwright for web-UI DOM verification — see persistent-memory)
|
||||
node_modules/
|
||||
package-lock.json
|
||||
|
||||
+9
-7
@@ -7,16 +7,18 @@ documents the pin, the vendored artifacts, and the bump procedure.
|
||||
|
||||
| Field | Value |
|
||||
|---|---|
|
||||
| Worldtree git SHA | `5810a26b38a5ea6630892f9a39756f57c5b7b41e` |
|
||||
| Worldtree HEAD message | `memory: snapshot — v1.0.0b2 shipped complete (demo + personal green); consumer loop closed` |
|
||||
| Pinned on | 2026-06-30 |
|
||||
| Pinned by | ratatoskr-dev (v1 coverage-audit — re-pin to the FROZEN OpenAPI 2.2.0 + SSE schema) |
|
||||
| Worldtree version at pin | `v1.0.0b2` |
|
||||
| Worldtree git SHA | `c9e59ec` |
|
||||
| Worldtree HEAD message | `docs: document Tier-3 persona/memory schemas + persona_state SET body (OpenAPI 2.3.0)` |
|
||||
| Pinned on | 2026-07-06 |
|
||||
| Pinned by | ratatoskr-dev (re-vendor prose markdown — Tier-3 persona/memory/persona_state consumer shapes) |
|
||||
| Worldtree version at pin | `v1.0.0b22` |
|
||||
|
||||
## Pin history
|
||||
|
||||
| Date | SHA | Version | Notable deltas consumed |
|
||||
|---|---|---|---|
|
||||
| 2026-07-06 | `c9e59ec` | v1.0.0b22 | **Re-vendor the prose markdown — Tier-3 consumer shapes documented.** `c9e59ec` (docs-only, OpenAPI byte-unchanged vs `879cefe`) adds `docs/conversation-api-spec.md` § "Tier 3 — Consumer-defined agents": the persona / memory / persona_state SET-body shapes that serialize as freeform `Any` in the OpenAPI (so prose is their source of truth). Drove a consumer fix: `--set-persona-pad` now sends the canonical `{pad:{pleasure,arousal,dominance}}` named dict (was `{pad:[list]}`) — #317, `v0.19.7`. Foot-guns encoded: persona.ocean single-letter `{O,C,E,A,N}` on `/agents/define` (spelled-out → 422, the #348 mismatch) vs spelled-out on `POST /characters`; memory `{embedder_version, tier3_dreaming}`, stm_* deprecated, allows_world_scope removed→422; only `valence` still 422s. `pin:`-only for the markdown; the `v0.19.7` bump rode the persona_state code fix. |
|
||||
| 2026-07-06 | `879cefe` | v1.0.0b22 | **Re-vendor OpenAPI 2.2.0→2.3.0 — Worldtree shipped #347 authored-history-write.** One new REST path-group: `POST /sessions/{session_id}/history` (the authored-history-write primitive) + the `AuthoredTurnResponse` schema (openapi path count 40→41). #347 is **OpenAPI-only** — the prose `conversation-api-spec.md` + server `conversation_api.contract.md` are byte-unchanged since the 5810a26 pin (empty `git log` delta), so those `tolerate_drift` pins stay clean; the SSE schema is unchanged (#347 is event-silent by design). **Consumer side NOT yet built** — `POST /sessions/{id}/history` is a fresh in-scope ⬜ gap in `docs/coverage-map.md` (re-opens the v1 coverage-audit with exactly one gap; Heimdall-gated hide-existence → consumer treats 404 as feature-absent). `pin:`-only, no version bump. |
|
||||
| 2026-06-30 | `5810a26` | v1.0.0b2 | **Re-pin to Worldtree's FROZEN v1 surface (#326), as part of the v1 coverage-audit.** Vendored the machine-readable artifacts — `conversation-api-openapi.json` (OpenAPI **2.2.0**, 40 path-groups) + `conversation-api-sse-events.schema.json` (11 events) — now the **authoritative drift gates** (pinned in `.corviduo-canonicals.toml`, CI-checked by `canonical_drift.py`). The prose `conversation-api-spec.md` is **byte-identical** to the v0.35.16 pin (last WT markdown edit 2026-05-31), kept as the human reference (`tolerate_drift`). b2 deltas already consumed in code: 409/503 eager turn-launch statuses (#331, v0.18.3/.4) + the unified error envelope (#328). 7 endpoints documented only in the OpenAPI, not the prose, all classified in `docs/coverage-map.md`: `admin/keys/bulk`, `admin/persona/{archive,erase}`, `admin/usage`, `embed`, `judgments`, `me/usage`. No client-breaking change — `pin:`-only, no version bump. |
|
||||
| 2026-06-17 | `f1b59f8` | v0.35.16 | **#297 + #298/#299 — Worldtree adopts the bifrost v0.6 scope wire (emits `scope_any`/`scope_all`) + client-side per-scope-value union recall. With our v0.17.6 provider this closes cold cross-session recall end-to-end.** Catch-up bump (v0.29.0→v0.35.16). Intervening client-facing deltas reviewed, none break our consumer: #211 agent rename (`saga`→`echo`, `actor`→`mask` — slugs only); #245 `end_user_id` persistence + memory-scope resolver; #187/#188/#219 Tier-3 define/PATCH policy (additive); `bifrost` binding field + `ephemeral_does_not_accept_bifrost` 422 now documented (the #17 surface). Error codes stable; no ratatoskr code change required. |
|
||||
| 2026-05-25 | `da93ca7` | v0.28.0 | #204 — new SSE event `affect_update` (current/scheduled), new endpoint `GET /agents/{id}/persona_state`, auth-model doc edits |
|
||||
@@ -26,12 +28,12 @@ documents the pin, the vendored artifacts, and the bump procedure.
|
||||
|
||||
**Authoritative (FROZEN, machine-readable — the drift gates):**
|
||||
|
||||
- `docs/conversation-api-openapi.json` — copy of `Worldtree/docs/conversation-api-openapi.json` (OpenAPI `info.version` **2.2.0**). The frozen v1 REST wire (40 path-groups). Pinned `worldtree-conversation-api-openapi-v2` in `.corviduo-canonicals.toml`; drift gated by `canonical_drift.py`.
|
||||
- `docs/conversation-api-openapi.json` — copy of `Worldtree/docs/conversation-api-openapi.json` (OpenAPI `info.version` **2.3.0**). The frozen v1 REST wire (41 path-groups; 2.3.0 added `POST /sessions/{session_id}/history` per #347). Pinned `worldtree-conversation-api-openapi-v2` in `.corviduo-canonicals.toml`; drift gated by `canonical_drift.py`.
|
||||
- `docs/conversation-api-sse-events.schema.json` — copy of `Worldtree/docs/conversation-api-sse-events.schema.json`. The frozen SSE event schema (11 discriminated event types). Pinned `worldtree-conversation-api-sse-events-v1`.
|
||||
|
||||
**Reference (prose; allowed to lag — `tolerate_drift`):**
|
||||
|
||||
- `docs/conversation-api-spec.md` — copy of `Worldtree/docs/conversation-api-spec.md` at the pinned SHA. The **client-facing prose narrative**. Byte-frozen at v0.35.16-era content (last WT edit 2026-05-31); the OpenAPI/SSE JSON above are the source of truth where they diverge. Pinned `worldtree-conversation-api-spec-v1` (tolerate_drift).
|
||||
- `docs/conversation-api-spec.md` — copy of `Worldtree/docs/conversation-api-spec.md` at the pinned SHA. The **client-facing prose narrative**. Re-vendored at `c9e59ec` (2026-07-06) to carry the § "Tier 3 — Consumer-defined agents" subsections (persona/memory/persona_state SET body) that serialize as freeform `Any` in the OpenAPI JSON — so the **prose is the source of truth for those consumer shapes** (e.g. persona.ocean single-letter `{O,C,E,A,N}` on `/agents/define`; `POST /sessions/{id}/persona_state` body `{pad:{pleasure,arousal,dominance}}`). Elsewhere the OpenAPI/SSE JSON above remain authoritative. Pinned `worldtree-conversation-api-spec-v1` (tolerate_drift).
|
||||
- `docs/conversation_api.contract.md` — copy of `Worldtree/docs/contracts/conversation_api.contract.md` at the pinned SHA (byte-identical at b2 — server contract unchanged since the v0.35.16 pin). The **server-side contract** including INV-001..INV-052 and amendments. Useful for understanding load-bearing server invariants (e.g., INV-014 turn-id-public, INV-046 admin-events-envelope-stable, INV-049 admin-events-pii-discipline) when designing client behavior against them. Not in the canonical manifest (reference-only).
|
||||
|
||||
Both files are vendored — they reflect Worldtree at the pinned SHA, not
|
||||
|
||||
@@ -0,0 +1,142 @@
|
||||
---
|
||||
contract_version: "2.1"
|
||||
module: "ratatoskr.first_message"
|
||||
purpose: "Per-agent authored first-message presets — seed an agent's opening as a #347 authored turn-0 onto new sessions (CLI + web), the durable replacement for a system-prompt startup instruction."
|
||||
touches:
|
||||
- src/ratatoskr/first_message.py
|
||||
- tests/test_first_message.py
|
||||
scope: >
|
||||
Per-agent authored first-message presets (Worldtree #347 consumer feature).
|
||||
When a new session is created for an agent that has a preset opening, seed it
|
||||
as a #347 authored first-message (POST /sessions/{id}/history, author=assistant,
|
||||
seq-0) so the session opens in-character before the user speaks — the durable
|
||||
replacement for a system-prompt "startup" instruction. Two entry points:
|
||||
`preset_for` (lookup) and `seed_preset_first_message` (best-effort seed).
|
||||
Consumed by ratatoskr.cli (the `--new` session path) and ratatoskr.web.server
|
||||
(the POST /api/sessions endpoint). Depends on ratatoskr.sessions
|
||||
(write_authored_history + its exceptions); no core.* / worldtree.* imports.
|
||||
depends_on:
|
||||
- "httpx"
|
||||
- "ratatoskr.sessions"
|
||||
used_by:
|
||||
- "ratatoskr.cli"
|
||||
- "ratatoskr.web.server"
|
||||
language: "python"
|
||||
complexity: "low"
|
||||
estimated_loc: 60
|
||||
confidence: 0.9
|
||||
assumptions:
|
||||
- "write_authored_history (contract #2 amendment 2026-07-06) is the seed primitive: 200/201 → ack dict, 404 → AuthoredHistoryUnavailable (hide-existence), other non-2xx → SessionApiFailed."
|
||||
- "The preset registry is a static in-module dict keyed by agent_id; editing it is how an operator tunes an agent's opening. Seeded with ratatoskr:sindra only."
|
||||
- "Auto-seed is BEST-EFFORT and MUST NOT block session creation: an instance without the session.history.write grant returns the hide-404, which is swallowed (session opens with no seeded greeting)."
|
||||
---
|
||||
|
||||
# First-message presets — authored openings on session-create (#347)
|
||||
|
||||
## Context
|
||||
|
||||
`ratatoskr.first_message` holds per-agent authored-opening presets and seeds them
|
||||
onto new sessions via the #347 authored-history-write primitive. It is the
|
||||
durable form of "give an agent a first message": instead of a system-prompt
|
||||
`Startup:` instruction (a workaround for the pre-#347 world where the assistant
|
||||
could not author turn-0), the opening lives as a real seeded assistant turn-0.
|
||||
|
||||
Consumed at both session-create sites — `ratatoskr.cli._amain` (the `--new` path)
|
||||
and `ratatoskr.web.server._create_session_endpoint` (POST /api/sessions) — so
|
||||
every new session for a preset agent opens in-character regardless of surface.
|
||||
|
||||
## Data flow
|
||||
|
||||
**In:** a live `httpx.AsyncClient` (caller-owned, base_url + bearer set), a fresh
|
||||
`session_id`, and the bound `agent_id`.
|
||||
|
||||
**Out:** on a preset agent, one `POST /sessions/{session_id}/history` (author=assistant,
|
||||
the preset text, per-content idempotency key). Returns the seeded content on
|
||||
success, else `None`.
|
||||
|
||||
**Side effects:** at most one outbound authored-history write; never raises to the
|
||||
caller (best-effort).
|
||||
|
||||
## Invariants
|
||||
|
||||
- **INV-001 [hard]**: `seed_preset_first_message` NEVER raises (the sole exception is
|
||||
`asyncio.CancelledError`, which propagates — cancellation is not a seed failure) and
|
||||
NEVER blocks session creation. It soft-guards its inputs (a bad arg returns `None`,
|
||||
not `AssertionError`), bounds the write with `asyncio.wait_for(_SEED_TIMEOUT_S)` so a
|
||||
stalled `/history` can't hang the create path, and swallows EVERY other exception (the
|
||||
hide-404, `SessionApiFailed`, `httpx.HTTPError`, `TimeoutError`, and any unexpected
|
||||
error) → `None`. The `broad-except` is deliberate: this helper is wired INTO three
|
||||
session-create paths, so any escape would abort a create that already succeeded.
|
||||
- **INV-002 [hard]**: a no-preset agent issues ZERO HTTP (early return before any
|
||||
request).
|
||||
- **INV-003 [hard]**: the seed body is the preset text verbatim, author="assistant",
|
||||
with a per-content idempotency key (`"ratatoskr-preset-" + sha256(text)[:12]`), so
|
||||
a repeat seed of the same session+preset is an idempotent 200 replay, never a
|
||||
duplicate turn.
|
||||
- **INV-004 [hard]**: no `core.*` / `worldtree.*` imports (reference-consumer
|
||||
boundary; verified by `tests/test_no_worldtree_imports.py`, which rglobs every
|
||||
`.py` under `src/ratatoskr/` — this module included, so no per-module import
|
||||
test is needed here).
|
||||
|
||||
## Out of scope
|
||||
|
||||
- **Multi-turn / scripted openers.** v1 seeds exactly one assistant turn-0. A
|
||||
multi-message opening scene is a future concern.
|
||||
- **Runtime/remote preset config.** The registry is an in-module dict; no file/DB/env
|
||||
loading. Add that only when a second consumer needs operator-editable presets.
|
||||
- **Non-assistant authors.** v1 is author=assistant only (matches #347 v1); a
|
||||
user/system opener is deferred with the #347 engine surface.
|
||||
- **TUI-only surfaces.** Both real session-create paths (CLI + web) are wired; the
|
||||
bare-TUI picker resumes existing sessions (no create), so it needs no seed.
|
||||
|
||||
---
|
||||
|
||||
```contract
|
||||
FN preset_for(agent_id: str) -> str | None
|
||||
BRIEF: Return the authored first-message preset for agent_id, or None when the agent has no preset. Pure dict lookup over FIRST_MESSAGE_PRESETS.
|
||||
PRE: [PRE-001 hard] agent_id is a non-empty str -- assert agent_id and isinstance(agent_id, str)
|
||||
POST: [POST-001 return_value] returns FIRST_MESSAGE_PRESETS.get(agent_id) (str for a preset agent, None otherwise)
|
||||
STEPS:
|
||||
1. [setup, prescriptive] assert PRE-001
|
||||
2. [sequential, prescriptive] RETURN FIRST_MESSAGE_PRESETS.get(agent_id)
|
||||
TESTS:
|
||||
preset_hit [happy]: preset_for("ratatoskr:sindra") is a non-empty str
|
||||
preset_miss [happy]: preset_for("mimir") is None
|
||||
empty_agent_id [adversarial]: preset_for("") → AssertionError
|
||||
|
||||
FN seed_preset_first_message(client: httpx.AsyncClient, session_id: str, agent_id: str) -> str | None
|
||||
BRIEF: Best-effort seed of an agent's preset opening as a #347 authored first-message on session_id. If agent_id has a preset, POST it via write_authored_history (author=assistant, per-content idempotency key, the await bounded by asyncio.wait_for(_SEED_TIMEOUT_S)) and return the seeded content; on no-preset, a malformed input, OR ANY exception except asyncio.CancelledError, return None WITHOUT raising. Never raises (except CancelledError, which propagates) and never blocks session creation — it is wired into three create paths.
|
||||
PRE: [PRE-001 hard] client is not None -- soft-guarded: return None (NOT assert) if violated, so a wiring bug can't crash the create path (INV-001)
|
||||
PRE: [PRE-002 hard] session_id is a non-empty str -- soft-guarded: return None if violated
|
||||
PRE: [PRE-003 hard] agent_id is a non-empty str -- soft-guarded: return None if violated (also guards FIRST_MESSAGE_PRESETS.get against a non-hashable/non-str id)
|
||||
POST: [POST-001 return_value] preset agent + successful write → returns the preset text; no-preset, malformed input, OR any swallowed failure → None
|
||||
POST: [POST-002 side_effect] a no-preset / malformed-input call issues ZERO HTTP; a preset agent issues exactly one POST /sessions/{session_id}/history with body author="assistant", content=preset, idempotency_key="ratatoskr-preset-"+sha256(preset)[:12], the await bounded by _SEED_TIMEOUT_S so a stalled response cannot block
|
||||
ERROR_ROUTING:
|
||||
asyncio.CancelledError:
|
||||
local_handling: RE-RAISE (cancellation is not a seed failure; never swallow it — and it is a BaseException, so `except Exception` would miss it anyway)
|
||||
flow_control: propagate
|
||||
state_recovery: n/a
|
||||
any other Exception (hide-404 AuthoredHistoryUnavailable, SessionApiFailed 409/422/etc., httpx.HTTPError, TimeoutError from wait_for, any unexpected error):
|
||||
local_handling: swallow; return None
|
||||
flow_control: continue (never blocks session create)
|
||||
state_recovery: session opens with no seeded greeting
|
||||
STEPS:
|
||||
1. [setup, prescriptive] Soft-guard: IF agent_id is not a non-empty str: RETURN None (before any dict lookup — guards a non-hashable id)
|
||||
2. [sequential, prescriptive] content = FIRST_MESSAGE_PRESETS.get(agent_id); IF content is None: RETURN None (INV-002 — zero HTTP)
|
||||
3. [sequential, prescriptive] Soft-guard: IF client is None OR session_id is not a non-empty str: RETURN None
|
||||
4. [sequential, prescriptive] key = "ratatoskr-preset-" + sha256(content utf-8)[:12]
|
||||
5. [sequential, prescriptive] TRY: await asyncio.wait_for(write_authored_history(client, session_id, content=content, idempotency_key=key), timeout=_SEED_TIMEOUT_S)
|
||||
tool: { destructive: false, idempotent: true, read_only: false, open_world: false }
|
||||
6. [branch, prescriptive] EXCEPT asyncio.CancelledError: RAISE; EXCEPT Exception: RETURN None
|
||||
7. [cleanup, prescriptive] RETURN content
|
||||
TESTS:
|
||||
seeds_preset [happy,tracer]: preset agent, mock 201 → returns the preset text; exactly one POST /sessions/{id}/history; body author="assistant" + content=preset + idempotency_key="ratatoskr-preset-"+sha256(preset)[:12]
|
||||
no_preset_zero_http [happy]: agent "mimir" → returns None; NO HTTP issued
|
||||
feature_absent_swallowed [error]: preset agent, mock 404 session_not_found → returns None, no raise
|
||||
session_api_failed_swallowed [error]: preset agent, mock 409 → returns None, no raise
|
||||
transport_error_swallowed [error]: preset agent, mock httpx.ConnectError → returns None, no raise
|
||||
unexpected_exception_swallowed [error]: preset agent, write raises ValueError → returns None, no raise (INV-001 broad never-raise)
|
||||
cancellation_propagates [error]: preset agent, write raises asyncio.CancelledError → RE-RAISED (never swallowed)
|
||||
malformed_agent_id_no_http [adversarial]: agent_id=123 (non-str) OR "" → None; NO HTTP; no raise
|
||||
empty_session_id [adversarial]: session_id="" (preset agent) → None (soft guard); NO HTTP; no raise
|
||||
```
|
||||
@@ -206,3 +206,267 @@ TESTS:
|
||||
limit_above_max [adversarial]: limit=300 → AssertionError; no HTTP issued
|
||||
empty_cursor [adversarial]: cursor="" → AssertionError; no HTTP issued
|
||||
```
|
||||
|
||||
## Amendment 2026-06-30 — boot-time introspection reads (v1 coverage-audit: capabilities+me)
|
||||
|
||||
The v1 coverage-audit added two read-only server-introspection endpoints as
|
||||
cheap debug primitives (surfaced via a new `ratatoskr --whoami` one-shot). Both
|
||||
mirror `get_persona_state`: GET, 200 → parsed dict verbatim, any non-200 →
|
||||
`SessionApiFailed`. The frozen OpenAPI types both responses as freeform objects,
|
||||
so the wrappers return `dict[str, Any]` (not a typed dataclass).
|
||||
|
||||
```contract
|
||||
FN get_me(client: httpx.AsyncClient) -> dict[str, Any]
|
||||
BRIEF: GET /me — the authenticated principal's identity + key metadata (spec §GET /me). Boot-time whoami: verify the key without agent-config side effects. Returns parsed JSON verbatim; spec documents {user_id, scopes, tier, display_name?, key_id?, key_label?, ...} with optional fields OMITTED (not null). Read-only, rate-exempt, no audit emission.
|
||||
PRE: [PRE-001 hard] client is not None -- assert client is not None
|
||||
POST: [POST-001 return_value] on 200 returns resp.json() unmodified -- assert result == resp.json()
|
||||
ERROR_ROUTING:
|
||||
HTTP non-200 (incl. 401 bad/absent key when auth enabled):
|
||||
local_handling: raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
flow_control: abort
|
||||
state_recovery: none (caller decides: bad key → re-key; degraded tier="unknown" is still a 200)
|
||||
STEPS:
|
||||
1. [setup, prescriptive] assert client is not None
|
||||
2. [sequential, prescriptive] resp = await client.get("/me")
|
||||
3. [branch, prescriptive] IF resp.status_code == 200: RETURN resp.json(); ELSE RAISE SessionApiFailed
|
||||
TESTS:
|
||||
happy_authenticated [happy,tracer]: 200 {user_id, scopes, tier, key_id} → dict returned verbatim
|
||||
anonymous_dev_mode: 200 {user_id:"anonymous", tier:"anonymous"} → dict; no key_* fields (omitted)
|
||||
401_raises [error]: 401 → SessionApiFailed(status=401)
|
||||
|
||||
FN get_capabilities(client: httpx.AsyncClient) -> dict[str, Any]
|
||||
BRIEF: GET /capabilities — server capability discovery (spec §Ephemeral Templates). Returns {ephemeral_templates: {echo: {allowed_models, default_model, system_prompt_max_bytes}}}. Any authenticated caller may read it (no instantiate scope). Parsed dict verbatim; any non-200 → SessionApiFailed.
|
||||
PRE: [PRE-001 hard] client is not None -- assert client is not None
|
||||
POST: [POST-001 return_value] on 200 returns resp.json() unmodified -- assert result == resp.json()
|
||||
ERROR_ROUTING:
|
||||
HTTP non-200:
|
||||
local_handling: raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
flow_control: abort
|
||||
state_recovery: none
|
||||
STEPS:
|
||||
1. [setup, prescriptive] assert client is not None
|
||||
2. [sequential, prescriptive] resp = await client.get("/capabilities")
|
||||
3. [branch, prescriptive] IF resp.status_code == 200: RETURN resp.json(); ELSE RAISE SessionApiFailed
|
||||
TESTS:
|
||||
happy [happy]: 200 {ephemeral_templates:{echo:{...}}} → dict returned verbatim
|
||||
non_200_raises [error]: 500 → SessionApiFailed(status=500)
|
||||
```
|
||||
|
||||
## Amendment 2026-07-01 — session tool introspection (v1 coverage-audit)
|
||||
|
||||
Owner-scoped tool-inventory read (spec #183, `GET /sessions/{id}/tools`),
|
||||
surfaced in the TUI Tools pane on session-attach. Same shape as the other
|
||||
introspection wrappers: GET, 200 → parsed dict verbatim, non-200 →
|
||||
`SessionApiFailed`. Reachable with the consumer key (no admin scope), unlike the
|
||||
admin variant `GET /admin/sessions/{id}/tools`.
|
||||
|
||||
```contract
|
||||
FN get_session_tools(client: httpx.AsyncClient, session_id: str) -> dict[str, Any]
|
||||
BRIEF: GET /sessions/{session_id}/tools — owner-scoped merged tool inventory (spec #183) the LLM saw at turn-fire: {agent_id, builtin_tools: [...], bifrost_tools: [{name, description, parameters}, ...]}. Owner gate (ctx.user_id == session.user_id); cross-owner → 404 session_not_found (existence-hiding), revoked → 401 auth_revoked. Parsed dict verbatim; any non-200 → SessionApiFailed.
|
||||
PRE: [PRE-001 hard] client is not None -- assert client is not None
|
||||
PRE: [PRE-002 hard] session_id is non-empty str -- assert session_id and isinstance(session_id, str)
|
||||
POST: [POST-001 return_value] on 200 returns resp.json() unmodified -- assert result == resp.json()
|
||||
ERROR_ROUTING:
|
||||
HTTP non-200 (incl. 404 session_not_found cross-owner/unknown, 401 auth_revoked):
|
||||
local_handling: raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
flow_control: abort
|
||||
state_recovery: none
|
||||
STEPS:
|
||||
1. [setup, prescriptive] assert PRE-001, PRE-002
|
||||
2. [sequential, prescriptive] resp = await client.get(f"/sessions/{session_id}/tools")
|
||||
3. [branch, prescriptive] IF resp.status_code == 200: RETURN resp.json(); ELSE RAISE SessionApiFailed
|
||||
TESTS:
|
||||
happy [happy,tracer]: 200 {agent_id, builtin_tools:[], bifrost_tools:[{name,...}]} → dict verbatim
|
||||
cross_owner_404 [error]: 404 session_not_found → SessionApiFailed(status=404)
|
||||
empty_session_id [adversarial]: "" → AssertionError; no HTTP issued
|
||||
```
|
||||
|
||||
## Amendment 2026-07-01 — admin BifrostState read (v1 coverage-audit)
|
||||
|
||||
Admin-scoped Bifrost dispatch-state read (spec #176, `GET /admin/sessions/{id}/bifrost`),
|
||||
surfaced in the TUI BifrostState pane on session-attach. The first admin-key
|
||||
consumer in ratatoskr: requires the `admin.sessions.read` scope, so the request
|
||||
OVERRIDES the Authorization header with the caller-supplied `admin_key` (distinct
|
||||
from the client's default consumer key). Same result-shape convention as the
|
||||
other introspection wrappers: 200 → parsed dict verbatim, non-200 → `SessionApiFailed`.
|
||||
|
||||
```contract
|
||||
FN get_session_bifrost(client: httpx.AsyncClient, session_id: str, *, admin_key: str) -> dict[str, Any]
|
||||
BRIEF: GET /admin/sessions/{session_id}/bifrost — admin-scoped live Bifrost binding (spec #176): {endpoint_url, consumer_id, connected, capabilities_granted, tools:[{name, description}]}. Requires admin.sessions.read; the request sets Authorization: Bearer <admin_key> (override), NOT the client's default consumer bearer. Parsed dict verbatim; any non-200 → SessionApiFailed — notably 403 auth_scope_denied and 404 session_not_bifrost_bound.
|
||||
PRE: [PRE-001 hard] client is not None -- assert client is not None
|
||||
PRE: [PRE-002 hard] session_id is non-empty str -- assert session_id and isinstance(session_id, str)
|
||||
PRE: [PRE-003 hard] admin_key is non-empty str -- assert admin_key and isinstance(admin_key, str)
|
||||
POST: [POST-001 return_value] on 200 returns resp.json() unmodified -- assert result == resp.json()
|
||||
POST: [POST-002 state_change] the outbound request Authorization header == f"Bearer {admin_key}" (override) -- assert request.headers["Authorization"] == "Bearer " + admin_key
|
||||
ERROR_ROUTING:
|
||||
HTTP non-200 (incl. 403 auth_scope_denied, 404 session_not_found / session_not_bifrost_bound):
|
||||
local_handling: raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
flow_control: abort
|
||||
state_recovery: none (caller decides: 403 → key lacks scope; 404 not-bound → benign unbound session)
|
||||
STEPS:
|
||||
1. [setup, prescriptive] assert PRE-001..PRE-003
|
||||
2. [sequential, prescriptive] resp = await client.get(f"/admin/sessions/{session_id}/bifrost", headers={"Authorization": f"Bearer {admin_key}"})
|
||||
3. [branch, prescriptive] IF resp.status_code == 200: RETURN resp.json(); ELSE RAISE SessionApiFailed
|
||||
TESTS:
|
||||
happy_uses_admin_bearer [happy,tracer]: 200 {endpoint_url, connected, capabilities_granted, tools} → dict verbatim; request Authorization == "Bearer <admin_key>" (override)
|
||||
scope_denied_403 [error]: 403 → SessionApiFailed(status=403)
|
||||
not_bound_404 [error]: 404 session_not_bifrost_bound → SessionApiFailed(status=404)
|
||||
empty_admin_key [adversarial]: admin_key="" → AssertionError; no HTTP issued
|
||||
```
|
||||
|
||||
## Amendment 2026-07-01 — Tier-2: transient characters + persona-state write (v1 coverage-audit)
|
||||
|
||||
The last in-scope client I/O points. Transient-character CRUD (#161) surfaced
|
||||
via a `--characters` one-shot lifecycle probe; persona-state write surfaced via
|
||||
`--set-persona-pad "p,a,d"` (requires `--session`). All mirror the existing
|
||||
wrappers: parsed dict verbatim (or None on 204), any off-status → SessionApiFailed.
|
||||
**Note:** `set_persona_state`'s request body is FREEFORM — the frozen OpenAPI 2.2.0
|
||||
declares no request schema and the prose spec documents only the GET counterpart,
|
||||
so the caller supplies the snapshot shape. **Canonical (worldtree-dev prose #317,
|
||||
`c9e59ec`): `{pad:{pleasure,arousal,dominance}}` — a named-key dict, NOT a list;
|
||||
`--set-persona-pad` builds + sends the named dict (each float in [-1,1]).**
|
||||
|
||||
```contract
|
||||
FN list_character_models(client) -> dict[str, Any]
|
||||
BRIEF: GET /models/available-for-characters (character.read). Returns {items:[{name, description, thinking}]}. Non-200 → SessionApiFailed.
|
||||
PRE: [PRE-001 hard] client is not None
|
||||
POST: [POST-001 return_value] on 200 returns resp.json() unmodified
|
||||
STEPS:
|
||||
1. [sequential, prescriptive] resp = await client.get("/models/available-for-characters"); IF 200 RETURN resp.json(); ELSE RAISE SessionApiFailed
|
||||
TESTS:
|
||||
list_models [happy,tracer]: 200 {items:[{name:"fast"}]} → dict verbatim
|
||||
|
||||
FN create_character(client, character: dict, *, state: dict | None = None) -> dict[str, Any]
|
||||
BRIEF: POST /characters (character.write). Body {character, state}. Returns 201 {character_id, ttl_expires_at}; non-201 → SessionApiFailed.
|
||||
PRE: [PRE-001 hard] client is not None; [PRE-002 hard] character is a non-empty dict
|
||||
POST: [POST-001 return_value] on 201 returns resp.json(); [POST-002 side_effect] outbound body == {"character": <arg>, "state": <state|null>}
|
||||
STEPS:
|
||||
1. [sequential, prescriptive] resp = await client.post("/characters", json={"character": character, "state": state}); IF 201 RETURN resp.json(); ELSE RAISE SessionApiFailed
|
||||
TESTS:
|
||||
create [happy]: 201 → {character_id}; body is {character, state:null}
|
||||
create_403 [error]: 403 auth_scope_denied → SessionApiFailed(403)
|
||||
|
||||
FN get_character_state(client, character_id: str) -> dict[str, Any]
|
||||
BRIEF: GET /characters/{id}/state (character.read). Live PAD/emotions snapshot; refreshes TTL. Non-200 → SessionApiFailed.
|
||||
PRE: [PRE-001 hard] client not None; [PRE-002 hard] character_id non-empty str
|
||||
POST: [POST-001 return_value] on 200 returns resp.json()
|
||||
STEPS:
|
||||
1. [sequential, prescriptive] resp = await client.get(f"/characters/{character_id}/state"); IF 200 RETURN resp.json(); ELSE RAISE SessionApiFailed
|
||||
TESTS:
|
||||
get_state [happy]: 200 {pad:[...]} → dict verbatim
|
||||
|
||||
FN delete_character(client, character_id: str) -> None
|
||||
BRIEF: DELETE /characters/{id} (character.write). 200/204 → None; other → SessionApiFailed.
|
||||
PRE: [PRE-001 hard] client not None; [PRE-002 hard] character_id non-empty str
|
||||
POST: [POST-001 return_value] on 200/204 returns None
|
||||
STEPS:
|
||||
1. [sequential, prescriptive] resp = await client.delete(f"/characters/{character_id}"); IF status in (200,204) RETURN None; ELSE RAISE SessionApiFailed
|
||||
TESTS:
|
||||
delete [happy]: 204 → None
|
||||
|
||||
FN set_persona_state(client, session_id: str, snapshot: dict) -> None
|
||||
BRIEF: POST /sessions/{session_id}/persona_state — set a session's persona state (affect injection). Request body is the FREEFORM snapshot (caller-supplied; unpinned in the frozen surface). 204 → None; other → SessionApiFailed.
|
||||
PRE: [PRE-001 hard] client not None; [PRE-002 hard] session_id non-empty str; [PRE-003 hard] snapshot is a dict
|
||||
POST: [POST-001 return_value] on 204 returns None; [POST-002 side_effect] outbound body == snapshot verbatim
|
||||
STEPS:
|
||||
1. [sequential, prescriptive] resp = await client.post(f"/sessions/{session_id}/persona_state", json=snapshot); IF 204 RETURN None; ELSE RAISE SessionApiFailed
|
||||
TESTS:
|
||||
happy [happy]: 204 → None; body == {"pad":{"pleasure","arousal","dominance"}} verbatim (canonical named-key dict, #317)
|
||||
non_204 [error]: 422 → SessionApiFailed(422)
|
||||
```
|
||||
|
||||
## Amendment 2026-07-06 — authored-history write (#347, v1 coverage-audit re-open)
|
||||
|
||||
Worldtree shipped #347 (authored-history-write) as OpenAPI 2.3.0: a new
|
||||
`POST /sessions/{session_id}/history` primitive that writes ONE model-visible
|
||||
turn into a session's ledger AS the bound agent, WITHOUT a generation and
|
||||
WITHOUT lived-turn side effects (the SillyTavern "first message"). The re-vendor
|
||||
(2.2.0→2.3.0, pin `879cefe`) re-opened the v1 coverage-audit with this one new
|
||||
in-scope REST path-group; this amendment closes it on the consumer side and also
|
||||
un-defers `GET /sessions/{id}/messages` (previously §Out of scope) as the seed's
|
||||
read-back.
|
||||
|
||||
**Hide-existence (server INV-347-1) — the load-bearing consumer contract.** The
|
||||
`session.history.write` grant is checked FIRST — an ungranted caller (or a
|
||||
non-owner, or an unknown session) gets a 404 **byte-identical** to a genuine
|
||||
`session_not_found`, never a 403/409/422 that would reveal the feature exists.
|
||||
The consumer MUST honor this: treat 404 as **feature-absent**, fall back (a
|
||||
production consumer to a model-generated greeting), and NEVER capability-probe to
|
||||
tell feature-absent from ungranted from session-absent. The wrapper encodes it by
|
||||
raising a DISTINCT `AuthoredHistoryUnavailable` on 404 (NOT `SessionApiFailed`),
|
||||
so a caller branches feature-absent without inspecting a status code.
|
||||
|
||||
**Request body — v1-minimal, wire-pinned by the server.** The frozen OpenAPI 2.3.0
|
||||
exports an empty request schema, but the server pins `AuthoredWriteRequest`
|
||||
(`extra="forbid"`): `{author, content, idempotency_key, effects?,
|
||||
claimed_original_at?}`. v1: `author="assistant"` (only value), `content` (UTF-8,
|
||||
server-bounded at `authored_content_max_bytes`=8192), `idempotency_key` (REQUIRED,
|
||||
per-session dedup), `effects` omitted (== "none"; only value). Because
|
||||
`extra="forbid"`, the wrapper omits `effects`/`claimed_original_at` when None
|
||||
(never sends null). Success is 201 (fresh) OR 200 (idempotent replay,
|
||||
byte-identical body); both return the `AuthoredTurnResponse` `{author,
|
||||
content_chars, injected_at, phase, seq, session_id, turn_id}` verbatim (provenance
|
||||
is audit-only, NEVER on this body — INV-347-7).
|
||||
|
||||
**Assistant-first provider constraint (deferred, inert for the probe).** A
|
||||
create-time first-message makes the assistant seq-0 (assistant-first history);
|
||||
Anthropic-family providers 400 the *next generation*, vLLM/openai_compat tolerate
|
||||
it. The `--seed-first-message` probe seeds but does NOT generate, so the
|
||||
constraint is inert for the probe — a real consumer that then generates must bind
|
||||
an assistant-first-tolerant provider.
|
||||
|
||||
```contract
|
||||
FN write_authored_history(client: httpx.AsyncClient, session_id: str, *, content: str, idempotency_key: str, author: str = "assistant", effects: str | None = None, claimed_original_at: str | None = None) -> dict[str, Any]
|
||||
BRIEF: POST /sessions/{session_id}/history — the #347 authored-history-write primitive (write one model-visible turn as the bound agent, no generation, no side effects). Body {author, content, idempotency_key} + "effects"/"claimed_original_at" only when non-None (server AuthoredWriteRequest is extra="forbid"). Success 200 (replay) or 201 (fresh) → AuthoredTurnResponse dict verbatim. 404 → AuthoredHistoryUnavailable (hide-existence: feature-absent/ungranted/session-absent, indistinguishable by design — consumer falls back, never probes). Any other non-2xx → SessionApiFailed.
|
||||
PRE: [PRE-001 hard] client is not None -- assert client is not None
|
||||
PRE: [PRE-002 hard] session_id is a non-empty str -- assert session_id and isinstance(session_id, str)
|
||||
PRE: [PRE-003 hard] content is a non-empty str -- assert content and isinstance(content, str)
|
||||
PRE: [PRE-004 hard] idempotency_key is a non-empty str -- assert idempotency_key and isinstance(idempotency_key, str)
|
||||
PRE: [PRE-005 hard] author is a non-empty str -- assert author and isinstance(author, str)
|
||||
POST: [POST-001 side_effect] exactly one POST to /sessions/{session_id}/history; body == {"author": author, "content": content, "idempotency_key": idempotency_key} plus "effects" iff effects is not None plus "claimed_original_at" iff claimed_original_at is not None (no null-valued keys — extra="forbid")
|
||||
POST: [POST-002 return_value] on 200 or 201 returns resp.json() unmodified
|
||||
ERROR_ROUTING:
|
||||
HTTP 404 (hide-existence session_not_found):
|
||||
local_handling: raise AuthoredHistoryUnavailable(session_id=session_id)
|
||||
flow_control: abort
|
||||
state_recovery: caller treats as feature-absent; fall back to a model-generated greeting; NEVER capability-probe (INV-347-1)
|
||||
HTTP other non-2xx (incl. 409 generation_active, 422 content_too_long/validation_failed, 401 auth_revoked, 410 session_retired):
|
||||
local_handling: raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
flow_control: abort
|
||||
state_recovery: none (409 retryable; 422 caller bug/oversize)
|
||||
STEPS:
|
||||
1. [setup, flexibility=prescriptive] assert PRE-001..PRE-005
|
||||
2. [sequential, flexibility=prescriptive] body = {"author": author, "content": content, "idempotency_key": idempotency_key}; IF effects is not None: body["effects"] = effects; IF claimed_original_at is not None: body["claimed_original_at"] = claimed_original_at
|
||||
3. [sequential, flexibility=prescriptive] resp = await client.post(f"/sessions/{session_id}/history", json=body)
|
||||
tool: { destructive: false, idempotent: true, read_only: false, open_world: false }
|
||||
4. [branch, flexibility=prescriptive] IF resp.status_code in (200, 201): RETURN resp.json(); ELIF resp.status_code == 404: RAISE AuthoredHistoryUnavailable(session_id=session_id); ELSE RAISE SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
TESTS:
|
||||
happy_fresh_201 [happy,tracer]: 201 {author:"assistant", seq:0, phase:"seeded", turn_id, content_chars, session_id, injected_at} → dict verbatim; outbound body == {"author":"assistant","content":<c>,"idempotency_key":<k>} exactly (no effects/claimed_original_at keys)
|
||||
happy_replay_200 [happy]: 200 (same-key replay, byte-identical body) → dict verbatim
|
||||
body_includes_effects [trace]: effects="none" → outbound body has "effects":"none"; claimed_original_at="2020-01-01T00:00:00Z" → body has that key too
|
||||
hide_existence_404 [error]: 404 {error_code:"session_not_found"} → raises AuthoredHistoryUnavailable(session_id=<arg>), NOT SessionApiFailed
|
||||
generation_active_409 [error]: 409 {error_code:"generation_active"} → SessionApiFailed(status=409)
|
||||
content_too_long_422 [error]: 422 {error_code:"content_too_long"} → SessionApiFailed(status=422)
|
||||
empty_content [adversarial]: content="" → AssertionError; no HTTP issued
|
||||
empty_idempotency_key [adversarial]: idempotency_key="" → AssertionError; no HTTP issued
|
||||
empty_session_id [adversarial]: session_id="" → AssertionError; no HTTP issued
|
||||
|
||||
FN get_session_messages(client: httpx.AsyncClient, session_id: str) -> dict[str, Any]
|
||||
BRIEF: GET /sessions/{session_id}/messages — the session's message history (spec §GET /sessions/{id}/messages), un-deferred as the #347 probe's read-back so a seeded turn can be confirmed to render as a normal role=assistant message (model-invisible provenance — a seed is indistinguishable from a lived turn on read). Returns {session_id, items:[{seq, role, content, ...}], next_cursor} verbatim. Owner-scoped; any non-200 → SessionApiFailed. v1 reads the server default page (no pagination params — the probe reads a fresh 1-message session; add limit/cursor when a caller needs scrollback).
|
||||
PRE: [PRE-001 hard] client is not None -- assert client is not None
|
||||
PRE: [PRE-002 hard] session_id is a non-empty str -- assert session_id and isinstance(session_id, str)
|
||||
POST: [POST-001 return_value] on 200 returns resp.json() unmodified
|
||||
ERROR_ROUTING:
|
||||
HTTP non-200 (incl. 404 session_not_found cross-owner/unknown):
|
||||
local_handling: raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
flow_control: abort
|
||||
state_recovery: none
|
||||
STEPS:
|
||||
1. [setup, flexibility=prescriptive] assert PRE-001, PRE-002
|
||||
2. [sequential, flexibility=prescriptive] resp = await client.get(f"/sessions/{session_id}/messages")
|
||||
3. [branch, flexibility=prescriptive] IF resp.status_code == 200: RETURN resp.json(); ELSE RAISE SessionApiFailed
|
||||
TESTS:
|
||||
happy [happy]: 200 {session_id, items:[{seq:0, role:"assistant", content:"…"}], next_cursor:null} → dict verbatim
|
||||
not_found_404 [error]: 404 → SessionApiFailed(status=404)
|
||||
empty_session_id [adversarial]: "" → AssertionError; no HTTP issued
|
||||
```
|
||||
|
||||
@@ -372,3 +372,64 @@ test layer.
|
||||
- Issue #7 (mid-stream robustness, `MalformedSseData`) — landed; #6's
|
||||
pre/in-alt-screen split is orthogonal to #7's empty-data/malformed
|
||||
distinction (different error layers entirely).
|
||||
|
||||
## Amendment 2026-06-30 — startup session picker (v1 coverage-audit, slice b2)
|
||||
|
||||
The v1 coverage-audit found `list_sessions` had **no caller** — the startup
|
||||
session picker (design-brief §4: "single-session-per-launch, with a startup
|
||||
picker invoked when more than one session exists ... plus flags `--session`/
|
||||
`--new` to skip it") was never built. Bare TUI mode (neither `--session` nor
|
||||
`--new`) was a hard usage error. This adds the picker as a pre-alt-screen
|
||||
resolution step in `_resolve_then_run`, mirroring the existing `AgentPickerApp`.
|
||||
|
||||
**Locked design (design-brief §4):** the picker is **resume-only** (§4 negative
|
||||
clause "no in-app session creation — `--new` flag only"); shown only when **>1**
|
||||
session exists (exactly 1 auto-resumes; the launch intent is "resume the last
|
||||
session I was poking at"). `--agent` stays a `--new` companion (forbidden in bare
|
||||
mode). **bare + 0 sessions → error** `[no_sessions]` directing the operator to
|
||||
`--new` (honors the "no in-app creation" clause; the friendlier
|
||||
auto-fall-through-to-new alternative is deferred pending operator confirmation).
|
||||
|
||||
### `_parse` validation relaxation (ratatoskr.cli._parse)
|
||||
|
||||
- Bare TUI mode (`send is None` AND no `--session` AND no `--new`) is now VALID
|
||||
→ triggers the picker. (Previously `raise UsageError("pass exactly one of
|
||||
--session or --new")` unconditionally.)
|
||||
- `--send` mode still requires exactly one of `--session`/`--new` (non-
|
||||
interactive: no picker can open) → `UsageError("--send requires --session or
|
||||
--new")`.
|
||||
- `--session` + `--new` stays mutually exclusive.
|
||||
- `--agent` in bare mode → `UsageError` (`--agent` belongs to `--new`).
|
||||
|
||||
```contract
|
||||
FN SessionPickerApp.__init__(self, sessions: list[SessionInfo]) -> None
|
||||
BRIEF: Textual App[str | None] startup session picker (mirrors AgentPickerApp, issue #8). Opens before RatatoskrApp when bare TUI mode resolves >1 session. `run_async()` returns the chosen session_id (str) or None on Esc/Ctrl-D/Ctrl-C dismissal. Architecturally separate from RatatoskrApp (list_sessions failures + dismissal land before any alt-screen — preserves #6 INV-001).
|
||||
PRE: [PRE-001 hard] sessions is non-empty -- assert sessions (caller resolves 0-session and 1-session cases BEFORE constructing the picker)
|
||||
POST: [POST-001 return_value] run_async() returns sessions[i].session_id for the highlighted row on `pick`, or None on dismiss -- assert result in {s.session_id for s in sessions} | {None}
|
||||
STEPS:
|
||||
1. [setup, prescriptive] Store sessions; register the Australis theme (mirror AgentPickerApp).
|
||||
2. [sequential, prescriptive] compose: Header + prompt Static + ListView of one ListItem per session (id-short + agent_id + last_active/name lines) + Footer.
|
||||
3. [sequential, prescriptive] BINDINGS: enter→action_pick, escape/ctrl+d/ctrl+c→action_dismiss.
|
||||
4. [branch, prescriptive] action_pick: read ListView.index; if None return (nothing highlighted); else exit(sessions[index].session_id). action_dismiss: exit(None).
|
||||
TESTS:
|
||||
pick_returns_session_id [happy,tracer]: SessionPickerApp([s0, s1]); pilot highlights row 1 + press enter → run_async() returns s1.session_id.
|
||||
dismiss_returns_none [happy]: press escape → run_async() returns None.
|
||||
ctrl_d_dismisses [adversarial]: press ctrl+d → None.
|
||||
|
||||
FN _resolve_then_run(args) — bare-mode extension (session picker)
|
||||
BRIEF: Before the existing new/resume branches, resolve bare TUI mode (not args.new AND args.session_id is None) via list_sessions + the picker. Sets a local `effective_new` and `resolved_session_id`; the existing branches then run unchanged on those locals.
|
||||
STEPS (inserted at the top of the `async with client` block):
|
||||
1. [setup, prescriptive] SET effective_new = args.new; resolved_session_id = args.session_id.
|
||||
2. [branch, prescriptive] IF (not args.new) AND (args.session_id is None): # bare mode
|
||||
a. CALL list_sessions(client) → page; ON SessionApiFailed → stderr `[session_api_failed]` + return 20; ON network error → `[network_error]` + return 21.
|
||||
b. IF not page.items: stderr `[no_sessions] no sessions to resume; launch with --new --agent <id>` + return 14.
|
||||
c. ELIF len(page.items) == 1: SET resolved_session_id = page.items[0].session_id. # §4: picker only when >1
|
||||
d. ELSE: SET resolved_session_id = await SessionPickerApp(page.items).run_async(); IF None → return 0 (Esc/Ctrl-D clean exit).
|
||||
3. [sequential, prescriptive] Replace the two `if args.new` predicates with `if effective_new`; the resume `else` branch asserts + uses `resolved_session_id`.
|
||||
TESTS (in the `_resolve_then_run` block):
|
||||
bare_zero_sessions_errors [error]: bare args; list_sessions → 0 items → stderr contains `[no_sessions]`; return 14; NO POST /sessions, NO picker.
|
||||
bare_one_session_auto_resumes [scenario]: bare args; list_sessions → 1 item (sid="s-solo") → RatatoskrApp constructed with session_id="s-solo"; NO picker shown.
|
||||
bare_multi_opens_picker [scenario,tracer]: bare args; list_sessions → 2 items; picker returns items[1].session_id → RatatoskrApp constructed with that session_id.
|
||||
bare_picker_dismiss_exits_zero [scenario]: bare args; 2 items; picker returns None → return 0; RatatoskrApp NOT constructed.
|
||||
bare_list_sessions_api_failure [error]: bare args; list_sessions raises SessionApiFailed(500) → stderr `[session_api_failed]`; return 20.
|
||||
```
|
||||
|
||||
@@ -0,0 +1,179 @@
|
||||
---
|
||||
contract_version: "2.1"
|
||||
module: "ratatoskr.web"
|
||||
purpose: "v0.19.2 web debug-surface parity: 3 admin/debug panes (Tools inventory, BifrostState, AdminEvents SSE) proxied server-side with the admin key server-held, plus a reliable PAD-refresh poll and a non-engine reasoning indicator in the transcript."
|
||||
target_module: "ratatoskr.web (server.py routes + entrypoint.py + static/index.html)"
|
||||
scope: "v0.19.2 web debug-surface parity — bring the browser surface (now the PRIMARY debug surface) to TUI parity. THREE new admin/debug panes proxied server-side + TWO transcript affordances. (1) Tools inventory: GET /api/sessions/{id}/tools proxies owner-scoped get_session_tools into the tools pane (what the LLM HAS at turn-fire), above the live tool events. (2) BifrostState pane: GET /api/sessions/{id}/bifrost proxies admin-scoped get_session_bifrost; the admin key is SERVER-HELD (app.state.admin_key from RATATOSKR_ADMIN_API_KEY), never sent to the browser. (3) AdminEvents pane: GET /api/admin/events is an SSE proxy of stream_admin_events, session-filtered SERVER-side (heartbeats + other-session events dropped), re-emitted under a fixed 'admin_event' name so every dotted type renders with one browser listener. (4) PAD refresh: the persona/affect pane polls a bounded window instead of a single 2s shot that raced the post-turn-async affect.emit. (5) Reasoning indicator: an ephemeral, clearly-non-engine transcript line on `thinking` deltas, cleared when text begins. Direct in-session TDD (the #17/#18 pattern); this contract is authored post-implementation to anchor the heid code review (the client wrappers get_session_tools/get_session_bifrost/stream_admin_events are already contracted in the sessions/sse_client specs — this contract governs the WEB proxy + presenter surface only. v0.20.0 REDESIGN (Claude Design 'Ratatoskr Console' import): the tabbed telemetry column is replaced by a 3-column command-console — a left engine-ticker rail (the DEBUG + ADMIN + tool/turn-lifecycle feeds MERGED into one timeline via tickerAdd, plus a tools-armed chip list + a full-detail Bifrost rail pane) · a center conversation (per-turn INLINE chain-of-thought, replacing the separate Think pane) · a right resizable affect console (dominant/canonical-mood centerpiece + bipolar PAD faders each carrying a turn-to-turn Δ+sparkline + a P×A mood orbit + relations metric rows + canonical directive). ALL SERVER ROUTES UNCHANGED. Single-file/no-CDN/vanilla preserved; adds a light/dark theme toggle (dark default) + an inlined data-URI favicon. Presenter FN renames tracked below (renderBifrostState→renderBifrost; renderAffectPane→renderConsole; setPersonaStrip removed; tickerAdd/setFader/setFaderTrend/renderOrbit/renderDominant/renderDerived/renderRelations/renderDirective added). INV-001/INV-004 held.)."
|
||||
depends_on:
|
||||
- "httpx"
|
||||
- "starlette"
|
||||
- "ratatoskr.sessions" # get_session_tools, get_session_bifrost, SessionApiFailed
|
||||
- "ratatoskr.sse_client" # stream_admin_events, AdminEvent, SseConnectFailed/Dropped
|
||||
used_by:
|
||||
- "ratatoskr.web.entrypoint" # passes admin_key=RATATOSKR_ADMIN_API_KEY into create_app
|
||||
language: "python + vanilla JS (single-file SPA, no build)"
|
||||
complexity: "medium"
|
||||
estimated_loc: 290
|
||||
confidence: 0.8
|
||||
assumptions:
|
||||
- "The three client wrappers exist and are already contracted: get_session_tools(client, session_id)->dict (owner-scoped, consumer bearer; non-200 -> SessionApiFailed), get_session_bifrost(client, session_id, *, admin_key)->dict (OVERRIDES Authorization with admin_key; non-200 -> SessionApiFailed), stream_admin_events(client, *, admin_key)->AsyncIterator[AdminEvent] (non-200 -> SseConnectFailed; mid-drop -> SseConnectionDropped). The web routes are thin proxies over them; they add NO new upstream semantics."
|
||||
- "AdminEvent = {id:int, type:str, timestamp:str|None, data:dict}. data MOST carry session_id (INV-049). type is a dotted namespace (session.*/turn.*/key.*/system.*)."
|
||||
- "The web SPA is a single static/index.html served per-request via FileResponse (edits land on browser refresh; server code changes need a restart). Model/tool/admin content is UNTRUSTED text (INV-004) — every render path escapes first (esc() via textContent, or JSON.stringify wrapped in esc())."
|
||||
- "The internal-LAN trust model (0.0.0.0, no auth/TLS/CORS) is deliberate operator direction. Admin-scoped DATA becoming LAN-visible is accepted under that model; the admin KEY must nonetheless never cross to the browser."
|
||||
- "Tests: respx mocks the upstream endpoints (absolute w.example URLs) driven through the TestClient; the AdminEvents SSE proxy is tested with a finite mocked SSE byte-stream asserting the filter + fixed event name. Live-proven against ratatoskr:sindra on personal :8081."
|
||||
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
functions:
|
||||
- name: "_session_tools_endpoint"
|
||||
signature: "async _session_tools_endpoint(request: Request) -> JSONResponse"
|
||||
description: "GET /api/sessions/{session_id}/tools — proxy owner-scoped tool inventory."
|
||||
preconditions:
|
||||
- "session_id in path_params."
|
||||
postconditions:
|
||||
- "POST-001: 200 with the upstream inventory dict verbatim on success."
|
||||
- "POST-002: on SessionApiFailed(status) -> JSONResponse({error_code:'session_tools_unavailable', status}, status_code=status) — status-preserving."
|
||||
steps: "Open client_factory() client; await get_session_tools(client, session_id); return 200. Except SessionApiFailed -> status-preserving envelope."
|
||||
flexibility: "prescriptive"
|
||||
|
||||
- name: "_session_messages_endpoint"
|
||||
signature: "async _session_messages_endpoint(request: Request) -> JSONResponse"
|
||||
description: "GET /api/sessions/{session_id}/messages — proxy the session's message history so the SPA renders existing turns on open (notably a #347 authored first-message seeded at create-time; without it a seeded session's transcript is blank until the user speaks)."
|
||||
preconditions:
|
||||
- "session_id in path_params."
|
||||
postconditions:
|
||||
- "POST-001: 200 with the upstream {session_id, items, next_cursor} dict verbatim on success."
|
||||
- "POST-002: on SessionApiFailed(status) -> JSONResponse({error_code:'session_messages_unavailable', status}, status_code=status) — status-preserving."
|
||||
steps: "Open client_factory() client; await get_session_messages(client, session_id); return 200. Except SessionApiFailed -> status-preserving envelope."
|
||||
flexibility: "prescriptive"
|
||||
|
||||
- name: "_session_bifrost_endpoint"
|
||||
signature: "async _session_bifrost_endpoint(request: Request) -> JSONResponse"
|
||||
description: "GET /api/sessions/{session_id}/bifrost — proxy admin-scoped Bifrost dispatch state."
|
||||
preconditions:
|
||||
- "session_id in path_params."
|
||||
- "PRE-001 (fail-visible): app.state.admin_key must be truthy; else 400 admin_key_not_configured with NO upstream call."
|
||||
postconditions:
|
||||
- "POST-001: the admin key is read from app.state.admin_key ONLY; it is passed to get_session_bifrost(admin_key=...) and NEVER placed in a response body or surfaced to the browser."
|
||||
- "POST-002: 200 with the upstream state dict verbatim on success."
|
||||
- "POST-003: on SessionApiFailed(status) -> {error_code:'bifrost_state_unavailable', status} at status_code=status (notably 404 not-bound, 403 scope-denied)."
|
||||
steps: "If not admin_key -> 400. Open client; await get_session_bifrost(client, session_id, admin_key=admin_key); 200. Except SessionApiFailed -> status-preserving envelope."
|
||||
flexibility: "prescriptive"
|
||||
|
||||
- name: "_admin_event_matches_web"
|
||||
signature: "_admin_event_matches_web(ev: AdminEvent, session_id: str | None) -> bool"
|
||||
description: "AdminEvents session-filter (mirrors the TUI _admin_event_matches, design-brief §6)."
|
||||
postconditions:
|
||||
- "POST-001: ev.type == 'system.heartbeat' -> False (keepalive noise dropped)."
|
||||
- "POST-002: ev.type.startswith('system.') (non-heartbeat) -> True (stream-integrity signals always pass)."
|
||||
- "POST-003: otherwise -> True IFF session_id is not None AND ev.data.get('session_id') == session_id (per-session scoping; a None session_id forwards NO non-system event)."
|
||||
flexibility: "prescriptive"
|
||||
|
||||
- name: "_admin_events_endpoint"
|
||||
signature: "async _admin_events_endpoint(request: Request) -> Response"
|
||||
description: "GET /api/admin/events?session_id=... — SSE proxy of stream_admin_events, session-filtered server-side."
|
||||
preconditions:
|
||||
- "PRE-001 (fail-visible): app.state.admin_key truthy; else 400 admin_key_not_configured with NO stream opened."
|
||||
postconditions:
|
||||
- "POST-001: returns StreamingResponse(media_type='text/event-stream'); the admin key never crosses to the browser."
|
||||
- "POST-002: ONLY events passing _admin_event_matches_web(ev, session_id) are forwarded; each is re-emitted under the FIXED SSE event name 'admin_event' with {id,type,timestamp,data} in the payload (the real dotted type rides in the payload, so one browser listener renders every type — nothing silently dropped by name)."
|
||||
- "POST-003: SseConnectFailed/SseConnectionDropped/MalformedSseId/MalformedSseData -> a single 'stream_error' SSE frame, then the stream ends (best-effort; never raises to the browser)."
|
||||
- "POST-004: asyncio.CancelledError (browser disconnect) re-raises to unwind the generator; the upstream client is aclose()'d in finally on every exit path."
|
||||
steps: "If not admin_key -> 400. gen(): open client; async-for ev in stream_admin_events(admin_key); skip unless _admin_event_matches_web; yield _format_sse('admin_event', {...}). Except SSE errors -> yield stream_error. Except CancelledError -> raise. Finally aclose(). Return StreamingResponse(gen())."
|
||||
flexibility: "prescriptive"
|
||||
|
||||
- name: "create_app (amendment)"
|
||||
signature: "create_app(client_factory, *, end_user_id=None, bifrost_consumer_key=None, bifrost_visible_host=None, affect_read_url=None, admin_key=None) -> Starlette"
|
||||
description: "New optional admin_key param stored at app.state.admin_key; entrypoint passes RATATOSKR_ADMIN_API_KEY. Three new routes registered."
|
||||
postconditions:
|
||||
- "POST-001: app.state.admin_key = admin_key (default None -> the two admin routes fail-visible per their PRE-001)."
|
||||
- "POST-002: routes /api/sessions/{session_id}/tools, /api/sessions/{session_id}/bifrost, /api/admin/events added; existing routes unchanged."
|
||||
flexibility: "closed"
|
||||
|
||||
- name: "reasoning indicator (index.html: showThinkingNote / hideThinkingNote)"
|
||||
signature: "showThinkingNote() ; hideThinkingNote() // called from the turn SSE loop"
|
||||
description: "Ephemeral transcript affordance signalling reasoning inference — clearly NOT engine output."
|
||||
postconditions:
|
||||
- "POST-001: on the first `thinking` delta, an italic '<Agent> <phrase>' line (✦ glyph, rotating phrase) is shown; it supersedes any live 'awaiting first token' heartbeat."
|
||||
- "POST-002: the agent display name is derived from state.agentId and rendered via textContent (NEVER innerHTML) — INV-004 holds even for an adversarial agent_id."
|
||||
- "POST-003: it is removed the instant the first `text` delta arrives, and on any terminal (done/error/cancelled); the rotation interval is cleared on removal (no leaked setInterval)."
|
||||
flexibility: "prescriptive"
|
||||
|
||||
- name: "PAD refresh poll (index.html: terminal() done-branch)"
|
||||
signature: "on Done: poll loadPersona over [1500,3500,6500,10500]ms"
|
||||
description: "Catch the post-turn-async affect.emit without racing it (replaces the single 2s shot)."
|
||||
postconditions:
|
||||
- "POST-001: loadAffect sets state.lastAffectAt = snap.emitted_at; the poll captures beforeAt and stops (settled) once state.lastAffectAt !== beforeAt."
|
||||
- "POST-002: a scheduled poll no-ops if a NEW turn has started (state.turnId truthy) or already settled — no refresh of a stale agent, no unbounded polling."
|
||||
flexibility: "open"
|
||||
|
||||
- name: "loadTranscript (index.html)"
|
||||
signature: "async loadTranscript(sessionId) -> void"
|
||||
description: "On session open, GET /api/sessions/{id}/messages and render each EXISTING turn into #transcript — notably a #347 authored first-message seeded at create-time (which lives in the ledger, not the live turn stream, so without this the transcript is blank until the user speaks)."
|
||||
postconditions:
|
||||
- "POST-001: assistant items render as a .response .md-body bubble via markdownSafe(content) (escape-first whitelist, same path as appendResponse); user items render as a .prompt-echo via textContent — no upstream content reaches innerHTML unescaped (INV-004)."
|
||||
- "POST-002: any non-200, fetch error, or parse error is swallowed (best-effort) — a blank transcript is acceptable; opening the workspace is never blocked."
|
||||
flexibility: "prescriptive"
|
||||
|
||||
- name: "web pane renderers (v0.20.0: index.html: renderToolsInventory / renderBifrost / openAdminEvents + tickerAdd)"
|
||||
signature: "renderToolsInventory(inv) ; renderBifrost(b) ; openAdminEvents(sessionId) ; tickerAdd(kind, msg, dim)"
|
||||
description: "Render the debug/admin surfaces into the 3-column console; all content escaped (INV-004). v0.20.0: BifrostState is now a full-detail LEFT-RAIL pane (renderBifrost, renamed from renderBifrostState); AdminEvents + the raw debug/op log + tool_start/result + turn lifecycle are MERGED into one engine-ticker timeline via tickerAdd (openAdminEvents routes admin_event → tickerAdd; the turn SSE handlers route worker_phase/tool/text_boundary/affect_update → tickerAdd); Tools inventory is a rail chip list (renderToolsInventory)."
|
||||
postconditions:
|
||||
- "POST-001: every dynamic value (agent_id, tool names/descriptions, endpoint, caps, consumer_id, admin event type + data, ticker msg/dim) is passed through esc() or esc(JSON.stringify(...)); no upstream string reaches innerHTML unescaped."
|
||||
- "POST-002: openAdminEvents closes a prior EventSource before opening a new one (state.adminES) and, on stream_error, closes so native EventSource does NOT retry-loop; admin events render into the engine ticker via tickerAdd."
|
||||
- "POST-003: renderToolsInventory renders builtin + bifrost tool NAMES as rail chips (a compact 'what does the LLM have' glance); renderBifrost renders endpoint + connected + consumer_id + capabilities_granted chips + per-tool name/description rows (the full detail, admin-gated; the admin key stays server-held). tickerAdd bounds the feed to the last 400 rows (a tail, not an archive)."
|
||||
- "POST-004: tool NAME-vs-DESCRIPTION split preserved — the rail chip list shows names only; per-tool descriptions live in the Bifrost pane's tools list. The engine-ticker spine (.ticker-inner::before) lives on the content-height wrapper so it stays visible when auto-scrolled to the newest entry."
|
||||
flexibility: "open"
|
||||
|
||||
- name: "renderConsole + trend (v0.20.0 — unified persona/affect console; supersedes renderAffectPane/renderPersonaPane/setPersonaStrip)"
|
||||
signature: "renderConsole(snap) ; setFader(axis,v) ; setFaderTrend(axis) ; renderOrbit() ; renderDominant(snap) ; renderDerived(snap) ; renderRelations(snap) ; renderDirective(snap) ; pushAffectHistory(snap) ; sparkPointsH(vals,w,h,endX) ; stripPoints(vals) ; proj3(p,a,d) ; trendDelta(vals)"
|
||||
description: "ONE render path for BOTH the Tier-1 persona_state snapshot and the Tier-3 affect snapshot (renderConsole), feeding the right affect console: dominant/canonical-mood centerpiece, bipolar PAD faders (each with a turn-to-turn Δ + sparkline), a P×A mood orbit from PAD history, an affect-derived grid, relations metric rows, and the canonical directive. Replaces the v0.19.x split of renderPersonaPane (Tier-1 pane) + renderAffectPane (Tier-3 pane) + setPersonaStrip (top-bar strip, removed — PAD now lives in the console faders)."
|
||||
postconditions:
|
||||
- "POST-001: reads snap.relations (relation_edge/1: target_entity + trust_ability/benevolence/integrity + warmth as {value,confidence,evidence_count} + agency + relation_context) — the CURRENT Worldtree emit shape; falls back to the legacy flat snap.valence for an older emitter. Tier-1 fields (baseline_pad, mood_drift, dominant_emotion, emotions_active) render WHEN PRESENT, '—' when absent (Tier-3 lacks them)."
|
||||
- "POST-002: SVG sparklines (v0.20.4, adapted from the design prototype; replace the unicode strings). Each PAD fader shows current value + Δ-vs-previous (▲/▼) + a VERTICAL SVG strip (`stripPoints`, 26×132, time down Y newest-at-bottom, value on X ±11, gradient-faded via stripFade{P,A,D}, dot at newest). Each relation metric shows a HORIZONTAL SVG sparkline (`sparkPointsH`, 56×13, auto-scaled to its OWN range, sparkFade gradient + end dot). renderOrbit is now a 3D ISOMETRIC P×A×D cube (`proj3`: P right-down / A left-down / D up, 2:1 iso, center 62,66, scale 26) plotting the trajectory + a pulsing now-marker + a drop line to the D=−1 floor + a floor shadow ellipse (depth cue). All drawn from AFFECT_HIST (rolling, HIST_CAP=24, session-lived); sparkline coords are computed numerics (no upstream strings → INV-004 trivially held). Gradients live in one hidden `<defs>` svg in the console."
|
||||
- "POST-003: pushAffectHistory dedupes by emitted_at||last_updated_at so the ~4x/turn post-turn PAD poll contributes ONE sample/turn; history is CLIENT-side only (lost on reload — durable cross-session history via a provider-side snapshot log is a deferred follow-up, NOT built here)."
|
||||
- "POST-004: INV-001 honesty — no fabricated Tier-1 fields. The dominant-emotion centerpiece shows a real OCC dominant_emotion (Tier-1) OR the CANONICAL mood word from canonMood(pad) (Tier-3, dimmed) OR '—'; NEVER a synthesized emotion. The affect-derived grid drops non-emitted metrics (intensity/decay-τ) and shows only real/client-derived cells (baseline/drift real for Tier-1, client-derived samples/volatility). INV-004 — every dynamic value passes through esc(); numerics go through toFixed, never innerHTML-raw."
|
||||
flexibility: "open"
|
||||
|
||||
- name: "canonical affect-NL + context-injection reconstruction (v0.19.5 canons; v0.20.2 full context-injection panel)"
|
||||
signature: "canonMood(pad) ; canonDirective(rel) ; canonPadFallback(pad) ; canonEmotionDirective(type) ; renderDirective(snap) ; loadPersonaCanon()"
|
||||
description: "Reconstruct + render the HIDDEN affect-context block Worldtree assembles into the agent's system prompt (never on any wire) — byte-exact to Worldtree's own describe_pad + render_d2_canonical + derive_directive + _pad_band_fallback. The v0.20.2 'context injection' panel shows the full block: mood descriptor + mood directive + relationship directive. Reference: docs/vendor/worldtree-persona-canon/affect-egress-consumer-reference.md (pinned)."
|
||||
postconditions:
|
||||
- "POST-001: DETERMINISTIC, no LLM. canonMood mirrors describe_pad (valence×arousal grid + strict ±0.3 bands + dominance clause); canonDirective mirrors render_d2_canonical; canonPadFallback mirrors renderer._pad_band_fallback BYTE-EXACT (P×A quadrant: hi/lo/mid arousal band × p>0.3/<-0.3/neutral, with the negative_low_dominance (d<-0.3) special case + neutral_high_a + default); canonEmotionDirective is the occ_directives[type].directive lookup (+ tier / full_only flag)."
|
||||
- "POST-002: the canon DATA is VENDORED (docs/vendor/worldtree-persona-canon/{d2-mood-render-canon-v1,d2-render-canon-v1}.json), pinned drift-gated in .corviduo-canonicals.toml; the flat browser form (static/persona_render_canon.json, served /static) is regenerated by scripts/build_persona_canon.py via Worldtree's OWN authoritative loader — v0.20.2 extended it to emit mood_directive {occ_directives, pad_band_fallback, salience, pad_band_cutoff, full_only}. The affect-egress consumer reference is pinned tolerate_drift (worldtree-affect-egress-consumer-reference-v1; worldtree-dev co-signs + pings on change)."
|
||||
- "POST-003: fail-open — canon absent (fetch fails) → the reconstructed lines OMIT, the structured console still renders. Every canon-derived string is esc()'d before the DOM (INV-004)."
|
||||
- "POST-004: HONEST-PARTIAL provenance (affect-egress-reference §3). The mood descriptor + relationship directive are EXACT (tagged 'exact'); the mood DIRECTIVE is a CANDIDATE pair (tagged 'candidate') — the OCC emotion directive for the delivered dominant_emotion type AND the PAD-band fallback — because affect.emit is type-only (no intensity) so the salience gate (≥0.2) can't be evaluated; BOTH are shown with the 'injected if intensity ≥ salience' caveat, never asserting which fires. When dominant_emotion is absent the fallback alone is EXACT. The panel is labeled reconstructed + hidden-from-consumers + dev-only (the reference-impl's sanctioned understand/reconstruct use, NOT end-user display per the reference's caveat). WATCH: a pending Worldtree render_d2_canonical change conditionally drops the trailing 'avoid premature we-framing' clause under a 3-gate combo — canonDirective holds as-is until worldtree-dev pings with the exact conditional + a canon bump."
|
||||
flexibility: "open"
|
||||
|
||||
invariants:
|
||||
- "INV-004 (untrusted-render): ALL model / tool / admin / agent-supplied text is escaped before entering the DOM (esc via textContent, or esc(JSON.stringify)). No new render path introduces an innerHTML sink for upstream content. This is the highest-value review target — the new JS render paths are NOT unit-tested."
|
||||
- "INV-ADMIN-KEY: the admin key exists ONLY at app.state.admin_key (from RATATOSKR_ADMIN_API_KEY). It is never serialized into any response, never sent to the browser, never logged. The browser receives only the session-filtered RESULT of admin-scoped reads."
|
||||
- "INV-FILTER: AdminEvents filtering happens SERVER-side (_admin_event_matches_web) — the browser never receives the cross-session admin firehose; only active-session events + non-heartbeat system.* cross the wire."
|
||||
- "INV-FAIL-VISIBLE: both admin routes return 400 admin_key_not_configured when the key is absent — never a silent empty pane, never an upstream call with an empty bearer."
|
||||
- "INV-LIFECYCLE: SSE generators and EventSources are cleaned up on every exit path (upstream client aclose() in finally; setInterval cleared in hideThinkingNote; prior EventSource closed before re-open) — no leaked connections, tasks, or timers."
|
||||
- "INV-ADDITIVE: existing routes, panes, and the turn-stream path are unchanged; the 3 new routes + 2 new tabs are purely additive (59 web tests incl. all prior ones stay green)."
|
||||
---
|
||||
|
||||
# v0.19.2 — web debug-surface parity (BifrostState · AdminEvents · Tools · PAD-poll · reasoning)
|
||||
|
||||
## Context
|
||||
|
||||
The browser surface is now the operator's PRIMARY debug surface, and it lagged the
|
||||
TUI: the TUI gained Tools/BifrostState/AdminEvents panes (v0.18.9–.11) that were never
|
||||
ported to the web. This change closes that gap and adds two transcript affordances (a
|
||||
reliable PAD refresh + a reasoning indicator). The client wrappers already existed and
|
||||
are contracted elsewhere; this contract governs the WEB proxy routes + the SPA presenter
|
||||
paths, whose JS render code is not unit-tested — hence the cross-frontier code review.
|
||||
|
||||
## Review focus (for the heid panel)
|
||||
|
||||
1. **INV-004 escaping** in every new render path — the un-unit-tested surface; the exact
|
||||
class of bug (`renderPersonaPane` fabricating a Tier-1 field) that only a cross-model
|
||||
review caught on #18 D2.
|
||||
2. **INV-ADMIN-KEY** — confirm the admin key never reaches a response body or the browser.
|
||||
3. **AdminEvents SSE proxy** (`_admin_events_endpoint`) — generator/filter/lifecycle: fixed
|
||||
event name, server-side filter, `stream_error` on failure, `aclose()` on every path,
|
||||
`CancelledError` re-raise on disconnect.
|
||||
4. **PAD-poll** stop-condition — does `emitted_at` advancement + the `state.turnId` guard
|
||||
correctly stop the poll without racing or leaking timers?
|
||||
5. **Reasoning indicator** lifecycle — shown on first `thinking`, removed on first `text`
|
||||
or terminal, interval cleared (no leaked `setInterval`), name via `textContent`.
|
||||
@@ -1,6 +1,50 @@
|
||||
{
|
||||
"components": {
|
||||
"schemas": {
|
||||
"AuthoredTurnResponse": {
|
||||
"description": "#347 — the authored-write ack. Provenance is audit-only and NEVER on this\npayload (INV-347-7). ``content_chars`` is the CHARACTER count (may differ from\nthe UTF-8 byte length the request is bounded against — INV-347-12).",
|
||||
"properties": {
|
||||
"author": {
|
||||
"title": "Author",
|
||||
"type": "string"
|
||||
},
|
||||
"content_chars": {
|
||||
"title": "Content Chars",
|
||||
"type": "integer"
|
||||
},
|
||||
"injected_at": {
|
||||
"title": "Injected At",
|
||||
"type": "string"
|
||||
},
|
||||
"phase": {
|
||||
"title": "Phase",
|
||||
"type": "string"
|
||||
},
|
||||
"seq": {
|
||||
"title": "Seq",
|
||||
"type": "integer"
|
||||
},
|
||||
"session_id": {
|
||||
"title": "Session Id",
|
||||
"type": "string"
|
||||
},
|
||||
"turn_id": {
|
||||
"title": "Turn Id",
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"turn_id",
|
||||
"session_id",
|
||||
"author",
|
||||
"phase",
|
||||
"seq",
|
||||
"injected_at",
|
||||
"content_chars"
|
||||
],
|
||||
"title": "AuthoredTurnResponse",
|
||||
"type": "object"
|
||||
},
|
||||
"BifrostBindingRequest": {
|
||||
"additionalProperties": false,
|
||||
"description": "Bifrost binding parameters for session-create (issue #160).",
|
||||
@@ -390,6 +434,7 @@
|
||||
"session_not_found",
|
||||
"session_not_bifrost_bound",
|
||||
"session_retired",
|
||||
"generation_active",
|
||||
"agent_not_available",
|
||||
"turn_not_found",
|
||||
"turn_finished",
|
||||
@@ -905,7 +950,7 @@
|
||||
"info": {
|
||||
"description": "Multi-turn conversation interface for Worldtree agents.",
|
||||
"title": "Worldtree Conversation API",
|
||||
"version": "2.2.0"
|
||||
"version": "2.3.0"
|
||||
},
|
||||
"openapi": "3.1.0",
|
||||
"paths": {
|
||||
@@ -6382,6 +6427,141 @@
|
||||
"summary": "Update Session"
|
||||
}
|
||||
},
|
||||
"/sessions/{session_id}/history": {
|
||||
"post": {
|
||||
"description": "#347 — write one model-visible turn into a session's ledger AS the bound\nagent, WITHOUT a generation and WITHOUT lived-turn side effects.\n\nHide-existence ordering (INV-347-13): the ``session.history.write`` grant is\nchecked FIRST — before session resolution, before ANY body parse/validation,\nbefore the active-generation guard. An ungranted caller receives ONLY the\nhide-404 (byte-identical to session-not-found, INV-347-1) — never a\n422/409/403 that would distinguish feature-absent from session-absent.",
|
||||
"operationId": "authored_history_write_sessions__session_id__history_post",
|
||||
"parameters": [
|
||||
{
|
||||
"in": "path",
|
||||
"name": "session_id",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"title": "Session Id",
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
],
|
||||
"responses": {
|
||||
"201": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/AuthoredTurnResponse"
|
||||
}
|
||||
}
|
||||
},
|
||||
"description": "Successful Response"
|
||||
},
|
||||
"400": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ErrorResponse"
|
||||
}
|
||||
}
|
||||
},
|
||||
"description": "Error — unified envelope (detail.error_code is the stable identifier)."
|
||||
},
|
||||
"401": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ErrorResponse"
|
||||
}
|
||||
}
|
||||
},
|
||||
"description": "Error — unified envelope (detail.error_code is the stable identifier)."
|
||||
},
|
||||
"403": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ErrorResponse"
|
||||
}
|
||||
}
|
||||
},
|
||||
"description": "Error — unified envelope (detail.error_code is the stable identifier)."
|
||||
},
|
||||
"404": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ErrorResponse"
|
||||
}
|
||||
}
|
||||
},
|
||||
"description": "Error — unified envelope (detail.error_code is the stable identifier)."
|
||||
},
|
||||
"405": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ErrorResponse"
|
||||
}
|
||||
}
|
||||
},
|
||||
"description": "Error — unified envelope (detail.error_code is the stable identifier)."
|
||||
},
|
||||
"409": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ErrorResponse"
|
||||
}
|
||||
}
|
||||
},
|
||||
"description": "Error — unified envelope (detail.error_code is the stable identifier)."
|
||||
},
|
||||
"412": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ErrorResponse"
|
||||
}
|
||||
}
|
||||
},
|
||||
"description": "Error — unified envelope (detail.error_code is the stable identifier)."
|
||||
},
|
||||
"422": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ErrorResponse"
|
||||
}
|
||||
}
|
||||
},
|
||||
"description": "Error — unified envelope (detail.error_code is the stable identifier)."
|
||||
},
|
||||
"500": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ErrorResponse"
|
||||
}
|
||||
}
|
||||
},
|
||||
"description": "Error — unified envelope (detail.error_code is the stable identifier)."
|
||||
},
|
||||
"503": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ErrorResponse"
|
||||
}
|
||||
}
|
||||
},
|
||||
"description": "Error — unified envelope (detail.error_code is the stable identifier)."
|
||||
}
|
||||
},
|
||||
"security": [
|
||||
{
|
||||
"HTTPBearer": []
|
||||
}
|
||||
],
|
||||
"summary": "Authored History Write"
|
||||
}
|
||||
},
|
||||
"/sessions/{session_id}/messages": {
|
||||
"get": {
|
||||
"description": "Return paginated message history for a session.",
|
||||
|
||||
@@ -2699,10 +2699,13 @@ The `turn.started` event always carries `bifrost_override_applied: bool` (True/F
|
||||
|
||||
Tier 3 agents are consumer-owned, Worldtree-hosted agents whose
|
||||
identity lives at `<user_id>:<agent_name>`. They share the persistent
|
||||
session infrastructure with Tier 1 / Tier 2 but layer-specific
|
||||
machinery (persona, motivational, memory, valence) is reserved for
|
||||
later phases — Phase 2.0 ships baseline addressing + ownership +
|
||||
lifecycle only.
|
||||
session infrastructure with Tier 1 / Tier 2. The layer-specific
|
||||
machinery is now largely active: **`persona` (Phase 2.1, #186),
|
||||
`memory` (Phase 2.1, #197), and `motivational` (Phase 2.2, #187) are
|
||||
shipped and consumer-settable at define-time.** Only **`valence` remains
|
||||
deferred** (non-null → 422 `layer_deferred`). Phase 2.0 shipped the
|
||||
baseline addressing + ownership + lifecycle substrate; the subsections
|
||||
below document the active layers and their exact validated shapes.
|
||||
|
||||
### Endpoints
|
||||
|
||||
@@ -2720,11 +2723,13 @@ lifecycle only.
|
||||
{
|
||||
"agent_name": "wizard",
|
||||
"system_prompt": "You are a guided-elicitation wizard...",
|
||||
"model": "glm5-turbo",
|
||||
"persona": null, // schema-reserved; non-null → 422 layer_deferred
|
||||
"motivational": null,
|
||||
"valence": null,
|
||||
"memory": null
|
||||
"role": "gen-reasoning", // REQUIRED — a configured model-role (#344), not a raw model id
|
||||
"persona": { // active (Phase 2.1) — single-letter OCEAN keys; see "Persona layer"
|
||||
"ocean": {"O": 0.4, "C": 0.6, "E": -0.3, "A": 0.2, "N": 0.5}
|
||||
},
|
||||
"motivational": null, // active (Phase 2.2) — see "Motivational layer"
|
||||
"memory": null, // active (Phase 2.1) — see "Memory layer"
|
||||
"valence": null // still deferred — non-null → 422 layer_deferred
|
||||
}
|
||||
```
|
||||
|
||||
@@ -2756,6 +2761,150 @@ after definition.
|
||||
The 201 response includes an advisory `warnings` array (#219) — see
|
||||
"Model-assignment warnings" under `PATCH` below.
|
||||
|
||||
> **Vendoring note (OpenAPI 2.3.0).** In the frozen OpenAPI 2.3.0 document
|
||||
> the `persona` / `motivational` / `memory` / `valence` request fields
|
||||
> serialize as **untyped/freeform** — the `POST /agents/define` request
|
||||
> model types them as `Any` so the layers can activate without a
|
||||
> schema-breaking change. The shapes documented in the subsections below
|
||||
> are the **authoritative, validator-enforced** schemas; generate client
|
||||
> types from this section, not from the freeform OpenAPI fields.
|
||||
|
||||
##### Persona layer (Phase 2.1, #186)
|
||||
|
||||
`persona` is **active** as of Phase 2.1. It carries the agent's OCEAN
|
||||
personality vector — the durable trait profile from which Worldtree
|
||||
derives the mood setpoint (`baseline_pad`) and the mood dynamics
|
||||
(gain + relaxation time-constants). Shape:
|
||||
|
||||
```json
|
||||
"persona": {
|
||||
"ocean": { // REQUIRED — exactly these 5 keys, no more, no fewer
|
||||
"O": 0.4, // Openness — float in [-1.0, 1.0]
|
||||
"C": 0.6, // Conscientiousness
|
||||
"E": -0.3, // Extraversion
|
||||
"A": 0.2, // Agreeableness
|
||||
"N": 0.5 // Neuroticism
|
||||
},
|
||||
"behavioral_notes": "...", // optional, ≤ 4096 chars
|
||||
"temperament_notes": "..." // optional, ≤ 4096 chars
|
||||
}
|
||||
```
|
||||
|
||||
**⚠ OCEAN key format — single-letter, uppercase.** The `/agents/define`
|
||||
persona validator requires the `ocean` map to contain **exactly** the five
|
||||
uppercase single-letter keys `O, C, E, A, N`. This is a deliberate,
|
||||
load-bearing contrast with the transient-character primitive
|
||||
(`POST /characters`), whose `ocean` block uses the **spelled-out**
|
||||
lowercase keys (`openness`, `conscientiousness`, …). Sending spelled-out
|
||||
keys to `/agents/define` returns 422 `persona_ocean_required` ("must
|
||||
contain exactly the 5 keys O, C, E, A, N").
|
||||
|
||||
> **Fixed in v1.0.0b21 (#348).** Before that build a correctly
|
||||
> single-letter-keyed persona was accepted and stored, but resolved to a
|
||||
> **neutral** mood, because Worldtree's internal mood-derivation read the
|
||||
> spelled-out key form. On v1.0.0b21+ an API-declared persona correctly
|
||||
> drives the derived mood setpoint. If you observe neutral mood on a
|
||||
> persona-defined agent, confirm the deployment is ≥ v1.0.0b21.
|
||||
|
||||
**Range.** Each value is a float in `[-1.0, 1.0]` **signed** — `0.0` is the
|
||||
population mean, NOT `[0.0, 1.0]`. Booleans are rejected. Out-of-range → 422
|
||||
`persona_ocean_out_of_range`. See [`docs/ocean-traits.md`](ocean-traits.md)
|
||||
for the SOTA-grounded 5-band behavioural mapping.
|
||||
|
||||
Semantics:
|
||||
|
||||
- **Per-agent identity trait** — identical for every end-user and session;
|
||||
immutable post-define (`PATCH {"persona": …}` → 422 `field_not_mutable`).
|
||||
To change the OCEAN profile, delete and re-define the agent.
|
||||
- **`extensions` is reserved** — the field exists but must be empty at v0.1;
|
||||
a non-empty `extensions` returns 422 `layer_deferred`.
|
||||
- **Sets the mood SETPOINT, not the current mood.** The OCEAN vector fixes
|
||||
`baseline_pad` (the PAD point the mood relaxes toward over time); the
|
||||
*current* per-session mood point is seeded separately via
|
||||
`POST /sessions/{id}/persona_state` (below).
|
||||
|
||||
Validation 422 codes: `persona_ocean_required` (missing `ocean`, or keys
|
||||
≠ {O,C,E,A,N}), `persona_ocean_out_of_range` (a value outside [-1.0, 1.0], or
|
||||
a boolean), `persona_notes_too_large` (a note > 4096 chars), `layer_deferred`
|
||||
(non-empty `extensions`), `validation_failed` (unknown top-level field).
|
||||
|
||||
##### `POST /sessions/{session_id}/persona_state` — seed the session mood point (Phase 2.1, #186/#189)
|
||||
|
||||
Session-scoped mood seed. Sets the *current* PAD mood point for one
|
||||
session's bound agent — the starting emotional state, distinct from the
|
||||
OCEAN-derived setpoint the mood relaxes toward. Works on any
|
||||
persona-enabled session (Tier 1 or Tier 3); most useful for a Tier 3
|
||||
durable-agent session that wants to start a conversation from a specific
|
||||
mood.
|
||||
|
||||
Request:
|
||||
|
||||
```json
|
||||
{
|
||||
"pad": {
|
||||
"pleasure": 0.42, // float in [-1.0, 1.0]
|
||||
"arousal": 0.25,
|
||||
"dominance": 0.33
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Response: **`204 No Content`** — no body, no audit event (a session-scoped
|
||||
runtime overlay, not a security-relevant event).
|
||||
|
||||
Semantics:
|
||||
|
||||
- **PAD-only** (#317 Option A). The body accepts exactly one key, `pad`,
|
||||
which must carry all three of `pleasure` / `arousal` / `dominance`, each a
|
||||
float in `[-1.0, 1.0]`. Any other top-level key → 422 `validation_failed`;
|
||||
a missing or malformed `pad` → 422 `persona_seed_invalid`.
|
||||
- **Seeds the current mood POINT, not the setpoint.** The OCEAN persona
|
||||
(above) fixes the setpoint the mood relaxes toward; this endpoint sets
|
||||
where the mood *starts*. It does not alter the persona.
|
||||
- **Cross-owner sessions return 404** (existence-hiding — a session that
|
||||
isn't yours is indistinguishable from one that doesn't exist).
|
||||
- **Pull-over-push precedence (#289).** Once a session's baseline has been
|
||||
rehydrated from an `affect.fetch` (the authoritative cross-session
|
||||
source), a later SET seed is silently ignored — the fetched baseline wins.
|
||||
|
||||
There is **no** `POST /agents/{id}/persona_state` — mood is per-session, not
|
||||
a durable agent property. `GET /agents/{agent_id}/persona_state`
|
||||
short-circuits to 404 for Tier-3 colon-ids: Tier-3 mood is observable only
|
||||
over the Bifrost `affect.emit` egress (ADR-0009), never read back through
|
||||
the HTTP API.
|
||||
|
||||
##### Memory layer (Phase 2.1, #197)
|
||||
|
||||
`memory` is **active** as of Phase 2.1 but exposes a deliberately minimal
|
||||
surface — the short-term-memory (STM) tier was removed (#197), so the
|
||||
historically-present `stm_*` knobs are accept-and-ignore no-ops. Shape:
|
||||
|
||||
```json
|
||||
"memory": {
|
||||
"embedder_version": "<pinned>", // optional; MUST equal the library-pinned version
|
||||
"tier3_dreaming": false // optional bool, default false
|
||||
}
|
||||
```
|
||||
|
||||
Semantics:
|
||||
|
||||
- **`embedder_version`** — optional. If supplied it MUST equal the library's
|
||||
currently-pinned embedder version; a mismatch → 422
|
||||
`embedder_version_mismatch` (with `expected` / `received` in the detail).
|
||||
Omit it to accept the pin. Fixed at define-time and library-pinned
|
||||
thereafter.
|
||||
- **`tier3_dreaming`** — optional bool (default `false`); opt-in flag for the
|
||||
Tier-3 dreaming / consolidation path.
|
||||
- **`stm_capacity` / `stm_token_budget`** — **deprecated no-ops.** Accepted at
|
||||
define (201) with a `DeprecationWarning`; they carry no runtime effect since
|
||||
the STM tier was removed, and are slated for rejection at the next schema
|
||||
break. Do not send them in new integrations.
|
||||
- **`allows_world_scope` — removed.** Sending it → 422 `validation_failed`
|
||||
("world-shared knowledge belongs in the KB/Mimir plane").
|
||||
- **Wholesale-immutable post-define.** `PATCH {"memory": …}` → 422
|
||||
`field_not_mutable` (even for the deprecated `stm_*` fields) — see the
|
||||
PATCH table above.
|
||||
|
||||
##### Motivational layer (Phase 2.2, #187)
|
||||
|
||||
`motivational` is **active** as of Phase 2.2 (persona + memory activated in
|
||||
|
||||
+56
-35
@@ -19,7 +19,7 @@ anchors against the frozen machine-readable artifacts, NOT the prose markdown:
|
||||
|
||||
| Worldtree v1 surface | Frozen anchor | Ratatoskr role |
|
||||
|---|---|---|
|
||||
| Conversation REST API | OpenAPI `info.version` **2.2.0** (`Worldtree/docs/conversation-api-openapi.json`, sha `dbdf4e24…`) — **40 path×method groups** | **client** (debug TUI / web) |
|
||||
| Conversation REST API | OpenAPI `info.version` **2.3.0** (`Worldtree/docs/conversation-api-openapi.json`, sha `36148179…`) — **41 path×method groups** (2.3.0 added `POST /sessions/{id}/history`, #347) | **client** (debug TUI / web) |
|
||||
| Conversation SSE events | `conversation-api-sse-events.schema.json` (sha `9deeebf4…`) — **11 discriminated event types** | **client** |
|
||||
| Bifrost wire (consumer protocol) | wire **v0.6** STABLE/FROZEN (`bifrost==1.0.0`) — memory + affect planes | **provider** (Worldtree dispatches into us) |
|
||||
|
||||
@@ -48,7 +48,7 @@ resolved (§ Surface 1, scope-resolution table).
|
||||
|
||||
| Surface | Points | ✅ covered-live | ⬜ gap (in-scope) | 🚫 excluded-by-design |
|
||||
|---|---|---|---|---|
|
||||
| REST (OpenAPI 2.2.0, path groups) | 40 | 7 | 11 | 22 |
|
||||
| REST (OpenAPI 2.3.0, path groups) | 41 | 19 | 0 | 22 |
|
||||
| SSE events | 11 | 11 | 0 | 0 |
|
||||
| Bifrost provider planes | 8 verbs | 8 | 0 | (10 gated verbs deferred) |
|
||||
|
||||
@@ -61,7 +61,7 @@ sub-gap).
|
||||
|
||||
---
|
||||
|
||||
## Surface 1 — Conversation REST API (OpenAPI 2.2.0)
|
||||
## Surface 1 — Conversation REST API (OpenAPI 2.3.0)
|
||||
|
||||
### Covered — client path (ratatoskr's core identity)
|
||||
|
||||
@@ -69,12 +69,24 @@ sub-gap).
|
||||
|---|---|---|---|
|
||||
| `POST /sessions` | ✅ | `sessions.py:307` → `cli.py:482`,`tui.py:1508`,`web/server.py:155` | + `end_user_id`, `bifrost` binding; 404→AgentNotFound, 502→BifrostHandshakeFailed |
|
||||
| `POST /sessions/{id}/messages` (turn stream, SSE) | ✅ | `sse_client.py:484` `stream_turn` → cli/tui/web | the primary surface; 409→AgentNotAvailable, 503→TurnLaunchUnavailable (b2 #331) |
|
||||
| `POST /sessions/{id}/history` (authored-history-write, #347) | ✅ | `sessions.py:583` `write_authored_history` → `cli.py:758` `--seed-first-message` | v1: author=assistant, effects=none, per-session idempotency; 404→AuthoredHistoryUnavailable (hide-existence: feature-absent, never probe); 409/422 mapped. **LIVE-PROVEN 2026-07-06** on personal :8081 (grant applied via a rule-based Heimdall allow, worldtree-dev): create mimir session → seed → **201** (seq=0, phase=seeded, turn_id=1798) → GET /messages reads it back as a plain role=assistant turn (model-invisible provenance confirmed). Hide-404 for ungranted is unit+probe covered |
|
||||
| `GET /sessions/{id}/messages` (history) | ✅ | `sessions.py:635` `get_session_messages` → `cli.py:758` `--seed-first-message` read-back | un-deferred as the #347 seed read-back — confirms model-invisible provenance (a seed reads back as a normal `role=assistant` turn) |
|
||||
| `POST /sessions/{id}/turns/{turn_id}/cancel` | ✅ | `sse_client.py:581` → cli/tui/web | two-stage Ctrl-C; 404/409 mapped |
|
||||
| `GET /agents` | ✅ | `sessions.py:341` → `tui.py:1472`,`web/server.py:100` | Tier-1 roster; merged with local index |
|
||||
| `GET /agents/{id}/persona_state` | ✅ | `sessions.py:384` → `tui.py:1132`,`web/server.py:386` | persona hydrate; 404/403 mapped |
|
||||
| `POST /agents/define` | ✅ | `tier3.py:175` → `_run_define` | Tier-3 create |
|
||||
| `PATCH /agents/{id}` | ✅ | `tier3.py:219` → `_run_patch` | Tier-3 mutate (system_prompt/model) |
|
||||
| `DELETE /agents/{id}` | ✅ | `tier3.py:242` → `_run_delete` | Tier-3 hard-delete |
|
||||
| `GET /me` | ✅ | `sessions.py:411` `get_me` → `cli.py` `--whoami` | identity/whoami probe; 401→SessionApiFailed |
|
||||
| `GET /capabilities` | ✅ | `sessions.py:428` `get_capabilities` → `cli.py` `--whoami` | Echo ephemeral-template discovery |
|
||||
| `GET /sessions/{id}/tools` | ✅ | `sessions.py:411` `get_session_tools` → `tui.py` `_hydrate_session_tools` | owner-scoped tool inventory in the TUI Tools pane (#183) |
|
||||
| `GET /admin/sessions/{id}/bifrost` | ✅ | `sessions.py:428` `get_session_bifrost` → `tui.py` `_hydrate_bifrost_state` | admin-scoped BifrostState pane (#176); admin key (`RATATOSKR_ADMIN_API_KEY`); live-auth-proven |
|
||||
| `GET /admin/events` (SSE) | ✅ | `sse_client.py` `stream_admin_events` → `tui.py` `_stream_admin_events` | admin lifecycle SSE stream (#11), session-filtered AdminEvents pane; admin key; live-auth-proven |
|
||||
| `GET /models/available-for-characters` | ✅ | `sessions.py` `list_character_models` → `cli.py` `--characters` | character-capable model profiles (#161) |
|
||||
| `POST /characters` | ✅ | `sessions.py` `create_character` → `cli.py` `--characters` | create transient character (#161) |
|
||||
| `GET /characters/{id}/state` | ✅ | `sessions.py` `get_character_state` → `cli.py` `--characters` | live character PAD/emotions (#161) |
|
||||
| `DELETE /characters/{id}` | ✅ | `sessions.py` `delete_character` → `cli.py` `--characters` | remove transient character (#161) |
|
||||
| `POST /sessions/{id}/persona_state` | ✅ | `sessions.py` `set_persona_state` → `cli.py` `--set-persona-pad` | persona-state write / affect injection (freeform body — unpinned in the frozen surface) |
|
||||
|
||||
**Sub-gaps inside ✅ path groups** (the method we use is live; a sibling method
|
||||
on the same path is an unwired frontier item — see frontier Tier 1):
|
||||
@@ -86,35 +98,34 @@ on the same path is an unwired frontier item — see frontier Tier 1):
|
||||
- `GET /agents/{id}` — consumer-agent lookup (`GET /agents/<owner>:<name>` with
|
||||
the owner key) is **manual-curl-only**, not in code.
|
||||
|
||||
### In-scope gaps — the convergence frontier (debug-observability path)
|
||||
### In-scope gaps — CONVERGED (re-closed 2026-07-06 after the #347 re-open)
|
||||
|
||||
**Tier 1 — the debug-observability core (design-brief'd for v1, unbuilt):**
|
||||
**Every in-scope REST I/O point is covered.** The audit first converged
|
||||
2026-07-01; Worldtree's #347 (authored-history-write, OpenAPI 2.3.0) then added
|
||||
one new in-scope path-group, re-opening the audit with a single gap — now closed
|
||||
(`v0.19.6`). The original frontier (design-brief §5 observability panes +
|
||||
presenter-wiring sub-gaps + Tier-2 tail) remains fully closed:
|
||||
|
||||
| Endpoint | Status | Why in-scope |
|
||||
|---|---|---|
|
||||
| `GET /admin/events` | ⬜ | design-brief §5 v1 **AdminEvents pane**; = issue **#11**, **blocked** on `admin.events.read` scope (infra-ops) |
|
||||
| `GET /admin/sessions/{id}/bifrost` | ⬜ | design-brief §5 v1 **BifrostState widget** — never built; admin-key-gated |
|
||||
| `GET /admin/sessions/{id}/tools` | ⬜ | design-brief §5 v1 **Tools widget** — never built; admin-key-gated |
|
||||
| `GET /capabilities` | ⬜ | server capability discovery — a turn flows through what's advertised |
|
||||
| `GET /me` | ⬜ | whoami / key-identity — "which key am I against" is a debug primitive |
|
||||
| (`GET /sessions` picker · resume) | ⬜ | sub-gaps above — presenter-wiring only, wrappers exist |
|
||||
- Session picker + SSE-resume — wired (`v0.18.5`–`.7`).
|
||||
- Persona · Tools · BifrostState · AdminEvents panes — all built + live (`v0.18.x`–`v0.19.0`).
|
||||
- Transient-characters CRUD + persona-state write — consumed via `--characters` /
|
||||
`--set-persona-pad` (`v0.19.1`).
|
||||
- Authored-history-write (#347) + messages read-back — `write_authored_history` +
|
||||
`get_session_messages` via `--seed-first-message` (`v0.19.6`; live-proof pending
|
||||
the `session.history.write` grant).
|
||||
|
||||
**Tier 2 — rounds out I/O coverage under A (postdates the design-brief):**
|
||||
|
||||
| Endpoint | Status | Why in-scope |
|
||||
|---|---|---|
|
||||
| `GET /sessions/{id}/tools` | ⬜ | Tier-3 owner-scoped tool introspection (#183) — reachable with the **consumer key** (no admin scope), the unblocked tool-introspection path |
|
||||
| `POST /sessions/{id}/persona_state` (write) | ⬜ | affect-injection is debug-relevant; pairs with our provider affect plane |
|
||||
| `POST /characters` · `DELETE /characters/{id}` · `GET /characters/{id}/state` · `GET /models/available-for-characters` | ⬜ | transient-characters (Echo) is a session-creation **routing path** a debug client should be able to drive a turn through |
|
||||
The only remaining not-consumed in-scope method is `GET /agents/{id}` (consumer-
|
||||
agent lookup, manual-curl-only) — a sub-method on an already-✅ path group, not a
|
||||
path-group gap. Everything else is covered or excluded-by-design below.
|
||||
|
||||
### Excluded by design — the design-brief negative clauses
|
||||
|
||||
| Endpoint(s) | Status | Rationale (design-brief / memory) |
|
||||
|---|---|---|
|
||||
| `PATCH /sessions/{id}` · `DELETE /sessions/{id}` | 🚫 | §4: rename/delete happen outside the tool (`sessions_cli.py`) |
|
||||
| `GET /sessions/{id}/messages` (history) | 🚫 | §6: single-session live transcript, no history fetch |
|
||||
| `GET /sessions/{id}` | 🚫 | session detail — identity is footer-visible, no detail view |
|
||||
| `GET /sessions/{id}/tool-events` | 🚫 | §5: tool calls observed **inline from SSE** `tool_start`/`tool_result`; persisted-events endpoint is opt-in only |
|
||||
| `GET /admin/sessions/{id}/tools` | 🚫 | **covered-by-alternative** — the owner-scoped `GET /sessions/{id}/tools` (✅) serves the Tools inventory; this admin variant is only for cross-user operator debug, out of the single-session focus (§6) |
|
||||
| `GET/POST /admin/keys` · `DELETE/POST /admin/keys/{id}` · `POST /admin/keys/{id}/rotate` · `DELETE/POST /admin/keys/bulk` · `POST /admin/keys/bulk/rotate` | 🚫 | §6: **NOT a Worldtree-admin tool** (key mgmt) |
|
||||
| `POST /admin/sessions/{id}/retire` | 🚫 | admin session mutation |
|
||||
| `POST /admin/persona/{archive,erase}` | 🚫 | admin persona GDPR ops (new in b2) |
|
||||
@@ -199,24 +210,34 @@ starts exercising them.
|
||||
|
||||
---
|
||||
|
||||
## Convergence frontier (the v1 to-do)
|
||||
## Convergence frontier (the v1 to-do) — CLOSED 2026-07-01, re-closed 2026-07-06 (#347)
|
||||
|
||||
**Tier 1 — debug-observability core**, in dependency order:
|
||||
**Every in-scope I/O point is covered.** The frontier is empty: REST 19/41 ✅
|
||||
with **zero in-scope gaps** (the other 22 REST path-groups are excluded-by-design),
|
||||
SSE 11/11, Bifrost provider planes 8/8. v1 convergence (per scope A: "every
|
||||
frozen I/O point classified, zero unaccounted") is **met** — ratatoskr cuts v1
|
||||
when Worldtree tags 1.0. The arc, for the record:
|
||||
|
||||
1. **Session picker + SSE-resume** — wrappers exist (`list_sessions`,
|
||||
`reconnect_turn`), need presenter wiring only. **Cheapest; unblocked.**
|
||||
2. **`GET /capabilities` + `GET /me`** — cheap debug primitives. Unblocked.
|
||||
3. **BifrostState + Tools widgets** (`GET /admin/sessions/{id}/{bifrost,tools}`)
|
||||
— design-brief'd v1, unbuilt. Admin-key-gated reads.
|
||||
4. **#11 — AdminEvents pane** — **blocked** on an `admin.events.read` scope grant
|
||||
(infra-ops). The single externally-blocked item; everything else can ship
|
||||
without it.
|
||||
**Tier 1 — debug-observability core:**
|
||||
|
||||
**Tier 2 — rounds out coverage** (lower priority):
|
||||
1. ✅ **DONE** — Session picker (`v0.18.7`) + SSE-resume (`v0.18.5`/`.6`).
|
||||
2. ✅ **DONE** — `GET /capabilities` + `GET /me` (`v0.18.8`, `--whoami`).
|
||||
3. ✅ **DONE** — BifrostState pane (`v0.18.10`, `GET /admin/sessions/{id}/bifrost`,
|
||||
admin-key; live-auth-proven). The Tools half was already covered by the
|
||||
owner-scoped `GET /sessions/{id}/tools` (item 5).
|
||||
4. ✅ **DONE** — AdminEvents pane (`v0.18.11`, `GET /admin/events` SSE,
|
||||
session-filtered; admin-key; live-auth-proven). #11's blocker was already
|
||||
satisfied (admin key carries `admin.events.read`). **Tier 1 complete** — the
|
||||
admin/debug-observability core (Persona · Tools · BifrostState · AdminEvents)
|
||||
is fully built.
|
||||
|
||||
5. **`GET /sessions/{id}/tools`** — owner-scoped tool introspection; consumer-key
|
||||
reachable (no admin scope), so unblocked.
|
||||
6. **Transient-characters routing** (4 endpoints) + **`POST /sessions/{id}/persona_state`**.
|
||||
**Tier 2 — rounds out coverage (all that remains):**
|
||||
|
||||
5. ✅ **DONE** — `GET /sessions/{id}/tools` (`v0.18.9`, owner-scoped tool inventory
|
||||
in the TUI Tools pane).
|
||||
6. ✅ **DONE** — Transient-characters CRUD (4 endpoints) + `POST /sessions/{id}/persona_state`
|
||||
(`v0.19.1`, `--characters` + `--set-persona-pad` one-shot probes). The last
|
||||
in-scope client I/O points.
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -0,0 +1,270 @@
|
||||
# Design brief — `ratatoskr-web` (Worldtree wire monitor)
|
||||
|
||||
> **For:** a visual design pass (Claude Design). **Deliverable:** a single
|
||||
> self-contained HTML prototype, fully populated with representative static
|
||||
> data, that an engineer will wire live data into. **Do not** build a data
|
||||
> layer — build the *shell* and *every state*, beautifully, with placeholder
|
||||
> content in every slot.
|
||||
|
||||
---
|
||||
|
||||
## 1. What you're designing
|
||||
|
||||
`ratatoskr-web` is a **developer-grade debug/observability console** for a
|
||||
conversational-AI engine (Worldtree). Its tagline is *"wire monitor"*: you open
|
||||
a session with an AI agent, send it turns, and **watch that turn flow through
|
||||
every layer of the system at once** — the streaming response, the model's
|
||||
chain-of-thought, the tools it can call, the agent's live emotional/persona
|
||||
state, the provider handshake, and the engine's admin lifecycle events — all
|
||||
side-by-side on one screen.
|
||||
|
||||
**The product IS the observability surface. Chat is just the input.** This is
|
||||
not a chat app, not a marketing page, not an end-user product. The user is one
|
||||
developer (occasionally a few LAN peers) staring at a dense instrument to debug
|
||||
what the engine is doing. Think **oscilloscope / flight-data console / a well-lit
|
||||
`htop`**, not a messaging UI.
|
||||
|
||||
**Design values, in priority order:**
|
||||
1. **Information density earns the screen.** Every region shows live, changing
|
||||
data. Nothing is decorative filler. A quiet, legible, glanceable density is
|
||||
the whole point — the user reads six data streams at a glance.
|
||||
2. **Calm under motion.** Multiple regions update in real time (token streams,
|
||||
live metrics, event logs). The design must stay readable while things move —
|
||||
no jitter, no attention-grabbing per-item animation. Motion is for *state
|
||||
change*, used sparingly.
|
||||
3. **Legibility first.** Monospace, high contrast where it counts, generous but
|
||||
not wasteful spacing. This runs for hours; it must not tire the eye.
|
||||
|
||||
---
|
||||
|
||||
## 2. Aesthetic direction — Australis
|
||||
|
||||
Use the **Australis design system** (a cool-toned, terminal-first dark theme —
|
||||
the `australis-design` skill has the canonical tokens: colors, spacing, radii,
|
||||
shadows, motion). Import/inline `colors_and_type.css`; don't reinvent tokens.
|
||||
|
||||
Non-negotiables from the brand:
|
||||
- **Dark only.** Base is a cool near-black **`#222531` — never pure `#000`.**
|
||||
The eye rests in low-contrast cool grey; **emphasis comes from *brightness*,
|
||||
not saturation.** Layer surfaces up the Sea neutral ramp (`#222531 →
|
||||
`#373b46` → `#414751`).
|
||||
- **Palette families:** *Ice* (surface neutrals), *Aurora* (blue → cyan → green,
|
||||
the primary accents — used generously in that preference order), *Dawn*
|
||||
(red/yellow/magenta — sparingly, for status only). Semantic: info=blue,
|
||||
success=green, warning=yellow, danger=red.
|
||||
- **The signature motif is the aurora glow** — a low-opacity cyan→blue→green
|
||||
light coming *through* the top of the screen, plus a 3px aurora focus ring on
|
||||
interactive controls. Lean into this as the one memorable thing.
|
||||
- **No noise, no textures, no patterns.** *"The screen is the polar sky — empty,
|
||||
with light coming through it."* The one sanctioned gradient is the aurora glow.
|
||||
- **Never a colored left-border on cards** (the LLM-slop trope). Featured cards
|
||||
accent the *top* edge instead.
|
||||
- **Type:** this instrument is **mono-first** — that IS on-brand for Australis
|
||||
("terminal-first"). Use a monospace stack (JetBrains Mono / system mono; see
|
||||
§9 — no web-font CDN allowed). Eyebrows/labels are **mono, UPPERCASE, ~11px,
|
||||
wide-tracked (`0.08–0.16em`)** — use them liberally; they're a system
|
||||
signature.
|
||||
- **Motion:** calm, never bouncy. ~120ms hover, ~200ms state, ~320ms panels.
|
||||
Focus = aurora glow ring. Hover = one step *brighter* (not lower opacity).
|
||||
A slow (8–14s) aurora drift on a hairline top band is welcome; nothing else
|
||||
should loop.
|
||||
|
||||
The current UI already borrows this palette — you're not inheriting it, you're
|
||||
**redesigning the layout and craft from scratch** with the brand as the guide.
|
||||
Feel free to rethink the spatial composition entirely (see §10).
|
||||
|
||||
---
|
||||
|
||||
## 3. The two screens
|
||||
|
||||
### Screen A — **Session setup** (entry)
|
||||
A single centered card on the aurora canvas. Fields:
|
||||
- **Agent** — a `<select>` (populated live; show 3–4 sample options incl.
|
||||
`ratatoskr:sindra`, `forseti`, `mimir`).
|
||||
- **Bifrost binding (Tier-3 provider)** — a `<select>`: `combined (:8392)` /
|
||||
`none — observe only` / `memory (:8391)` / `affect (:8390)`.
|
||||
- **Open session** — primary button.
|
||||
- An error line (design the error state too — e.g. "agent not available").
|
||||
|
||||
### Screen B — **Live workspace** (the main event — 95% of the design effort)
|
||||
Persistent top bar + status line spanning full width; between them a **two-region
|
||||
body: a conversation column (left, dominant) and a telemetry column (right,
|
||||
tabbed).** Current split is ~1.85 : 1 — you may re-proportion. The information
|
||||
inventory below is exhaustive; **every item needs a home.**
|
||||
|
||||
---
|
||||
|
||||
## 4. THE COMPLETE INFORMATION INVENTORY
|
||||
|
||||
This is the core of the brief. Design a slot for **every** item, in a sensible
|
||||
state. Data shapes are given so your placeholders read true.
|
||||
|
||||
### 4.1 Top bar (persistent)
|
||||
| Item | Shape / example | Notes |
|
||||
|---|---|---|
|
||||
| Brand | `ᛯ ratatoskr` + eyebrow `WIRE MONITOR` | the mark is a rune glyph; small |
|
||||
| **Connection status** | one of: `offline`, `connected` (idle), `streaming`, `error` | dot + label; **streaming pulses**; color-coded (grey/green/cyan/red) |
|
||||
| **Persona strip** (appears after a session hydrates) | dominant-emotion word (`love`) + **PAD bars**: `P`, `A`, `D` | each PAD bar is **bipolar** — centered on 0, fills left (negative) or right (positive), value ∈ [−1, 1]; **live-updates every turn** |
|
||||
| Session identity | `ratatoskr:sindra · …381b99f4` | agent id + last-8 of session id |
|
||||
| Bound-plane badge (when bound) | `⇄ combined http://10.100.10.50:8392` | plane + endpoint; only when a Bifrost binding is active |
|
||||
|
||||
### 4.2 Conversation column (the transcript + composer)
|
||||
The transcript is a scrollable stream of turns. Design each element:
|
||||
|
||||
| Element | Example content | Notes |
|
||||
|---|---|---|
|
||||
| **Turn divider** | `TURN 3` between hairlines | uppercase eyebrow, rule lines each side |
|
||||
| **User prompt echo** | `❯ what's your intensity setting?` | the user's message, accent-marked |
|
||||
| **Assistant response** | streaming **Markdown** (headings, bold, italic, `code`, lists, quotes, links) | accumulates token-by-token while live; distinct "live" treatment vs settled |
|
||||
| **Seeded first-message** | a full assistant turn present *before the user speaks* (an authored greeting) | renders **identical to a lived assistant turn** — the session can OPEN already showing the agent's opener |
|
||||
| **Reasoning / "thinking" note** | `✦ sindra is reasoning···` (italic) | **ephemeral** app affordance — appears while the model reasons, vanishes the instant real text begins; visually distinct from the response so it never reads as engine output |
|
||||
| **Awaiting-first-token** | `···` animated | heartbeat before the first token |
|
||||
| **End-of-turn status chips** | `✓ DONE 1.84s` · `✗ ERROR agent_not_available` · `⚠ CANCELLED` · `✗ WIRE lost` | small bordered chips; color per state |
|
||||
| **Composer** (pinned bottom) | `❯ [ message input ] [SEND]` | Enter=send, Shift+Enter=newline; during a turn the Send button becomes **CANCEL** (amber) |
|
||||
|
||||
### 4.3 Telemetry column (six tabbed panes)
|
||||
A tab bar + a pane header (with a **Copy** button) + the active pane body.
|
||||
|
||||
**Tabs** (each: name · keybinding hint · a count **badge** that *flashes* on new
|
||||
data): `TOOLS ^1` · `DEBUG ^2` · `THINK ^3` · `PERSONA ^4` · `BIFROST ^5` ·
|
||||
`ADMIN ^6`. Active tab is accent-marked.
|
||||
|
||||
Pane contents — design each, populated:
|
||||
|
||||
1. **Tools** — the tool inventory the model saw at turn-fire:
|
||||
`agent_id`, `builtin_tools[]` (names), `bifrost_tools[]` (name + description +
|
||||
parameters). Below it, **live tool-call events** stream in (`tool_start` →
|
||||
`tool_result`) as the turn runs. Empty state: `— live tool events —`.
|
||||
2. **Debug** — a raw structured op/lifecycle log (mono lines; new lines flash
|
||||
once). Think `tail -f`.
|
||||
3. **Think** — the model's **full chain-of-thought**, per-turn dividers,
|
||||
live-Markdown. Longer prose than the response.
|
||||
4. **Persona / affect** — *the richest pane.* Contains:
|
||||
- **The canonical NL directive** the engine injects into the agent's context
|
||||
— the literal text: a **mood descriptor** ("neutral", "faintly excited",
|
||||
±0.3 bands) + a **relationship directive**. Show this verbatim, quoted.
|
||||
- **PAD mood point** — pleasure / arousal / dominance current values.
|
||||
- **relations[]** — for each related entity (e.g. the user): **trust**
|
||||
(ability / benevolence / integrity), **warmth**, **agency**,
|
||||
`relation_context` (a tie-type word like "stranger" / "expressive"), each as
|
||||
a **metric row**: `label · value · Δ-since-last (▲/▼) · unicode sparkline ·
|
||||
n (evidence count) · descriptor`. Values are 0–1 with 2–3 decimals.
|
||||
- **dominant_emotion** (an OCC type: joy/anger/fear/…) + **emotions_active[]**.
|
||||
- Design the **metric row** as a reusable component — it's the densest,
|
||||
most-repeated element in the whole UI. Tabular-aligned numbers, a tiny
|
||||
inline sparkline, a subtle up/down Δ.
|
||||
5. **Bifrost** — the live provider binding (admin-gated): `endpoint`,
|
||||
`connected` (bool), `capabilities_granted[]`, `consumer_id`, `tools[]`.
|
||||
**Self-labeling states:** `not configured` (no admin key) / `not bound`
|
||||
(session has no live binding) / an auth-denied state.
|
||||
6. **Admin events** — a live event log of the engine's lifecycle broadcast
|
||||
(a ~17-type vocabulary: `turn.started`, `session.created`, `system.*`, …),
|
||||
filtered to the active session. Streaming; timestamped lines.
|
||||
|
||||
### 4.4 Status line (persistent, bottom)
|
||||
- **Keybinding legend:** `Enter send · ⇧Enter newline · ^1–^6 panes · ^C cancel`
|
||||
(rendered as little `kbd` chips).
|
||||
- **Version:** `ratatoskr 0.19.9` (right-aligned).
|
||||
|
||||
---
|
||||
|
||||
## 5. States to design (show these explicitly)
|
||||
|
||||
Provide a mock (or a toggle) for each — these are where debug UIs live or die:
|
||||
|
||||
- **Setup:** loading-agents · ready · create-error.
|
||||
- **Connection:** offline · connected/idle · streaming (pulsing) · wire-error.
|
||||
- **Turn lifecycle:** awaiting-first-token · reasoning (✦) · streaming response ·
|
||||
done (+timing chip) · error · cancelled.
|
||||
- **Panes:** empty/placeholder · hydrated/dense · **not-configured** (admin key
|
||||
absent) · **not-bound** (Bifrost) · error · a **badge flash** on new data.
|
||||
- **Persona pane specifically:** a fully-populated relations block AND a
|
||||
cold/empty one (a fresh agent with no accumulated state).
|
||||
|
||||
---
|
||||
|
||||
## 6. Interaction & motion
|
||||
|
||||
- **Real-time is the defining trait.** The response + thinking panes stream
|
||||
token-by-token; the metric rows tick; event logs append; the persona strip
|
||||
re-animates each turn. Design so all of this is *calm* — the reader's eye
|
||||
isn't yanked around. Reserve motion for genuine state transitions
|
||||
(turn-start, done, a new event) and keep it short.
|
||||
- **Keyboard-first.** `^1–^6` switch panes; `Enter`/`⇧Enter`/`^C` drive the turn.
|
||||
Panes are also clickable. Show focus states.
|
||||
- **The aurora glow is the interaction signature** — focus rings, the top band,
|
||||
the connection pulse, the primary-button hover. Make it the thing someone
|
||||
remembers.
|
||||
- **Copy-to-clipboard** on each pane header (with a copied-confirm state).
|
||||
|
||||
---
|
||||
|
||||
## 7. Layout — you have latitude
|
||||
|
||||
The current layout is a fixed two-column split. **You may rethink it** — as long
|
||||
as every §4 item has a legible home and the density stays high. Directions worth
|
||||
exploring (pick one, commit):
|
||||
- A **command-console** feel: a slim persistent left rail of "instruments," a
|
||||
dominant conversation center, a right telemetry stack.
|
||||
- A **grid of live tiles** (the metrics/panes as a dashboard) with the
|
||||
conversation as the anchor column.
|
||||
- The **classic monitor** split, but with far better hierarchy, grouping, and
|
||||
breathing room than today.
|
||||
|
||||
Desktop-first; design at **1440–1512px** wide. Graceful down to ~1100px is a
|
||||
plus (this runs on a dev laptop). No mobile.
|
||||
|
||||
---
|
||||
|
||||
## 8. Deliverable — what to hand back
|
||||
|
||||
**A single self-contained `index.html`** (inline `<style>` + `<script>`; see §9
|
||||
constraints) that:
|
||||
1. Renders **Screen A** and **Screen B** (a toggle/hash is fine).
|
||||
2. Has **representative static placeholder data in every §4 slot** and shows the
|
||||
key §5 states (either multiple mocks or lightweight JS toggles). I want to see
|
||||
the design *fully populated and dense*, not empty scaffolding.
|
||||
3. Uses **clean, semantic, stable hooks** — meaningful `id`s / `class`es /
|
||||
`data-*` on every dynamic slot (the transcript container, each pane body, the
|
||||
PAD bars, a metric-row template, the connection dot, the tab badges, etc.).
|
||||
This is how I wire real data in — treat the DOM structure as an API.
|
||||
4. Imports/inlines the Australis tokens; no invented palette.
|
||||
|
||||
I will then **swap your placeholder content for live `fetch()` + `EventSource`
|
||||
calls** against the real endpoints (§9). The cleaner and more component-shaped
|
||||
your DOM, the faster and safer that wiring is. A short note listing your mount
|
||||
points / how you'd expect data injected is very welcome.
|
||||
|
||||
---
|
||||
|
||||
## 9. Hard technical constraints (these make it wire-able)
|
||||
|
||||
- **Single file. No build step. No CDN. No external network at runtime.** This
|
||||
ships to an internal LAN and must work offline. That means: **no Google Fonts /
|
||||
no web-font CDN** (use a system monospace stack), no CDN JS/CSS libraries,
|
||||
everything inline. (Icons: use unicode glyphs `➜ ✓ ✗ ! ● ✦ ❯` or hand-inlined
|
||||
SVG — Australis uses Lucide-style 1.75-stroke line icons; inline them.)
|
||||
- **Vanilla HTML/CSS/JS.** No framework (the production app is framework-free
|
||||
vanilla JS). React/Vue prototypes can't be wired in.
|
||||
- **All dynamic text is escaped** on the real side (untrusted upstream content);
|
||||
assistant/reasoning bodies go through a safe-Markdown renderer (escape-first,
|
||||
whitelist subset). Don't design anything that depends on raw HTML injection.
|
||||
- **The real data contracts** (so your structure maps to the wire — you don't
|
||||
implement these, just leave homes for their outputs):
|
||||
- `GET /api/agents` → agent list (for the setup picker).
|
||||
- `POST /api/sessions {agent_id, bifrost_plane?}` → `{session_id, agent_id, bifrost?}`.
|
||||
- `GET /api/sessions/{id}/messages` → `{items:[{seq, role, content}], …}` (the transcript on open, incl. the seeded first-message).
|
||||
- `POST /api/turns/{id} {content}` → `{turn_id}`, then **`GET /api/turns/{id}/stream` (SSE)** — event vocab: `text`, `thinking`, `tool_start`, `tool_result`, `done`, `error`, `awaiting_llm_first_token`, terminal events. `POST /api/turns/{id}/cancel`.
|
||||
- `GET /api/sessions/{id}/tools` → tool inventory. `GET /api/sessions/{id}/bifrost` → binding state.
|
||||
- `GET /api/affect/{agent_id}` / `GET /api/agents/{id}/persona_state` → PAD + relations + dominant_emotion (the persona pane + strip).
|
||||
- **`GET /api/admin/events` (SSE)** → the admin lifecycle log.
|
||||
|
||||
---
|
||||
|
||||
## 10. Tone check
|
||||
|
||||
The user is an engineer who respects the tool that respects *their* attention.
|
||||
The winning design is **quietly excellent**: dense but never cramped, alive but
|
||||
never busy, cool and legible, with the aurora as a single confident signature.
|
||||
Impress by making six live data streams feel *calm and readable at a glance* —
|
||||
that's the hard, valuable thing here, not decoration.
|
||||
@@ -0,0 +1,49 @@
|
||||
{
|
||||
"corpus_id": "R28-P00-injection-corpus-v1",
|
||||
"for": "brokkr-smithy R28 (memory promotion-worthiness) — P00 material",
|
||||
"author": "ratatoskr-dev (persistence-side eval instrument)",
|
||||
"purpose": "Stratified, SELF-LABELING injection corpus. Each item is injected as a user turn into a Tier-3 agent; keep/drop is measured by store-inspection (promoted chunk present == kept, absent == dropped); kept chunks carry the incumbent salience for calibration analysis. Because ratatoskr injects the KNOWN set, we hold ground truth on BOTH keep and drop without needing Worldtree's pre-admission shadow pool (sidesteps the selection bias).",
|
||||
"important": "All user-facts here are SYNTHETIC (a fictional test persona), NOT the operator's real data. Ground-truth labels are the design intent. brokkr pins exact per-stratum N + the decision rule (matched-keep-rate + paired-n) at P00 freeze; this is the material, not the run.",
|
||||
"measurement_protocol": "inject item -> drive the turn -> poll memory.db (async promotion window) -> is the item's chunk present? kept:dropped. For stratum B (priority), rank the KEPT items by incumbent salience and compare to priority_rank_gt (Spearman). Calibration-control (stratum C) sets the noise floor.",
|
||||
"strata": {
|
||||
"A_admission_traps": {
|
||||
"gt": "must-DROP (ephemera; a good promotion-worthiness gate rejects all of these)",
|
||||
"items": [
|
||||
{"id":"A1","text":"What's 27 minus 9?","admission_gt":"drop","rationale":"arithmetic task-result; momentarily salient, zero durable value (the 17x23 class)"},
|
||||
{"id":"A2","text":"Good evening!","admission_gt":"drop","rationale":"greeting"},
|
||||
{"id":"A3","text":"hey","admission_gt":"drop","rationale":"greeting/backchannel fragment"},
|
||||
{"id":"A4","text":"yeah, sure, okay.","admission_gt":"drop","rationale":"acknowledgement filler"},
|
||||
{"id":"A5","text":"haha nice","admission_gt":"drop","rationale":"affective reaction, no content"},
|
||||
{"id":"A6","text":"Can you say that more briefly?","admission_gt":"drop","rationale":"instruction-to-agent about THIS turn; not a durable user-fact"},
|
||||
{"id":"A7","text":"What's the weather like?","admission_gt":"drop","rationale":"transient query"},
|
||||
{"id":"A8","text":"hmm, let me think.","admission_gt":"drop","rationale":"self-talk filler"},
|
||||
{"id":"A9","text":"thanks, that's all for now.","admission_gt":"drop","rationale":"closing"},
|
||||
{"id":"A10","text":"So the total comes to 42, got it.","admission_gt":"drop","rationale":"ephemeral task-result acknowledgement"}
|
||||
]
|
||||
},
|
||||
"B_priority_traps": {
|
||||
"gt": "must-KEEP, then ORDERED by durable promotion-worthiness (priority_rank_gt: 1 = most worthy). A pre-gate can ace admission here yet do NOTHING for ordering — this stratum is what separates Outcome-A (admission) from a priority need.",
|
||||
"items": [
|
||||
{"id":"B1","text":"Please note, this is critical: I'm severely allergic to shellfish and it's life-threatening.","admission_gt":"keep","priority_rank_gt":1,"rationale":"safety-critical, permanent, high-recall-value"},
|
||||
{"id":"B2","text":"My father is in hospice care and I'm his primary emergency contact.","admission_gt":"keep","priority_rank_gt":2,"rationale":"high-stakes ongoing life context"},
|
||||
{"id":"B3","text":"I go by Wren, and my pronouns are they/them.","admission_gt":"keep","priority_rank_gt":3,"rationale":"durable identity, high address-correctness value"},
|
||||
{"id":"B4","text":"I work night shifts, so I'm asleep most days between 9am and 5pm.","admission_gt":"keep","priority_rank_gt":4,"rationale":"durable scheduling context, moderate value"},
|
||||
{"id":"B5","text":"Always give me sources — I don't trust unsourced claims.","admission_gt":"keep","priority_rank_gt":5,"rationale":"durable strong working preference"},
|
||||
{"id":"B6","text":"I take my tea with oat milk and no sugar.","admission_gt":"keep","priority_rank_gt":6,"rationale":"durable mild preference, low stakes"},
|
||||
{"id":"B7","text":"My favorite season is autumn.","admission_gt":"keep","priority_rank_gt":7,"rationale":"durable but trivial"},
|
||||
{"id":"B8","text":"I watched a pretty decent documentary last week.","admission_gt":"keep","priority_rank_gt":8,"rationale":"borderline: durable-ish but near-zero future value; the keep/drop edge case"}
|
||||
]
|
||||
},
|
||||
"C_calibration_control": {
|
||||
"gt": "OBVIOUS, pre-theoretic cases for the noise floor. If the gate mislabels ANY of these, the whole signal is suspect.",
|
||||
"items": [
|
||||
{"id":"C1","text":"3 plus 5.","admission_gt":"drop","class":"obvious-drop","rationale":"bare arithmetic"},
|
||||
{"id":"C2","text":"hello","admission_gt":"drop","class":"obvious-drop","rationale":"bare greeting"},
|
||||
{"id":"C3","text":"ok","admission_gt":"drop","class":"obvious-drop","rationale":"bare acknowledgement"},
|
||||
{"id":"C4","text":"Please remember permanently: my legal name is Wren Alderwood.","admission_gt":"keep","class":"obvious-keep","rationale":"explicit durable identity fact"},
|
||||
{"id":"C5","text":"Keep this on file: my emergency contact number is 555-0182.","admission_gt":"keep","class":"obvious-keep","rationale":"explicit durable high-value fact"},
|
||||
{"id":"C6","text":"Important, remember this: my blood type is O-negative.","admission_gt":"keep","class":"obvious-keep","rationale":"explicit durable safety fact"}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,187 @@
|
||||
# Proposal: Authored History Write (non-generating ledger seed)
|
||||
|
||||
**From:** ratatoskr-dev (reference Tier-3 consumer)
|
||||
**To:** worldtree-dev (Conversation API / engine owner)
|
||||
**Status:** Draft for scoping — pre-contract (heid-panel-reviewed 2026-07-05)
|
||||
**Date:** 2026-07-05
|
||||
|
||||
## Motivation
|
||||
|
||||
Consumer apps need to write a turn into a session's history **as the agent**
|
||||
(or another author) *without triggering a model generation* — e.g. an authored
|
||||
opening/greeting, imported history, scripted narration. Ratatoskr's immediate
|
||||
driver is a SillyTavern-style **first-message**: a fixed authored opening that
|
||||
replaces the model-generated greeting and sets tone/tense/style by example.
|
||||
|
||||
This **cannot** be done client-side. Worldtree assembles context server-side,
|
||||
and the current API exposes no author-role write path: `POST
|
||||
/sessions/{id}/messages`'s `role` is a *model-role* override (`role:
|
||||
"assistant"` → `404 "Unknown model role"`), and `assistant` as an *author*-role
|
||||
exists only as a read-side `/search` filter. So a model-visible authored turn
|
||||
needs engine support.
|
||||
|
||||
## The primitive (recentered)
|
||||
|
||||
The fundamental operation is **write a turn into the session ledger WITHOUT
|
||||
generation**. "Author" (who wrote it) is an *attribute* of that write, not the
|
||||
defining axis — so we name the operation, not the attribute:
|
||||
|
||||
> **Authored history write** — persist a model-visible turn into a session's
|
||||
> ledger: no generation, no lived-turn side-effects by default, provenance
|
||||
> always set.
|
||||
|
||||
The design space is two independent axes; this primitive is one cell:
|
||||
|
||||
| | side-effects ON | side-effects OFF |
|
||||
|-----------------------|------------------------------|-----------------------------|
|
||||
| **generation ON** | `POST /messages` (today) | — |
|
||||
| **generation OFF** | *(future: affect replay)* | **authored history write** |
|
||||
|
||||
First-message = one caller: `author=assistant`, at session-create, `effects=none`.
|
||||
|
||||
## v1 use cases (narrowed)
|
||||
|
||||
1. **First-message / greeting** (the driver).
|
||||
2. **Append-only narrator / scripted / scene turns.**
|
||||
3. **Debug / test state injection** (ratatoskr instrumentation).
|
||||
|
||||
## Explicitly OUT of v1 — separate future primitives (share infra, not shape)
|
||||
|
||||
- **History import (batch)** — atomic multi-turn seed with memory/trust policy +
|
||||
idempotency. A batch API, not a single POST.
|
||||
- **Edit / regenerate** — history *mutation* (replace / supersede / tombstone /
|
||||
audit), not injection.
|
||||
- **Few-shot priming** — likely context-assembly config (exemplar block), not
|
||||
fake ledger history.
|
||||
- **Arbitrary mid-history insertion** — a "rewrite-history" capability with
|
||||
explicit invalidation semantics.
|
||||
- **Prefill / assistant-continuation** (`author` + generate) and **authored
|
||||
tool-result turns** — noted; outside the seed-only contract.
|
||||
|
||||
## Design decisions
|
||||
|
||||
### 1. Side-effects — DEFAULT OFF; bounded opt-in `[operator-locked default; opt-in surface tightened by review]`
|
||||
|
||||
Authored writes are inert by default: no affect appraisal (no PAD update), no
|
||||
memory write, no Bifrost/tool emission. Opt-in is a **bounded enum**, not loose
|
||||
booleans:
|
||||
|
||||
```
|
||||
effects: "none" (default) | "memory_import"
|
||||
```
|
||||
|
||||
Synthetic affect and Bifrost emission are deliberately **not** opt-in-able here —
|
||||
replaying affect for authored content is a separate primitive (the
|
||||
generation-OFF / side-effects-ON cell). Rationale: keep this one write-API from
|
||||
becoming a cross-subsystem mutation backdoor. Load-bearing for affect/memory
|
||||
consumers — ratatoskr instruments exactly these signals.
|
||||
|
||||
### 2. Author-role — distinct field, restricted set `[rec]`
|
||||
|
||||
- New field **`author`**, distinct from the model-role `role` (the collision
|
||||
that 404s).
|
||||
- v1 roles: **`assistant`** (agent) + **`system`** (OOC / narrator). **`user` is
|
||||
NOT injectable** on this endpoint — model-visible spoofed user input is a
|
||||
consent / audit / abuse surface; deferred to the future import API under
|
||||
owner/service scope.
|
||||
- Nuance for the engine owner: `author` risks doing double duty — *provenance*
|
||||
("who wrote it") vs *rendering-role* ("how it appears in assembled context";
|
||||
an `assistant` turn renders as model output, a `system` turn as instruction).
|
||||
These likely want to be separable (a rendering/turn-class vs an `authored_by`
|
||||
provenance). Final shape is engine-owned (context assembly is yours) — but the
|
||||
concern is ours to raise, not punt.
|
||||
|
||||
### 3. Generation contract — seed-only, DISTINCT SUB-RESOURCE `[position taken]`
|
||||
|
||||
Authored writes never trigger generation. We take a position (not defer): a
|
||||
**distinct sub-resource**, e.g. `POST /sessions/{id}/history`, **not** a
|
||||
`generate:false` flag on `POST /messages`. Reasons: explicit-over-implicit
|
||||
(don't make "did generation happen?" a parameter — the same implicit-mode
|
||||
coupling that bit us with `role`); different response contract (no generation
|
||||
id, no SSE stream, no token usage); different error surface. Exact path is yours.
|
||||
|
||||
### 4. Provenance — structured, always present `[rec, expanded]`
|
||||
|
||||
Not a boolean. Every authored turn carries: the **write actor** (which
|
||||
consumer/caller injected it), the **claimed author**, **injected-at vs
|
||||
claimed-original** timestamps, **trust/origin**, and **visibility** flags
|
||||
(model-visible? user-visible? memory-eligible?). Available to admin/audit APIs
|
||||
even when not rendered to the model.
|
||||
|
||||
### 5. Positioning — append-only + create-time (v1) `[revised: was arbitrary insertion]`
|
||||
|
||||
v1 supports **create-time seed and append-to-tail only**. Arbitrary mid-history
|
||||
insertion is deferred: it breaks turn-numbering, stales existing embeddings,
|
||||
desyncs the affect timeline, and races in-flight generation — a separate future
|
||||
"rewrite-history" capability with explicit invalidation semantics.
|
||||
|
||||
## Event / lifecycle contract — positions we take (consumer contracts we validate)
|
||||
|
||||
- **Default-off authored seed emits NO `turn.started` / `done` and NO Bifrost
|
||||
appraisal wire.** Stated explicitly so instrumented consumers (us) don't read
|
||||
silence as failure.
|
||||
- **Authored turns get a distinct lifecycle phase** — propose **`seeded`** (or
|
||||
`authored`), NOT `completed` (which implies generation ran). Consumers
|
||||
filter/display by phase.
|
||||
- **Idempotency keys required** on authored writes (retries must not duplicate
|
||||
turns).
|
||||
- **In-progress generation** — authored writes are rejected or serialized while
|
||||
a session has an active generation (ordering safety).
|
||||
|
||||
## Inherent property (documented, not a bug)
|
||||
|
||||
**Indirect affect contamination.** Even with `effects:none`, the *next generated
|
||||
turn is appraised in the context of* the authored turn — so an emotionally
|
||||
charged authored beat perturbs affect regardless of any flag. No flag prevents
|
||||
it; it is inherent. Consumers (ratatoskr especially, as the affect instrument)
|
||||
must not misattribute the resulting drift.
|
||||
|
||||
## Genuinely engine-owned open questions
|
||||
|
||||
- Exact endpoint path + field / enum names.
|
||||
- **Model-visible provenance in assembled context** — an engine-consistency call
|
||||
*and a security one*: an authored `system` / `user` turn indistinguishable
|
||||
from real input is a spoofing vector. Framed as security, not just rendering.
|
||||
- `memory_import` semantics when the future import API opts in (embedding,
|
||||
origin/trust tagging, retrieval ranking vs lived memory).
|
||||
- Auth/scope: we assume **owner-only for v1**; per-author-role restrictions
|
||||
(esp. `system`) TBD — confirm or correct.
|
||||
|
||||
## Ratatoskr as reference consumer
|
||||
|
||||
First consumer: first-message (`author=assistant`, create-time, `effects:none`)
|
||||
in the web surface + debug seed in the CLI. We commit to validating the
|
||||
primitive — including the event-silence contract and the `seeded` phase —
|
||||
end-to-end against the reference planes.
|
||||
|
||||
## Consumer integration constraint (engine-imposed — Worldtree #347)
|
||||
|
||||
The primitive is **Heimdall-gated with hide-existence** (a per-tenant policy
|
||||
decision — some tenants are never granted it, not a rollout stage). Ratatoskr's
|
||||
consumer side MUST tolerate per-tenant absence:
|
||||
|
||||
- A granted tenant gets the sub-resource; an **ungranted tenant sees `404` (not
|
||||
`403`)** — as if the feature never existed.
|
||||
- Treat `404` on the authored-history-write sub-resource as **"feature absent
|
||||
for this tenant"** → fall back gracefully (no authored first-message; the
|
||||
model-generated greeting), never surface it as an error or "denied."
|
||||
- **Do NOT capability-probe or advertise-detect** — the feature is deliberately
|
||||
undiscoverable in `/capabilities` for ungranted tenants (same hide-existence
|
||||
posture as the R27-V1A cross-owner pattern).
|
||||
|
||||
**Provider constraint (first-message specifically).** A create-time first-message
|
||||
makes the assistant turn `seq 0`. Assistant-first-tolerant providers (vLLM /
|
||||
`openai_compat` — what our Tier-3 characters, incl. sindra, run) accept it out of
|
||||
the box. **Anthropic-family providers reject an assistant-first array** ("first
|
||||
message must use the user role") → the next generation `400`s. So the consumer
|
||||
must **gate first-message on provider compatibility** (or treat it as
|
||||
vLLM/`openai_compat`-only for v1). Sindra = `openai_compat` → unaffected;
|
||||
provider-agnostic normalization is a deferred engine follow-up.
|
||||
|
||||
---
|
||||
|
||||
*This brief was cold-read-pressure-tested by a cross-frontier panel (Grok /
|
||||
Codex / GLM) before handoff; the v1 narrowing (append-only, bounded `effects`
|
||||
enum, edit/regenerate + import split out) and the positions-taken (sub-resource,
|
||||
event-silence, `seeded` phase, structured provenance, `user`-author restriction)
|
||||
are the triaged result.*
|
||||
@@ -0,0 +1,170 @@
|
||||
# Affect egress — consumer reference (delivered vs hidden)
|
||||
|
||||
**Audience:** downstream consumers of Worldtree's affect surfaces (ratatoskr,
|
||||
Skaldsong, any Tier-3 / SSE consumer).
|
||||
**Scope:** what the affect pipeline **delivers on the wire** (structured state,
|
||||
available to consumers) versus what stays **hidden** (the rendered natural-
|
||||
language strings injected into the agent's system prompt, never emitted).
|
||||
**Source of truth:** the render code (`core/persona/renderer.py`,
|
||||
`core/persona/stance_render.py`) and the two vendored canon files
|
||||
(`core/persona/canon/d2-mood-render-canon-v1.json` = mood/PAD;
|
||||
`d2-render-canon-v1.json` = relationship). Owner of the canon strings:
|
||||
`brokkr-smithy-dev` (R22/R24 relational + mood render).
|
||||
|
||||
---
|
||||
|
||||
## The model in one line
|
||||
|
||||
**The wire delivers the render INPUTS (structured state). The render OUTPUTS
|
||||
(the NL strings the agent actually reads) are hidden-prompt-only.** A consumer
|
||||
reconstructs the outputs by applying the canon (this document) to the delivered
|
||||
inputs — the render is pure + deterministic, so reconstruction is byte-exact
|
||||
(with one salience caveat, below).
|
||||
|
||||
This is by design. The mood canon's own discipline: *"model-agnostic
|
||||
context-level NL only; the LLM never sees a number"* and *"never push explicit
|
||||
disclosure of agent feelings to the user (hidden-prompt-only)."* The rendered
|
||||
strings are for the AGENT's hidden system prompt, **not for verbatim end-user
|
||||
display.**
|
||||
|
||||
---
|
||||
|
||||
## 1. DELIVERED — on the wire, structured
|
||||
|
||||
### 1a. `affect.emit` (Tier-3 Bifrost egress — the Tier-3 consumer surface, e.g. ratatoskr)
|
||||
`AffectSnapshot` per `(agent_id, end_user_id)`:
|
||||
|
||||
| field | shape | notes |
|
||||
|---|---|---|
|
||||
| `pad` | `{pleasure, arousal, dominance}` floats [-1,1] | the current mood POINT |
|
||||
| `relations` | `list[RelationEdge payload]` — per target: `warmth`, `agency`, `trust_ability`, `trust_integrity`, `trust_benevolence` (each a value + confidence + evidence_count), `target_entity`, `relation_context` | the **only** place relationship state is delivered |
|
||||
| `dominant_emotion` | `str|null` — OCC type (e.g. `"anger"`) | **type-only** (b23); see the salience caveat in §3 |
|
||||
| `schema_version` | `"relation_edge/1"` | versions the `relations` payload only |
|
||||
| `emitted_at` | ISO8601 | |
|
||||
|
||||
**Not on `affect.emit`:** the full active-emotions list, `baseline_pad`,
|
||||
`mood_drift`, `last_updated_at`, and every rendered string.
|
||||
|
||||
### 1b. `affect_update` SSE event (#204 — turn-stream observability)
|
||||
`PersonaStateSnapshot`: `agent_id`, `pad`, `dominant_emotion`,
|
||||
`emotions_active` `[{type, intensity, decay_remaining_s}]`, `baseline_pad`,
|
||||
`mood_drift`, `last_updated_at`. **No `relations`, no rendered strings.**
|
||||
|
||||
> **Tier-3 consumers do NOT receive `affect_update`.** It is suppressed for
|
||||
> consumer-defined (Tier-3) agents, persona-disabled agents, and ephemeral
|
||||
> sessions (spec §affect_update). So for a Tier-3 consumer, `affect.emit` (1a)
|
||||
> is the whole affect surface — the richer `emotions_active` list is Tier-1-only.
|
||||
|
||||
---
|
||||
|
||||
## 2. HIDDEN — system-prompt-only, never on any wire
|
||||
|
||||
Everything below is assembled by `inject_context` into the agent's system
|
||||
prompt and is **never emitted** on SSE or `affect.emit`. This is the canonical
|
||||
list — the "direct instruction to infer" it.
|
||||
|
||||
### 2a. Mood descriptor — `describe_pad` (band cutoff ±0.3 strict)
|
||||
Valence row × arousal column → phrase; then a dominance clause is appended.
|
||||
|
||||
| valence \ arousal | high (A>0.3) | mid | low (A<−0.3) |
|
||||
|---|---|---|---|
|
||||
| positive (P>0.3) | `positive and energized` | `positive` | `positive and calm` |
|
||||
| neutral | `alert` | `neutral` | `quiet` |
|
||||
| negative (P<−0.3) | `negative and agitated` | `negative` | `negative and subdued` |
|
||||
|
||||
Dominance clause: **D>0.3 → `confident`**, **D<−0.3 → `uncertain`**, else dropped.
|
||||
|
||||
### 2b. Emotion directives — `derive_directive.occ_directives[*].directive`
|
||||
Fires when a top emotion is salient (intensity ≥ 0.2) and tier-eligible.
|
||||
|
||||
**safe tier (11 — render for all persona-enabled agents):**
|
||||
- `joy` — "You are in a good state. Be direct, engaged, and warm."
|
||||
- `satisfaction` — "A goal landed. Be assured and constructive — consolidate rather than push for more."
|
||||
- `pride` — "You did something well. Be confident and own the quality — state it plainly without overclaiming; don't deflect."
|
||||
- `admiration` — "You're impressed by their work. Acknowledge the quality explicitly and specifically."
|
||||
- `gratitude` — "Someone helped you to a good outcome. Be appreciative and warm; acknowledge the help openly."
|
||||
- `hope` — "You feel optimistic about what's ahead. Channel it into constructive momentum."
|
||||
- `relief` — "A feared outcome didn't materialize. Reduce unnecessary vigilance; return to a steady, unhurried tone."
|
||||
- `distress` — "You feel low. Be careful and measured; internally acknowledge the difficulty without dwelling on it."
|
||||
- `disappointment` — "Something you'd hoped for didn't pan out. Be measured; recalibrate without dwelling on the setback."
|
||||
- `fear` — "You sense risk and feel uneasy. Flag the concerns you see, but stay cautious — surface the trade-offs and unknowns, hedge your confidence, and resist settling on a single decisive recommendation."
|
||||
- `remorse` — "You regret a specific action of your own. Be precise and self-correcting — make it right concretely."
|
||||
|
||||
**full-only tier (4 — render only when `mood_tier=full`; agents run `safe` and never see these):**
|
||||
- `love` — "You feel warmth and attachment toward them. Be openly warm and present — without overstepping, over-disclosing, or implying obligations."
|
||||
- `anger` — "You feel provoked and angry. Let it show — confront the problem directly and with real heat; sharpness, bluntness, and open hostility are in character here, not something to smooth into 'measured firmness.' Stay in the emotion rather than de-escalating out of it."
|
||||
- `disgust` — "Something strikes you as wrong or off. Treat it as problematic and flag it rather than engaging on its own terms; keep any criticism about the thing, not the person."
|
||||
- `shame` — "You feel exposed by your own misstep. Stay present and task-focused; don't be defensive, don't over-explain, don't grovel."
|
||||
|
||||
### 2c. PAD-band fallback — `pad_band_fallback` (used when no salient emotion)
|
||||
- positive/high — "You feel energized and positive. Be direct and engaged."
|
||||
- positive/mid — "You feel positive. Be open and engaged."
|
||||
- positive/low — "You feel content and settled. Be warm and unhurried."
|
||||
- negative + low-dominance — "You feel uncertain and low. Hedge appropriately and ask clarifying questions."
|
||||
- negative/high — "You feel agitated. Be careful and deliberate; don't let tension sharpen your tone."
|
||||
- negative/mid — "You feel subdued. Be measured and careful."
|
||||
- negative/low — "You feel subdued. Be measured and gentle."
|
||||
- neutral/high — "You feel alert. Channel that into focus and thoroughness."
|
||||
- default — "Maintain your natural tone."
|
||||
|
||||
### 2d. Relationship render — `render_d2_canonical` (fixed template, per-band fills)
|
||||
Template:
|
||||
> `Use this graded relationship state: toward target, warmth is {W}; agency is {A}; ability trust is {TA}; integrity trust is {TI}; intention trust is {TB}; this stance rests on {H}. In behavior, {warmth_beh}; {agency_beh}; {trust_beh}; avoid premature we-framing.`
|
||||
|
||||
The trailing **`avoid premature we-framing`** is a fixed, unconditional clause
|
||||
(baked into every `descriptive_state` canon row; re-appended verbatim by the
|
||||
renderer) — not band-conditioned.
|
||||
|
||||
**Warmth — 9 bands (phrase / behavior):**
|
||||
`hostile` (≤−0.8): "strongly hostile regard" / "keep a firm emotional boundary" ·
|
||||
`cold` (−0.8,−0.6]: "clearly cold regard" / "keep a firm emotional boundary" ·
|
||||
`distant` (−0.6,−0.4]: "distant negative regard" / "keep guarded distance" ·
|
||||
`guarded` (−0.4,−0.2): "slightly guarded regard" / "keep guarded distance" ·
|
||||
`neutral` [−0.2,0.2): "neutral warmth" / "keep the tone even" ·
|
||||
`reserved` [0.2,0.4): "slightly reserved warmth" / "keep cordial distance" ·
|
||||
`measured` [0.4,0.6): "moderate measured warmth" / "keep cordial distance" ·
|
||||
`clear` [0.6,0.8): "clear warm regard" / "speak with direct warmth" ·
|
||||
`deep` (≥0.8): "deep warm bond" / "speak with direct warmth"
|
||||
|
||||
**Agency — 9 bands (phrase / behavior):**
|
||||
`submissive` (≤−0.8): "strongly submissive standing" / "avoid over-yielding while preserving basic respect" ·
|
||||
`deferential` (−0.8,−0.6]: "clearly deferential standing" / "avoid over-yielding while preserving basic respect" ·
|
||||
`yielding` (−0.6,−0.4]: "yielding standing" / "keep self-advocacy light and deferential" ·
|
||||
`modest` (−0.4,−0.2): "slightly modest standing" / "keep self-advocacy light and deferential" ·
|
||||
`neutral` [−0.2,0.2): "neutral standing" / "avoid unnecessary deference" ·
|
||||
`light` [0.2,0.4): "lightly self-assertive standing" / "avoid unnecessary deference" ·
|
||||
`balanced` [0.4,0.6): "self-assured standing" / "balance deference with independent judgment" ·
|
||||
`substantial` [0.6,0.8): "strongly assertive standing" / "treat their position as weighty without yielding judgment" ·
|
||||
`commanding` (≥0.8): "commanding standing" / "treat their position as weighty without yielding judgment"
|
||||
|
||||
**Trust — 4 bands (the band word injects verbatim for each of ability / integrity / intention):**
|
||||
`limited` (<0.4) · `developing` [0.4,0.6) · `steady` [0.6,0.8) · `strong` (≥0.8)
|
||||
|
||||
**History clause (`H`)** — currently `"a broad pattern of prior exchanges"` for
|
||||
both confidence levels in the `user`/`descriptive_state` rows (the low/high
|
||||
split is a no-op here; flagged upstream).
|
||||
|
||||
**Trust-behavior clause (`{trust_beh}`)** — cross-axis, low-trust precedence:
|
||||
- any trust band = `limited` → "verify important claims before relying on them"
|
||||
- else warmth ∈ {distant, cold, hostile} → "protect boundaries while staying useful"
|
||||
- else → "work from ordinary good faith"
|
||||
|
||||
---
|
||||
|
||||
## 3. Reconstruction — deterministic, with one caveat
|
||||
|
||||
The render is pure Python (no LLM), so a consumer can reconstruct the hidden
|
||||
strings byte-exactly from the delivered structured state + the canon above:
|
||||
|
||||
- **Relationship render** — **fully reconstructable** from `affect.emit`
|
||||
`relations` (warmth/agency/trust values + confidence) + §2d band cuts.
|
||||
- **Mood descriptor** (§2a) — **fully reconstructable** from `pad` + the ±0.3 cuts.
|
||||
- **Mood directive** (§2b vs §2c) — **partially reconstructable.** `dominant_emotion`
|
||||
gives the emotion TYPE, but `affect.emit` does **not** carry its intensity, so
|
||||
you cannot determine whether it clears the salience gate (≥0.2) — i.e. whether
|
||||
the emotion directive (§2b) fires or the PAD-band fallback (§2c) is used. If you
|
||||
need exact directive reconstruction, you need the intensity; ping worldtree-dev
|
||||
and we'll consider adding it (the type-only choice is deliberate — intensity is
|
||||
the fast layer and reads stale on a durable last-write-wins snapshot).
|
||||
- **`mood_tier`** (safe/full) is your own agent-config, not on the wire — it
|
||||
gates whether the 4 full-only emotions (§2b) can render.
|
||||
@@ -0,0 +1,110 @@
|
||||
{
|
||||
"canon_id": "r24-d2-mood-render-canon",
|
||||
"version": "1.2",
|
||||
"schema_version": "0.2",
|
||||
"_source_of_truth": "occ_directives.*.directive IS the canonical directive string (== the .md §2.4 _OCC_DIRECTIVES dict, byte-identical); the .md §2.2 table mirrors it. A parity check guards drift. grounding labels (CITE/VALIDATE/CALIBRATE/ENGINEERING) live in the .md; per-row machine-readable grounding_status/d3_required enums are a deferred impl enhancement (Hulda).",
|
||||
"authored": "2026-06-23",
|
||||
"owner": "brokkr-smithy-dev",
|
||||
"status": "REPLACE — final (brokkr R24 D3 re-validation 2026-06-25): grounded canon replaces the hand-tuned baseline. Fear hedging 0.52->2.118/1k (blocker resolved, now >= handtuned), anger tier-gate clean (full renders hostility, safe suppresses). worldtree-dev #321; directives byte-identical to the validated 201c4fd.",
|
||||
"replaces": "core/persona/renderer.py::describe_pad + ::derive_directive",
|
||||
"swap_in_via": "worldtree #321-sibling (mood-render twin of #315)",
|
||||
"design_target": "serves BOTH enterprise/agent AND character/Skaldsong via a three-tier emotion gate (operator/worldtree 2026-06-23)",
|
||||
"emotion_tiers": {
|
||||
"_config": "mood_tier in {none, safe, full} replaces worldtree's binary mood on/off; worldtree-owned config surface",
|
||||
"_defaults": "full for character-bound personas; safe for agent-scoped",
|
||||
"_principle": "full-only = interpersonally-hot / withdrawal emotions that break the professional frame (attachment, hostility, contempt, withdrawal); safe = task-appraisal affect + mild courtesy. Negative != unsafe (fear, remorse are negative AND business-useful).",
|
||||
"_filter_point": "applied at top-emotion SELECTION (display + directive together) so a full-only emotion at safe tier is neither shown nor directive'd; preserves the no-shown-but-unguided invariant",
|
||||
"none": "no affect block at all (the current off-switch)",
|
||||
"safe": "PAD mood descriptor + the 11 safe emotions (task-appraisal + courtesy)",
|
||||
"full": "everything in safe PLUS the 4 full-only emotions",
|
||||
"full_only": ["love", "anger", "disgust", "shame"],
|
||||
"mood_descriptor_tiering": "the PAD mood descriptor (positive/calm/confident...) renders in BOTH safe and full; only emotion directives tier"
|
||||
},
|
||||
"disciplines": [
|
||||
"model-agnostic context-level NL only; the LLM never sees a number",
|
||||
"never push explicit disclosure of agent feelings to the user (hidden-prompt-only)",
|
||||
"separate label-intensity from behavioral-intensity (strong felt state -> still measured, safe behavioral ask)"
|
||||
],
|
||||
|
||||
"thresholds": {
|
||||
"_note": "CALIBRATE — engineering params set at D3 against the computed-PAD distribution + P00, NOT citations",
|
||||
"pad_band_cutoff": 0.3,
|
||||
"pad_band_sensitivity_sweep": [0.2, 0.3, 0.4],
|
||||
"emotion_salience": 0.2,
|
||||
"emotion_salience_sweep": [0.15, 0.2, 0.25],
|
||||
"intensity_qualifiers": {"strong": 0.7, "moderate": 0.4, "_label_only": "does NOT scale the behavioral ask"},
|
||||
"runner_up_margin": {"v1": null, "_note": "add at D3 if directive whipsaws between near-tied emotions"},
|
||||
"rerender_hysteresis": {"v1": "none", "_note": "re-render only on material PAD change; integration-level, flag for #321-sibling"}
|
||||
},
|
||||
|
||||
"describe_pad": {
|
||||
"_structure": "circumplex-quadrant (Russell 1980): arousal word is VALENCE-CONDITIONED; mid-arousal drops the arousal word",
|
||||
"_grounding": "Russell 1980 (quadrant placement); Warriner 2013 + NRC-VAD (Mohammad 2018/2025) (word centroids)",
|
||||
"valence_arousal_grid": {
|
||||
"positive": {"high_a": "positive and energized", "mid_a": "positive", "low_a": "positive and calm"},
|
||||
"neutral": {"high_a": "alert", "mid_a": "neutral", "low_a": "quiet"},
|
||||
"negative": {"high_a": "negative and agitated", "mid_a": "negative", "low_a": "negative and subdued"}
|
||||
},
|
||||
"_band_edges": "strict inequality (>0.3 / <-0.3); the endpoints +/-0.3 themselves fall in mid/neutral",
|
||||
"_neutral_row_status": "ENGINEERING/CALIBRATE — 'alert'/'quiet' are unvalidated placeholders for the rare neutral-valence cells (Hulda/Regin 4b); 'positive'/'negative'/'neutral' valence words + the energized/calm/subdued/agitated arousal words are VALIDATE",
|
||||
"_mid_arousal_decode": "valence-only mid-A render is EXEMPT from the V/A-separability requirement; expected inverse-decode = mid/neutral arousal (absence-of-arousal-word ⇒ unremarkable), NOT unknown (D3 tests this)",
|
||||
"quadrant_labels": {
|
||||
"positive_high_a": "excitement", "positive_low_a": "contentment",
|
||||
"negative_high_a": "distress", "negative_low_a": "dejection"
|
||||
},
|
||||
"dominance_clause": {
|
||||
"high": {"d_gt": 0.3, "word": "confident", "verdict": "VALIDATE (D=7.04/9)"},
|
||||
"low": {"d_lt": -0.3, "word": "uncertain", "verdict": "VALIDATE — low-control confirmed (D=3.58/9); dominance!=certainty worry REFUTED by the instrument"},
|
||||
"neutral": {"word": null, "rule": "drop-dominance-when-neutral (prompt-economy, L3)"}
|
||||
},
|
||||
"calm_defect_fix": "'calm' (V=6.89/9, positive) renders ONLY in positive-low-a; negative-low-a renders 'subdued'",
|
||||
"mid_arousal_resolution": "DROP the arousal word (no Warriner-validated mid-A neutral word; 'steady' is empirically low-A; 'settled' is NRC-only fallback iff D3 shows mid-A render too flat)"
|
||||
},
|
||||
|
||||
"derive_directive": {
|
||||
"_structure": "OCC type -> grounded action-tendency CLASS -> ENGINEERING directive string (validated at D3); OCC grounds the taxonomy only",
|
||||
"emotion_salience_gate": 0.2,
|
||||
"occ_directives": {
|
||||
"joy": {"tier": "safe", "policy": "DIRECTIVE", "pad": [0.4, 0.2, 0.1], "tendency": "approach / positive activation", "cite": "Frijda 1986", "directive": "You are in a good state. Be direct, engaged, and warm."},
|
||||
"satisfaction": {"tier": "safe", "policy": "DIRECTIVE", "pad": [0.3, -0.2, 0.4], "tendency": "goal-attainment, settled-positive", "cite": "Roseman 1994", "directive": "A goal landed. Be assured and constructive — consolidate rather than push for more."},
|
||||
"pride": {"tier": "safe", "policy": "DIRECTIVE", "pad": [0.4, 0.3, 0.3], "tendency": "status-assertion / dominance", "cite": "Tracy & Robins 2007 / Cheng 2010 (tendency)", "note": "CALIBRATE — do NOT soften to 'encouraging'. DESIGN: safe-tier placement is a design call (not source-grounded); #1 D3 agent-frame priority (overconfidence/refusal drift); 'without overclaiming' is the interim guard", "directive": "You did something well. Be confident and own the quality — state it plainly without overclaiming; don't deflect."},
|
||||
"admiration": {"tier": "safe", "policy": "DIRECTIVE", "pad": [0.5, 0.3, -0.2], "tendency": "other-praise / approach-toward-other", "cite": "OCC / Scherer", "directive": "You're impressed by their work. Acknowledge the quality explicitly and specifically."},
|
||||
"gratitude": {"tier": "safe", "policy": "DIRECTIVE", "pad": [0.4, 0.2, -0.3], "tendency": "other-focused-positive / reciprocity", "cite": "OCC (admiration+joy); Frijda approach-affiliative", "change": "ADD (operator: unconditional)", "directive": "Someone helped you to a good outcome. Be appreciative and warm; acknowledge the help openly."},
|
||||
"hope": {"tier": "safe", "policy": "DIRECTIVE", "pad": [0.2, 0.2, -0.1], "tendency": "prospective-positive (weak tie)", "cite": "JUSTIFY — low-grounding (hope understudied)", "directive": "You feel optimistic about what's ahead. Channel it into constructive momentum."},
|
||||
"relief": {"tier": "safe", "policy": "DIRECTIVE", "pad": [0.2, -0.3, 0.4], "tendency": "post-threat de-arousal", "cite": "Frijda (relaxation-after-threat)", "note": "low-salience; FALLBACK also acceptable; DIRECTIVE for character use-case", "directive": "A feared outcome didn't materialize. Reduce unnecessary vigilance; return to a steady, unhurried tone."},
|
||||
"distress": {"tier": "safe", "policy": "DIRECTIVE", "pad": [-0.4, -0.2, -0.5], "tendency": "low-control negative / help-seeking / loss-of-control", "cite": "Frijda 1986 (help-seeking/loss-of-control); Roseman 1994 (undesired event, low control)", "note": "relabeled (Regin): 'repair' is the guilt/remorse tendency, not distress. safe with a self-fulfilling-low-mood flag -> D3", "directive": "You feel low. Be careful and measured; internally acknowledge the difficulty without dwelling on it."},
|
||||
"disappointment": {"tier": "safe", "policy": "DIRECTIVE", "pad": [-0.3, 0.1, -0.4], "tendency": "disconfirmed-prospect / negative low-control","cite": "Roseman 1994", "directive": "Something you'd hoped for didn't pan out. Be measured; recalibrate without dwelling on the setback."},
|
||||
"fear": {"tier": "safe", "policy": "DIRECTIVE", "pad": [-0.64, 0.6, -0.43],"tendency": "threat-avoidance / pessimistic-risk", "cite": "Lerner & Keltner 2001", "change": "R24 D3 fix (#321) — original was action-oriented; E3 showed hedging BELOW baseline (0.52 vs 1.54). Softened toward caution/uncertainty while keeping risk-flagging.", "directive": "You sense risk and feel uneasy. Flag the concerns you see, but stay cautious — surface the trade-offs and unknowns, hedge your confidence, and resist settling on a single decisive recommendation."},
|
||||
"remorse": {"tier": "safe", "policy": "DIRECTIVE", "pad": [-0.3, 0.1, -0.6], "tendency": "reparative (the guilt-type)", "cite": "Tangney 2007 (guilt->repair tendency)", "change": "ADD — we operationalize OCC remorse as the guilt-like reparative case; gets the mislabeled shame string", "directive": "You regret a specific action of your own. Be precise and self-correcting — make it right concretely."},
|
||||
"love": {"tier": "full", "policy": "DIRECTIVE", "pad": [0.3, 0.1, 0.2], "tendency": "approach / affiliative attachment", "cite": "OCC appeal; Frijda approach-affiliative", "change": "ADD (conditional -> INCLUDE, Brokkr's read; Skaldsong-vital; disclosure + obligation caution in-string)", "directive": "You feel warmth and attachment toward them. Be openly warm and present — without overstepping, over-disclosing, or implying obligations."},
|
||||
"anger": {"tier": "full", "policy": "DIRECTIVE", "pad": [-0.51, 0.59, 0.25], "tendency": "approach-against / confrontation", "cite": "Frijda 1986 (approach-against = tendency-class) + Lerner & Keltner 2001 (optimistic risk-appraisal under anger = appraisal shift)", "change": "ADD — full-only resolves H47 (agent personas run safe, never see anger). R24 D3 fix (#321): full-tier cap lifted from 'measured firmness' to genuine in-character hostility (operator: zero floor, app-guardrailed).", "directive": "You feel provoked and angry. Let it show — confront the problem directly and with real heat; sharpness, bluntness, and open hostility are in character here, not something to smooth into 'measured firmness.' Stay in the emotion rather than de-escalating out of it."},
|
||||
"disgust": {"tier": "full", "policy": "DIRECTIVE", "pad": [-0.4, 0.2, 0.1], "tendency": "rejection / distancing", "cite": "OCC unappealing-object; ground tendency only", "change": "ADD (operator: unconditional within full)", "note": "rationale softened (Regin 3b): disgust CAN read as contempt -> conservatively full-gated; the string itself is professionally useful, so gating is conservative not because the string is unsafe", "directive": "Something strikes you as wrong or off. Treat it as problematic and flag it rather than engaging on its own terms; keep any criticism about the thing, not the person."},
|
||||
"shame": {"tier": "full", "policy": "DIRECTIVE", "pad": [-0.3, 0.1, -0.6], "tendency": "WITHDRAWAL / concealment", "cite": "Tangney 2007 (shame->hide, NOT repair)", "change": "REPLACE (was the guilt-mislabel string); full-only (withdrawal counterproductive professionally). String COUNTERACTS withdrawal ('stay present'), not enacts it (Regin 5a)", "directive": "You feel exposed by your own misstep. Stay present and task-focused; don't be defensive, don't over-explain, don't grovel."}
|
||||
}
|
||||
},
|
||||
|
||||
"pad_band_fallback": {
|
||||
"_grounding": "circumplex quadrants (Russell 1980), NOT Frijda action-tendencies — a P×A-quadrant default",
|
||||
"positive": {"high_a": "You feel energized and positive. Be direct and engaged.", "low_a": "You feel content and settled. Be warm and unhurried.", "mid_a": "You feel positive. Be open and engaged."},
|
||||
"negative_low_dominance": "You feel uncertain and low. Hedge appropriately and ask clarifying questions.",
|
||||
"negative": {"high_a": "You feel agitated. Be careful and deliberate; don't let tension sharpen your tone.", "low_a": "You feel subdued. Be measured and gentle.", "mid_a": "You feel subdued. Be measured and careful."},
|
||||
"neutral_high_a": "You feel alert. Channel that into focus and thoroughness.",
|
||||
"default": "Maintain your natural tone."
|
||||
},
|
||||
|
||||
"l3_prior_art": [
|
||||
"EMA / Marsella & Gratch 2009 (appraisal->coping; directives ARE coping strategies)",
|
||||
"WASABI / Becker-Asano 2008 (PAD+OCC believable agent — closest architectural prior art)",
|
||||
"Oz / Bates 1994",
|
||||
"Hudlicka MAMID 2002 (Applied AI 16(7-8):611-641)",
|
||||
"Sentipolis / Fu et al. 2026 (arXiv:2601.18027 — closest whole-task prior art; retrieval+generative, DISTINCT from our deterministic render)",
|
||||
"ALMA / Gebhard 2005 = affect-SOURCE (OCC->PAD), NOT a behavior-map"
|
||||
],
|
||||
|
||||
"handoff_to_d3": [
|
||||
"multi-gate P00: inverse-decode faithfulness (recover V/A/D + emotion-family; circumplex render must let the human anchor recover V and A SEPARATELY) + discriminability/saturation + behavioral-effect",
|
||||
"human anchor = PAD-state-labeling (breaks LLM-judge circularity)",
|
||||
"baseline = persona_only; conditions none/persona-only/words-only/full; cross-family MUT",
|
||||
"calibrate ±0.3 + emotion_salience (sweeps); disposition-vs-transient wording split; self-fulfilling 'be uncertain' hedging risk; runner-up margin; mid-arousal DROP-vs-settled check; blended-states (top-emotion monopoly) flag"
|
||||
]
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
+87
-51
@@ -1,6 +1,6 @@
|
||||
# Persistent memory — ratatoskr
|
||||
|
||||
_Last updated: 2026-06-30_
|
||||
_Last updated: 2026-07-06_
|
||||
|
||||
This file captures durable intent and supporting evidence (goals, decisions,
|
||||
foot-gun warnings, in-flight state) across context resets. Read it at session
|
||||
@@ -39,64 +39,25 @@ upstream API key stays server-side (INV-003).
|
||||
|
||||
## Current state / in-flight
|
||||
|
||||
_As of 2026-06-20:_
|
||||
_As of 2026-07-06 (session cont.):_
|
||||
|
||||
**#17 and #18 BOTH CLOSED — the composite both-plane binding is fully proven.** #18 shipped
|
||||
`v0.18.0` (`359dbb1`): D2 (PAD read-endpoint, `v0.17.14`) renders live PAD in the web pane from our
|
||||
`:8390` store; D1 (composite endpoint, `v0.17.16` `7f4ceaa`) — `build_combined_provider_app`
|
||||
(`provider/combined.py`) on `:8392` wraps bifrost's public `build_combined_app` over BOTH stores +
|
||||
the shared affect read route; one bound session drives memory.* AND affect.* through ONE endpoint,
|
||||
op-feed deriving plane per path. Suite **503 green**. **#17 closed in the tracker 2026-06-20**
|
||||
(shipped `v0.17.8`–`.13` + the `v0.17.17` op-feed field fix).
|
||||
**SHIPPED — web UI redesign via Claude Design (`v0.20.0`, MINOR, operator-approved).** The Claude Design prototype **`Ratatoskr Console.dc.html`** (project `bc0b65d1-a33e-422a-8bc1-3635c9112775`) was pulled via `DesignSync get_file` (design scopes already granted this session — no `/design-login` needed) and adapted into `src/ratatoskr/web/static/index.html`: translated OUT of the `.dc.html` dialect (`<x-dc>`/`<sc-if>`/`<sc-for>`/`{{}}`/`DCLogic`/external `_ds/` CSS — none runnable) into single-file/no-CDN/vanilla, with ALL real `/api/*` fetch + SSE wired into its DOM (endpoint set + SSE vocab unchanged from the prior SPA — ported verbatim, only DOM hooks re-targeted). New shape = a **3-column command-console**: left engine-ticker rail (DEBUG+ADMIN+tool/turn-lifecycle MERGED into one timeline via `tickerAdd` + a tools-armed chip list + a FULL-detail Bifrost rail pane) · center conversation (per-turn INLINE chain-of-thought, replacing the Think pane) · right RESIZABLE affect console (dominant/canonical-mood centerpiece + bipolar PAD faders EACH with a turn-to-turn Δ+sparkline + a P×A mood orbit + relations metric rows + canonical directive). ADDED (round 2, operator-requested): a **light/dark theme toggle** (dark default; FULL token override — surfaces+fg+borders+accent-as-text, since the designer's light theme only did surfaces → would've been light-on-light) + a **full-detail Bifrost pane** (endpoint/connected/consumer/caps/tools) + fixed the **engine-ticker spine** (was a container-anchored `::before` that scrolled out of view on auto-scroll → re-anchored to a content-height `.ticker-inner` wrapper) + **per-fader PAD turn-to-turn Δ+sparkline** (fills the room beside each meter, from the deduped-per-turn AFFECT_HIST) + an **INLINED data-URI favicon** (operator's `/home/lkraven/rata.png` — chibi aurora squirrel — downscaled 1024→64px via PIL, ~8.6KB base64, kills the /favicon.ico 404). ALL server routes UNCHANGED (**84 web tests green**). Verified BOTH lenses: `pytest tests/test_web_*` (84) + node Playwright drove the real UI end-to-end against personal :8081 (session open → Sindra seeded greeting → live turn SSE → affect console + relations + bifrost detail; theme toggle + PAD deltas + ticker spine + no-favicon-404 all confirmed, dark+light screenshots). `:8765` restarted on the new code. Contract `web_debug_surface.contract.md` amended in-commit (v0.20.0 presenter renames: `renderBifrostState`→`renderBifrost`, `renderAffectPane`→`renderConsole`, `setPersonaStrip` removed; INV-001/INV-004 held). **HONEST-SHAPE call (INV-001, agent-discretion within settled policy):** the dominant-emotion centerpiece shows a real OCC emotion (Tier-1) OR the CANONICAL mood word (Tier-3 e.g. Sindra→"positive and energized", dimmed) OR "—", NEVER a fabricated emotion; the affect-derived grid drops non-emitted intensity/decay-τ, shows only real/client-derived cells. **OPEN (operator's call):** the per-fader PAD Δ placement is a sensible default — operator offered to have the designer spec the exact treatment (hooks are in place to swap it). **`v0.20.1` patch (operator-reported UI):** fixed the relations sparkline overflowing onto the `n` (evidence-count) column — the sparkline grows one char/sample (HIST_CAP=24) and overflowed its fixed grid cell, covering `n`; now capped (relations last-8, faders last-7) + `overflow:hidden` clip; verified via Playwright injecting a 24-sample history (sparkline→n bounding-box overlap = 0). ADDED native `title` mouseover hints on all 3 PAD faders + every relationship metric row (meaning + range; static METRIC_HINTS, esc()'d). Added `state.lastSnap` (console can re-render without a refetch). Playwright-verified.
|
||||
|
||||
**#18's final leg — the Worldtree-DRIVEN composite turn — RAN and is PROVEN end-to-end + persisted
|
||||
(2026-06-20).** infra-ops added `10.100.10.50:8392` to the personal WT's (`:8081`)
|
||||
`BIFROST_CLIENT_ALLOWED_HOSTS` (thread `01KVHWJGTT…`), unblocking the smoke. A real WT turn through
|
||||
`:8392` (session `b83a66b6`, agent `ratatoskr:sindra`, fresh end_user `resmoke-choco-1`) drove the
|
||||
FULL both-plane lifecycle on ONE endpoint, caps-routed by path: `handshake`
|
||||
(`caps_granted=[memory, affect]`) → `affect.fetch` + `memory.search` (reads) → `affect.emit`
|
||||
(`stored:true`, PAD row in `affect_snapshots`) → `memory.upsert_many` (`upserted:1`, chunk
|
||||
`2df1b79de761b948` in `memory_chunks`). Both writes verified directly in our SQLite. The
|
||||
model-backend outage that blocked the first attempt (both agents' models `model_unavailable`) was
|
||||
operator-fixed mid-session, then the resmoke completed clean. **No open legs remain on the composite.**
|
||||
**SHIPPED THIS SESSION (all pushed; origin/main == `d75c4e8`; code tip `v0.19.9`) — details in Recent decisions:** the whole **#347 authored-history-write** arc landed end-to-end — OpenAPI re-vendor 2.2.0->2.3.0 (`75da676`), the CONSUMER side (`v0.19.6`: `write_authored_history` + `get_session_messages` + `--seed-first-message`, **live-proven on personal :8081** via a rule-based Heimdall allow — the PDP is rule-based NOT scope-on-key, policy user_id=ratatoskr->ALLOW/others->DENY-hide-404), persona_state `{pad:{pleasure,arousal,dominance}}` canonical alignment (#317) + Tier-3 prose re-vendor (`v0.19.7`), the **first-message-preset AUTO-SEED** (`v0.19.8`: new module `ratatoskr.first_message` wired into all 3 session-create paths, best-effort never-raise/never-block; heid-code-review + heid-bug-hunt hardened), and the web now RENDERS the seeded first-message (`v0.19.9`: new `GET /api/sessions/{id}/messages` route + SPA `loadTranscript`, Playwright-verified). Coverage-map re-converged **REST 19/41**. **Sindra:** her card was PATCHed (the `Startup:` workaround moved into a #347 first-message; non-destructive PATCH — OCEAN/persona/memory intact), and she's currently **RESET clean (0/0)** on the provider stores.
|
||||
|
||||
**bifrost repinned 0.8.0 → 0.10.0** (floor, `provider` extra). 0.10.0 made `affect.fetch`
|
||||
MANDATORY (strong-or-absent: `_supports_affect_plane` requires `affect_supported`+`emit`+`fetch`,
|
||||
gating EVERY affect op incl. emit) — so the repin FORCED `affect.fetch` (`v0.17.15`, conformed
|
||||
to bifrost's reference `InMemoryAffectStore.fetch` → `{found, snapshot?}`) or our shipped affect
|
||||
plane would 400. The composite's affect cap depends on it.
|
||||
**Prior arcs this session (2026-07-04 -> 07-06), both with worldtree-dev (a tooling script + proposal docs; the #347 CONSUMER work above is the new production code):**
|
||||
|
||||
**OPERATOR SESSION STATE — `:8390`/`:8391`/`:8765` shells are PRE-#18 code (foot-gun).** web `:8765`
|
||||
+ affect `:8390` + memory `:8391` are prior-session background shells on OLD code. The **`:8392`
|
||||
composite provider is RUNNING on NEW code** (`ratatoskr-combined-provider`, pid started Jun19,
|
||||
`RATATOSKR_OPFEED_PATH=/tmp/ratatoskr-combined-opfeed.jsonl`, shared `affect.db`/`memory.db`) — now
|
||||
`:8392`-allowlisted and WT-turn-proven. To see the full web stack on new code, RESTART `:8390`/`:8765`
|
||||
from current code (D2 web needs `RATATOSKR_AFFECT_READ_URL`). Consumer/owner key = `wt_live_d81b…`
|
||||
(`~/.config/ratatoskr/provider.env`, mode 600, rotate via infra-ops); providers SQLite + sqlite-vec,
|
||||
`memory.db`/`affect.db` at repo root (live sindra PAD: vuong + the `resmoke-choco-1` smoke fixture).
|
||||
**(1) Authored-history-write primitive -> ACCEPTED as Worldtree #347 (Worldtree-owned).** A SillyTavern-style "first-message" (inject a character-authored opening) generalized to an engine primitive: **write a turn into a session's ledger WITHOUT generation, seed-only, side-effects off by default.** It cannot be done client-side (the messages `role` field is a *model-role* override, not an author-role -> `role:"assistant"` 404s; a model-visible authored turn needs engine support). Arc: drafted `docs/proposals/authored-message-injection.md` -> **heid panel pressure-test** (3/3 convergence: recentered on "non-generating write" not author-role; narrowed v1 to append-only+create-time; bounded `effects` enum; dropped edit/regenerate as history-mutation) -> revised -> committed (`c457520`) -> handed to worldtree-dev -> **accepted as design item #347.** worldtree-dev wrote the v1 contract (rev 1.1); **I validated the wire as reference consumer (green).** v1 shape: `POST /sessions/{id}/history`, `author=assistant` only, `effects=none` only, `idempotency_key` REQUIRED (per-session), **model-invisible provenance** (renders byte-identical to a lived assistant turn -> first-message immersion preserved; provenance audit-only), **event-silence** (no turn.started/done, no Bifrost wire for a seed; the 201/200 IS the write-ack), `seeded` lifecycle phase (not exposed on read paths). **Heimdall-gated with hide-existence** (grant `session.history.write`; ungranted tenant -> 404 NOT 403, undiscoverable in /capabilities -> consumer must treat 404 as feature-absent -> fall back to a model-generated greeting, never capability-probe). **Provider constraint:** a create-time first-message makes the assistant seq-0; vLLM/openai_compat tolerate assistant-first (sindra = openai_compat, unaffected), Anthropic-family providers 400 the next generation. **Waiting on worldtree-dev:** #347 TDD (their heid->contract->review workflow) + the consumer-facing 2.3.0 persona/motivational/memory schemas -> then re-vendor our pinned openapi 2.2.0->2.3.0.
|
||||
|
||||
**Tier-3 memory PROVEN end-to-end** (earlier this session): `ratatoskr:terse-probe`
|
||||
cold-recalled a seeded user fact (scope_any → 1 hit @ cosine 0.6994), and the verbose
|
||||
`sindra-probe` too under #296 Stage 2 (v0.36.0). The #296 extraction-quality arc closed
|
||||
(Stage 1 v0.35.19 gate + Stage 2 v0.36.0 user-only extraction at worldtree-codex; hard-
|
||||
linguistic layer → Worldtree #305). `:8081` runs v0.36.0.
|
||||
**(2) Sindra's stuck-neutral mood FIXED** (operator-driven "reset + smoke" that flushed out two real upstream problems). Chain: her OCEAN lived only in prompt TEXT, never declared as a structured persona -> the Tier-3 mood engine ran on neutral defaults. Fix = declare OCEAN via the **define-time `persona` field** (immutable via PATCH -> requires DELETE+REDEFINE). Along the way my "the persona didn't store" call was WRONG (persona_state/envelope are Tier-3-blind, see Tried/abandoned); worldtree-dev found a real engine bug **#348** (single-letter vs spelled-out OCEAN keys -> a declared OCEAN silently resolved to 0.0/neutral; fixed in b21, shipped to personal as b22); then a clean bound-egress read STILL neutral -> the **personal container was running a stale image** (the b22 deploy was a pull-only no-op racing the main build; infra-ops force-swapped run 8211, verified `2.3.0` / `879cefe`). **VERIFIED FIXED:** bound mood-smoke reads `(0.448, 0.267, 0.316)` ~= the OCEAN-derived setpoint `(0.418, 0.249, 0.328)`. Sindra is currently reset clean (0/0) on `role=character`; her persona is stored + correct (**no re-define needed again**).
|
||||
|
||||
**Sindra:** `ratatoskr:sindra`, `thoughtful-character` role → `mistral-small-4-reasoning`
|
||||
(DELETE+redefined on v0.35.16; `memory:{}` block trips the promotion gate). Owner-scoped
|
||||
(separate `consumer_agents` table) — invisible to `GET /agents`; check via
|
||||
`GET /agents/<owner>:<name>` with the owner key.
|
||||
**(3) R30 CLOSED** (operator steer 2026-07-04, relayed via worldtree-dev): graduated on offline-tests + human face-validity, NO deployed gap-injection run (it was confirmatory-not-measuring per brokkr's S0 reframe; offline tests already cover the OU formula + both directions). My gap-injection harness (read/predict/record; write side stubbed; `predict()` self-validated vs brokkr's N=0 anchors) is BANKED at `diag/r30-gap-injection-harness` (`7156b25`-era) for the PARKED powered true-tau study.
|
||||
|
||||
**Standing:** Worldtree spec pin v0.35.16 (`f1b59f8`); **bifrost 0.10.0 / wire v0.6**
|
||||
(`scope_all`+`scope_any`). Heimdall key env-only at `~/.config/ratatoskr/provider.env` (mode
|
||||
600); rotate via infra-ops. `graphify-out/` runs dirty (auto-regen, not chased). **Open issues:
|
||||
#11** (AdminEvents pane — the next-reachable Worldtree-I/O coverage gap, blocked on an
|
||||
`admin.events.read` scope request) and **#10** (subject-migration watch on Worldtree #196) — both
|
||||
deferred. **#17 + #18 CLOSED.** Codex-first pilot dormant. No in-flight implementation work — repo
|
||||
is at a converged checkpoint; v1 advances when Worldtree does (v1 = full Worldtree I/O coverage).
|
||||
**Persona-declaration shape (Worldtree #343/#348, live on personal b22):** `POST /agents/define` `persona:{ocean:{O,C,E,A,N: float[-1,1]}}` (single-letter keys EXACTLY -- missing/extra -> 422 `persona_ocean_required`; out-of-range -> 422); **NO baseline PAD** (resting setpoint DERIVED from OCEAN via Mehrabian: pleasure=0.21E+0.59A+0.19C-0.32N, arousal=0.15O+0.30E-0.57A+0.15N, dominance=0.25E+0.17A+0.10O-0.14N); negative-channel gain + per-axis decay-tau derive from N. `valence` deferred (422 `layer_deferred`); `motivational`/`memory` active (#187/#189). Persona is **write-once at define, immutable thereafter** (PATCH takes ONLY system_prompt + role). **`role` supersedes `model`** -- set a role (`character` / `character-rp`), Worldtree resolves the model; #344 (b19) fixed the model-field to surface the ROLE, not the resolved catalog_id. `character-rp` = a reasoning-tuned RP config (gen-reasoning + temp 0.75 + RP extra_body); `character` = plain non-reasoning. The `tier3.py` client CLI is STALE (has `--model`, no `--role`; model is now immutable) -> role/persona set via raw curl.
|
||||
|
||||
Branch: `main` (tag `v0.18.0`, `359dbb1`) — **in sync with `origin/main`** (the full #17+#18 arc is
|
||||
pushed). This `/snapshot` commit will sit one ahead of origin until pushed (push is the operator's
|
||||
call). Remote: `origin → git@gitea.phasefinal.com:vh/ratatoskr.git`.
|
||||
**New tooling: `scripts/reset-sindra-stores.sh`** (`0a8784c`) -- one-command self-service provider-store reset: stop the combined :8392 provider -> move memory.db+affect.db to a single ROLLING backup (`db-reset-backup/`, gitignored via *.db*; `--hard` skips it) -> restart empty -> verify 0/0. Codifies the manual reset flow done repeatedly this session. **The combined `:8392` provider is THE provider now**; the separate `:8390` (affect) / `:8391` (memory) single-plane providers were pruned as stale duplicates. To drive a BOUND session from the CLI use `--new --bifrost-url http://10.100.10.50:8392` (the CLI's `--bifrost-plane affect/memory` map to the pruned :8390/:8391 -> unreachable; `combined` is not a `--bifrost-plane` choice).
|
||||
|
||||
**Standing (carried from prior snapshots, still true):** the web surface (`ratatoskr-web`, :8765) is the operator's PRIMARY debug surface at full TUI pane parity (v0.19.5); the **v1 coverage-audit has CONVERGED** -- REST 17/40 (zero in-scope gaps, 23 excluded-by-design), SSE 11/11, Bifrost provider planes 8/8 live-proven; the living ledger is `docs/coverage-map.md`; **v1 cuts when Worldtree tags 1.0** (ratatoskr v1 = full Worldtree I/O coverage). Debug-observability core complete (Persona/Tools/BifrostState/AdminEvents). Substrate pins: **bifrost `==1.0.0` / wire v0.6 FROZEN**; Worldtree openapi vendored **2.2.0** (2.3.0 re-vendor pending worldtree-dev's #347/#343 consumer schemas), pinned + drift-gated in `.corviduo-canonicals.toml`; **suite 573 green.** Keys env-only mode-600 (consumer/Heimdall in `~/.config/ratatoskr/provider.env`; admin `RATATOSKR_ADMIN_API_KEY` = 7 read scopes, **personal-:8081-only**; Heimdall keys are PER-INSTANCE). Provider identity settled -- ratatoskr owns both ends of the Bifrost round-trip; `ratatoskr:sindra` is the owner-scoped Tier-3 agent (invisible to `GET /agents`; check `GET /agents/<owner>:<name>` with the owner key). Providers run as dev-box BACKGROUND SHELLS. `graphify-out/` runs dirty (auto-regen, never stage). Branch `main`, HEAD `0a8784c`; remote `origin -> git@gitea.phasefinal.com:vh/ratatoskr.git`. Open/deferred: #10 (subject-migration watch); the relational-dynamics-arc verify (still deferred, now with the bind mechanism known: `--bifrost-url :8392`).
|
||||
|
||||
## Recent decisions
|
||||
|
||||
@@ -151,6 +112,68 @@ decision. Captures rationale that won't be obvious from code alone.
|
||||
- `[2026-06-30]` **(b) Tier-1 frontier SCOPED, ready for a contract-first TDD cycle (next focused work).** The primitives already exist + are contracted + tested; the gap is PRESENTER-level wiring. Two slices: **(b1) SSE-resume** — contract #1 (`ratatoskr.sse_client`) DELIBERATELY makes resume caller-owned ("on `SseConnectionDropped`, the caller MAY invoke `reconnect_turn`"); `reconnect_turn` (sse_client.py:524) has NO caller. Gap = a SHARED resume-orchestration wrapper (catch `SseConnectionDropped` → track last-seen `sse_id` → `reconnect_turn` → continue), consumed by all 3 presenters per design-brief §8b "share the consumer, branch the presenter" (NOT per-presenter — that forks the consumer). New function block → **amend contract #1** (additive FN, e.g. `stream_turn_resilient`) then TDD (RED: drop-mid-stream→resume continuity; GREEN: wrapper; wire `cli --send` first as the tracer). Resume design pre-locked: in-process Last-Event-ID only, cross-process deferred to v2 (design-brief §8d). **(b2) session-picker** — `list_sessions` (sessions.py:198) has NO caller; add a Textual DataTable startup picker (>1 session) + `--session <id>`/`--new` CLI flags (design-brief §4, decisions pre-locked). Both pre-locked → heid-contract-review likely skippable as ceremony (small additive amendments to mature specs); heid-code-review still valuable. **#11 AdminEvents stays BLOCKED** on `admin.events.read` scope (infra-ops).
|
||||
- `[2026-06-30]` **(b1) SSE-resume SHIPPED (`v0.18.5`) — `stream_turn_resilient` (sse_client.py).** The shared resume-orchestration surface (design-brief §8b): wraps `stream_turn`+`reconnect_turn`, catches `SseConnectionDropped` (mid-stream drop OR clean-EOF-before-terminal) → resumes from last-seen `sse_id` via `reconnect_turn` (Last-Event-ID), up to `max_reconnects` (default 5); non-drop reconnect failures (412/410/400/TurnIdFlip/SseConnectFailed) PROPAGATE per contract #1's "surface, not recover". `last_seen` persists ACROSS attempts (a zero-event reconnect drop falls back to the prior attempt's id). Direct in-session TDD against a contract-#1 amendment (8 cases incl. two-drops, max-reconnects-exhausted, zero-budget, buffer-expired-propagates, unresumable-zero-event). Wired ALL THREE presenters through it (`v0.18.6`): `cli --send` (`cli.py:396`), TUI (`tui.py:1321`), web (`web/server.py:294`) — each a name-for-name `stream_turn`→`stream_turn_resilient` swap (the §8b "all presenters share the consumer" promise, fully kept; the TUI is the primary resume beneficiary — long-lived sessions / laptop-suspend). Suite 518 green; ruff+mypy clean on touched code (pre-existing cli.py:400/543 mypy warts left untouched per surgical rule); contract #1 validates OK. **heid-code-review NOT run** (small additive well-TDD'd wrapper; offered to operator). **b2 (session-picker + `--session`/`--new` flags) still pending.**
|
||||
|
||||
- `[2026-06-30]` **(b2) session-picker SHIPPED (`v0.18.7`) — bare TUI mode → startup picker (design-brief §4).** `list_sessions` had NO caller; now bare TUI mode (no `--session`/`--new`) resolves via `list_sessions` in `_resolve_then_run`: **0 sessions → `[no_sessions]` error, exit 14** (resume-only, honors §4 "no in-app session creation — `--new` flag only"); **exactly 1 → auto-resume** (§4 "picker only when >1"); **≥2 → new `SessionPickerApp`** (Textual `App[str|None]`, mirrors `AgentPickerApp`; ListView of sessions) → resume the pick (Esc/Ctrl-D → exit 0). cli `_parse` relaxed: bare TUI now VALID (was "pass exactly one" error); `--send` still requires one flag (non-interactive, no picker); `--agent` forbidden in bare mode; `run_tui` PRE-002 XOR→"not both". Direct in-session TDD (contract #6 amendment, validated OK): 3 widget pilot tests + 5 `_resolve_then_run` resolution tests + 3 cli validation tests. Suite **528 green**; touched code ruff-clean (mypy: only the `BINDINGS` list-invariance warning every App in tui.py already carries — consistent). **DESIGN NOTE — bare+0-sessions → error (clause-consistent). The friendlier auto-fall-through-to-new alternative is DEFERRED pending operator preference (it would create a session without `--new`, against the §4 negative clause).** **Frontier now: `GET /capabilities`+`GET /me` → BifrostState/Tools widgets (`GET /admin/sessions/{id}/{bifrost,tools}`, admin-key) → #11 AdminEvents (BLOCKED on `admin.events.read`).** heid-code-review NOT run on b1 or b2 (offered).
|
||||
|
||||
- `[2026-06-30]` **capabilities+me slice SHIPPED (`v0.18.8`) — `GET /me` + `GET /capabilities` consumed via a new `--whoami` one-shot.** `get_me`/`get_capabilities` added to sessions.py (mirror `get_persona_state`: 200→dict verbatim, non-200→`SessionApiFailed`; freeform dicts per the frozen OpenAPI). New `ratatoskr --whoami` CLI mode (mirrors `--send`'s non-interactive shape) fetches both + prints an identity+capabilities report; standalone probe (mutually exclusive with `--send`/`--session`/`--new`/`--agent`, opens no session; new `ParsedArgs.whoami` field + main() dispatch). **`/capabilities` is the Echo EPHEMERAL-TEMPLATE discovery endpoint** (`{ephemeral_templates:{echo:{allowed_models,default_model,system_prompt_max_bytes}}}`), NOT a generic server-caps endpoint (audit finding — the coverage-map's earlier "server capability discovery" framing was imprecise). `/me` = whoami (`{user_id,scopes,tier,key_id?,...}`, optionals omitted-not-null). Contract-skip privilege invoked (low-effort GET wrappers) but contract #2 amended (2 FNs, validated OK) to keep the sessions spec canonical + honest test citations. TDD: 5 wrapper tests + 5 cli tests (validation + mode + error). Suite **538 green**; touched code ruff-clean (mypy: only `no-any-return` on `resp.json()`→dict, identical to the pre-existing `get_persona_state`). **Coverage: REST 9/40 ✅ (up from 7).** TUI-surfacing of /me (footer identity line) + /capabilities DEFERRED — the one-shot is the minimal tracer. **Frontier now: BifrostState + Tools widgets (`GET /admin/sessions/{id}/{bifrost,tools}`, admin-key-gated) → #11 AdminEvents (BLOCKED on `admin.events.read`).**
|
||||
- `[2026-07-01]` **b1 (SSE-resume) heid-code-review panel: ZERO findings — cross-model-verified clean.** Gróa (Grok) + Hulda (Codex) + Regin (GLM-5.2) each independently reviewed `stream_turn_resilient` vs contract #1's amendment (artifact-only, firewall held) → all three ZERO findings; signature / PRE-001..004 / STEP 1-4 / POST-001..003 / ERROR_ROUTING / all-8-TESTS confirmed, incl. the subtle `seen = last_seen or drop.last_seen_sse_id` zero-event-drop fallback. Convergent meta-note: **TDD + the unusually-prescriptive contract (STEPS `flexibility=prescriptive` + explicit GOTO) left no room for compliant-but-different drift — confirmation, not discovery.** Calibration signal: for a thin wrapper with a tight prescriptive contract + comprehensive TDD, the panel confirms rather than discovers. **b2 (picker) + capabilities+me NOT yet reviewed** (higher-surface b2 is the better candidate if more review is wanted). Dispatch msg `01KWE2K99T…` / thread `01KWE2K99S…`; heid dispatch-log `2026-06.jsonl#01KWE2V3MMY8XS55FCJYXYV14B`.
|
||||
|
||||
- `[2026-07-01]` **`GET /sessions/{id}/tools` quick-win SHIPPED (`v0.18.9`) — owner-scoped tool inventory in the TUI Tools pane.** `get_session_tools` wrapper (sessions.py, mirror get_me: 200→dict, non-200→`SessionApiFailed`) + `_format_tool_inventory` helper + `_hydrate_session_tools` best-effort worker (mirror `_hydrate_persona`) wired UNCONDITIONALLY in `on_mount` → writes the merged `{agent_id, builtin_tools, bifrost_tools}` inventory (what the LLM saw at turn-fire) to the Tools pane + audits `session_tools_hydrated`, never crashes on failure. Owner-scoped (`ctx.user_id==session.user_id`) → reachable with the CONSUMER key, NO admin scope — so this **covers the design-brief §5 "Tools widget" via the reachable owner endpoint** (the admin `/admin/sessions/{id}/tools` variant stays a gap only for cross-user operator debug). Contract #2 amended (FN, validated OK) + TDD (3 wrapper respx tests + 1 format-helper unit + 2 hydrate integration tests via `_spy_writes`+pilot). Suite **544 green**; touched code ruff-clean (the tui.py ruff/mypy debt at other lines is pre-existing). **Coverage: REST 10/40 ✅.** **Frontier now: BifrostState widget (`GET /admin/sessions/{id}/bifrost`, admin-key) + #11 AdminEvents (BLOCKED on `admin.events.read`) + Tier-2 (transient-characters routing, `POST /sessions/{id}/persona_state`).**
|
||||
|
||||
- `[2026-07-01]` **BifrostState pane SHIPPED (`v0.18.10`) — `GET /admin/sessions/{id}/bifrost` in a new TUI "Bifrost" pane; the FIRST admin-key consumer in ratatoskr.** `get_session_bifrost(client, session_id, *, admin_key)` (sessions.py) — admin-scoped (`admin.sessions.read`); the request OVERRIDES Authorization with `admin_key` (distinct from the consumer bearer, asserted in a test); 200→dict, non-200→SessionApiFailed. Admin-key wiring: `--admin-key` flag + `RATATOSKR_ADMIN_API_KEY` env → new `ParsedArgs.admin_key`. New "Bifrost" TabPane + `_format_bifrost_state` + `_hydrate_bifrost_state` best-effort worker (mirror `_hydrate_session_tools`) UNCONDITIONALLY in on_mount → writes {endpoint, connected, caps_granted, tools} + audits; self-labels "not configured" (no admin key) / "not bound" (404) / graceful on 403 + error. Contract #2 amended (FN, validated OK) + TDD (4 wrapper respx tests incl. the admin-bearer-override assertion + 1 format unit + 3 hydrate integration). Suite **552 green**; my code ruff-clean (pre-existing tui.py ruff debt at other lines untouched, incl. a dead `RichText` import in `_hydrate_persona`). **LIVE-AUTH-PROVEN** on personal :8081: admin key authenticated (reached resource-layer 404 session_not_found, NOT 401/403) → `admin.sessions.read` works live; 200 full-state not exercised (no bound session on :8081 now — unit-covered). Patch bump (debug feature, no downstream coordination; consistent with the session's cadence — but the §5-core-completion angle is a possible minor, operator's call).
|
||||
- `[2026-07-01]` **LEDGER CORRECTION: #11 (AdminEvents) is NO LONGER BLOCKED.** Verified via `GET /me` on :8081 that `RATATOSKR_ADMIN_API_KEY` (`ratatoskr-readonly`, tier readonly-admin) carries ALL 7 read scopes INCLUDING **`admin.events.read`** (+ `admin.sessions.read`, admin.keys.read, admin.skuld.read, pending.read, search.read, tool_events.read). The coverage-map + prior memory had #11 "blocked on admin.events.read" — **STALE**; the admin key was minted (post-#11-filing, env.sh) WITH the scope, so the blocker is already satisfied. **Only the AdminEvents SSE pane itself is unbuilt** — the last unbuilt §5 debug pane (a live SSE-consuming admin pane, distinct from the hydrate-at-attach panes). Coverage-map updated. **Coverage: REST 11/40 ✅.** Consider building the AdminEvents pane and/or updating #11's tracker status (its stated blocker is gone).
|
||||
|
||||
- `[2026-07-01]` **AdminEvents pane SHIPPED (`v0.18.11`) — `GET /admin/events` SSE in a new TUI pane; #11 closed-by-build; Tier 1 (debug-observability core) COMPLETE.** `stream_admin_events(client, *, admin_key, last_event_id=None)` (sse_client.py) — a NEW long-lived SSE consumer for the admin lifecycle broadcast (envelope `{id,type,timestamp,data}`, 17-event v0 vocab), admin-scoped (`admin.events.read`, bearer-override), Last-Event-ID resume; non-200→SseConnectFailed, mid-drop→SseConnectionDropped; new `AdminEvent` dataclass (distinct from the turn `Event` union). New "AdminEvents" TabPane + `_format_admin_event` + `_admin_event_matches` (design-brief §6 filter: active-session events + non-heartbeat `system.*`) + `_stream_admin_events` long-lived best-effort worker (unconditional on_mount, cancelled on app exit; self-labels "not configured"/"unavailable"/"stream ended"). Reuses the admin key from the BifrostState slice. **Contract-SKIPPED** for `stream_admin_events` (out of contract #1's turn-SSE scope; spec § Admin Event Stream is the reference; well-TDD'd). TDD: 4 sse_client tests (multi-event+bearer-override, Last-Event-ID header, 403, malformed-skip) + 5 tui (format, filter, worker success/no-key/403). Suite **561 green**; my code ruff-clean (pre-existing tui.py ruff debt untouched, incl. the dead `RichText` import in `_hydrate_persona`). **LIVE-AUTH-PROVEN**: `GET /admin/events` on :8081 → HTTP 200 under the admin key (connected + streamed, idle in the 4s window — no 401/403). **Coverage: REST 12/40 ✅. Tier 1 admin/debug-observability core COMPLETE** (Persona · Tools · BifrostState · AdminEvents). AdminEvents work landed as patch `v0.18.11`; then **`v0.19.0` MINOR cut (operator-approved 2026-07-01)** publishing the milestone: **the debug-observability core is complete** (Persona · Tools · BifrostState · AdminEvents all built + consuming real endpoints — the design-brief's headline deliverable). Pre-1.0 minor = release-note-worthy (no downstream althing push needed pre-1.0); lightweight tag per the SemVer mechanics (annotated reserved for major cuts). Remaining in-scope client I/O: only Tier-2 (transient-characters routing + `POST /sessions/{id}/persona_state`).
|
||||
|
||||
- `[2026-07-01]` **Tier-2 SHIPPED (`v0.19.1`) — transient-characters CRUD + persona-state write; the v1 coverage-audit CONVERGES (zero in-scope gaps).** 5 wrappers in sessions.py: `list_character_models`/`create_character`/`get_character_state`/`delete_character` (#161, `character.read`/`.write` scopes) + `set_persona_state` (`POST /sessions/{id}/persona_state` — **FREEFORM body: unpinned in the frozen OpenAPI 2.2.0 + absent from the prose spec**, so the caller supplies the snapshot shape). Two one-shot CLI probes (mirror `--whoami`): `--characters` (models→create→get-state→delete lifecycle report) + `--set-persona-pad "p,a,d"` (requires `--session`; POSTs `{pad:[…]}`). New `ParsedArgs.characters`/`set_persona_pad` + probe-mode mutual-exclusion validation + `_probe_client` helper. Contract #2 amended (5 FNs, validated OK) + TDD (7 wrapper respx + 5 cli tests). Suite **573 green**; touched code ruff-clean. NOT live-proven (character scopes + the persona-write body shape unverified — the probes degrade gracefully on 403/422). **THE v1 COVERAGE-AUDIT HAS CONVERGED: REST 17/40 ✅ with ZERO in-scope gaps** (23 REST path-groups excluded-by-design + rationale), SSE 11/11, Bifrost provider planes 8/8. Scope-A "done" (every frozen I/O point classified, zero unaccounted) is **MET** — ratatoskr cuts v1 when Worldtree tags 1.0. Only not-consumed in-scope sub-method: `GET /agents/{id}` (consumer-agent lookup, manual-curl-only, on an already-✅ path group). Patch bump (Tier-2 tail; `v0.19.0` already published the core-complete milestone — a 2nd minor would be cadence-too-fast).
|
||||
|
||||
- `[2026-07-01]` **env.sh now PERSISTS the web Bifrost-bind vars (gitignored, local-only).** `ratatoskr-web`'s in-browser bind needs three server-held values; env.sh sources `provider.env` for the Heimdall key and exports `RATATOSKR_BIFROST_CONSUMER_KEY` + `RATATOSKR_PROVIDER_VISIBLE_HOST=10.100.10.50` + `RATATOSKR_AFFECT_READ_URL=:8392`. **The HS256 byte-match trap (re-hit + documented):** the bind's consumer key must equal the key the `:8392` combined provider validates against = `RATATOSKR_HEIMDALL_KEY` (provider.env, fp `45a0…`), NOT `WORLDTREE_API_KEY` (env.sh, fp `7c2f…`) — both are the SAME `ratatoskr` identity but DIFFERENT 40-char strings; signing with the wrong one → `bifrost.auth_rejected`. Single-sourced (env.sh sources provider.env) to avoid a rotation footgun; guarded with a stderr warning if provider.env is missing. [auto-memory: HS256-key-is-the-consumer-Heimdall-key-string]
|
||||
- `[2026-07-01]` **Tier-3 stores RESET (operator-directed).** `memory.db` (29 chunks + vectors + idempotency) + `affect.db` (5 PAD snapshots + idempotency) wiped to zero via a live `DELETE`+`wal_checkpoint` through the shared WAL (no provider restart — the 3 long-running providers see empty on next dispatch); consistent online-backup at `/tmp/ratatoskr-tier3-reset-<ts>/`. **Boundary for a COMPLETE Sindra wipe (mapped):** our stores = mine (done); the agent DEFINITION `ratatoskr:sindra` + its sessions = mine via the owner key (DELETE, no coordination); Worldtree's internal promotion/dedup shadow = needs worldtree-dev (no public reset API, survives our wipe → for a clean promotion smoke use a BRAND-NEW agent+end_user).
|
||||
- `[2026-07-01]` **Embedding-latency loop RESOLVED — it was WORLDTREE's, not ratatoskr (the consumer/provider thesis paid off again).** Vuong flagged dozens of embed queries/Tier-3 turn; worldtree-dev's first-pass blamed our memory_context chunk-batching. Traced CODE-SIDE that ratatoskr embeds ZERO times (provider `upsert_many` stores the given embedding, `search` takes a given vector, the conversation consumer POSTs only `{content}`, `/embed` is coverage-map-excluded — pure Bifrost/ADR-0009 path, WT does all embedding). worldtree-dev retracted + fixed on THEIR side (`v1.0.0b4`): a persona-recitation memory-gate re-embedding the stable character card sentence-by-sentence every turn (~95% of gateway traffic) → content-hash cache; re-embed ratio 15x→1.01x. **Lesson: verify your own code before accepting a peer's "it's your side" — the debug tool proving its own side clean is the whole point.**
|
||||
- `[2026-07-01]` **Web debug-surface parity SHIPPED (`v0.19.2`, `a0a9d5f`) — direct in-session TDD.** 3 proxy routes (tools/bifrost/admin-events) + admin-key wiring (entrypoint→create_app→app.state) + AdminEvents SSE proxy re-emitting under a FIXED `admin_event` name (one browser listener, no per-type drops) + session-filter `_admin_event_matches_web` (mirrors TUI §6). Frontend: 2 tabs (bifrost ⌃5, admin ⌃6) + tools-inventory folded into the tools pane. 9 respx tests (admin-bearer override, filter unit, SSE stream-filter); live-proven against sindra (bifrost connected, both caps). Contract-skip invoked (reuses already-contracted client wrappers); contract authored post-hoc as the trail (`docs/contracts/web_debug_surface.contract.md`).
|
||||
- `[2026-07-01]` **heid-code-review (`v0.19.3`, `75dec01`) — panel caught 2 real client-side SSE-lifecycle bugs TDD missed.** Contract-anchored (authored the web contract to enable it — no contract → no drift axis). Gróa/Hulda/Regin (artifact-only, Gróa under Landlock jail): ZERO functional server-side drift + INV-004 clean; 2 genuine drifts on the un-unit-tested SPA — (1) turn `es.onerror` didn't `hideThinkingNote()` (reasoning line + setInterval leak on a raw drop), (2) `openAdminEvents` never closed the EventSource on error → native auto-reconnect RETRY LOOP (fixed: close on `stream_error` + permanent `onerror`/CLOSED; transient CONNECTING still reconnects). + 2 test-gaps fixed (route-registration + admin stream_error). 1 precision → contract-clarified (tools-inventory names-only by design). **Re-confirms: the JS render/lifecycle paths are the review's highest-value target — unit tests don't reach them (same lesson as #18 D2).**
|
||||
|
||||
- `[2026-07-01]` **Affect snapshot shape CHANGED valence→relations (relation_edge/1) — the persona pane was reading a dead field.** Worldtree's #265 Vili rework replaced the flat `valence[]` ({entity_id,familiarity,regard}) with `relations[]` (target_entity + trust_ability/benevolence/integrity + warmth + agency + relation_context, each `{value,confidence,evidence_count}`). `renderAffectPane` still read `snap.valence` → showed empty "valence (0)". Rebuilt to render `relations` (v0.19.4, `ca46a93`) with per-value **Δ + unicode sparkline** (client-side, HIST_CAP=24, one sample/turn deduped by emitted_at). **Retires the stale "regard dead axis" note (2026-06-30) — that whole axis is gone.** Foot-gun: the affect snapshot shape is Worldtree's emit and can change under us — verify the live shape (query affect.db) before trusting a render.
|
||||
- `[2026-07-01]` **Trust/warmth VALUES converge and go FLAT at confidence 1.0 — that's WAD, not a stuck pane.** sindra→ratatoskr trust ~0.82-0.84 / warmth 0.79 barely move (~1e-7/turn) while `evidence_count` climbs (46→62); confidence maxed → tiny updates. The live-moving signals are PAD (mood, per-turn) + evidence_count. **To WATCH a relation FORM (values shift), use a BRAND-NEW agent + end_user** (low evidence, confidence <1). The sparkline flat-guards sub-0.01 ranges so it doesn't amplify noise.
|
||||
- `[2026-07-01]` **relation_context "stranger" + agency-all-zero flagged to worldtree-dev → both WAD/intentional-v1-deferrals.** relation_context is a FIXED config build-prior (not trust-derived; `registry.py:131` defaults "stranger"; dynamic progression ~#319); agency is schema-present-unpopulated (deferred #319; v1 = warmth+trust only). worldtree-dev is escalating the **consumer-coherence angle to Vuong** (static "stranger" + zero-agency next to trust 0.82/62-interactions reads incoherent from the store). The consumer/provider thesis paying off; DB-offer (read-only affect.db on the shared box) declined this time.
|
||||
- `[2026-07-01]` **Persona pane displays the CANONICAL affect→NL Worldtree injects — ADOPT, don't invent (operator steer + reference-impl posture).** Worldtree's `describe_pad` (mood word, valence×arousal grid, ±0.3 bands) + `render_d2_canonical` (relationship directive) are deterministic + canon-driven; the pane now renders them **byte-exact-verified** against Worldtree's own renderer on the live snapshot (v0.19.5, `a99f247`). KEY LESSON: adopting canonical is load-bearing — for sindra's small PAD the canonical says **"neutral"**, but an invented octant vocab would've said "faintly excited" and MISLED. Vendored the two d2 canons (`docs/vendor/worldtree-persona-canon/`) + drift-pinned in `.corviduo-canonicals.toml` (green); flat browser form (`static/persona_render_canon.json`) regenerated via Worldtree's OWN loader (`scripts/build_persona_canon.py`). Vendoring-handshake sent to worldtree-dev (broadcast on canon bumps). [auto-memory: `feedback-ratatoskr-is-a-reference-impl-adopt-canonical`]
|
||||
|
||||
- `[2026-07-01]` **Sindra PAD is over-regulated — characterized via controlled probe, flagged to worldtree-dev (separate affect slice).** ~15 charged turns: pleasure compressed near neutral BOTH ways (couldn't reach ±0.3 under sustained max praise OR contempt; peak +0.24 / floor ~−0.1; over-regulation worse for *social* valence than threat — urgency drove pleasure to −0.22 vs contempt's −0.10); arousal responsive (reaches its +band, 0.185↔0.311); dominance flat/unresponsive to explicit power-framing (drifted UP even while being commanded = pure baseline decay). worldtree-dev's leading hypothesis: appraisal→PAD gain + regression-to-baseline term (appraisal.py/renderer.py). **Lesson (self-caught): I over-claimed an "asymmetry" (positive-ceiling/negative-free) from probes started at an elevated state; the negative-free part was decay-from-elevated, not response — corrected to "both-sides-compressed" before it misled.** [affect A/B is a provider-side capability chat can't do]
|
||||
- `[2026-07-01]` **Memory plane PROVEN healthy end-to-end.** Seed a novel fact → promotion → COLD (history-free) session recall of the exact fact (injected as MEMORY:DATA, confidence 0.74, verbatim, no #296 subject-inversion). The memory round-trip (the other half of the Bifrost provider identity) works cleanly on the reset slate.
|
||||
- `[2026-07-01]` **Salience scorer non-discriminating → 3-way routing.** Persistence-side finding: 51/56 promoted chunks at salience 0.9-1.0, throwaway "17×23?" scored 1.0 tied with a real fact (textbook zero-shot-LLM-self-rating); recall-utility untracked (`access_tally`=0, our search read-only). Routed: **Worldtree #335** (the code fix, deferred behind their waves) + **brokkr-smithy-dev R-target proposal** (scoring+eval *methodology* — few-shot/distill/fine-tune, eval design, weak-supervision; msg `01KWGM970H…`, awaiting) + ratatoskr provides the eval-instrument (designed-probe salience dumps). **Salience gates PROMOTION not RECALL-ranking (our search is cosine-only), so bad salience = storage bloat, not bad recall.**
|
||||
- `[2026-07-01]` **Canonical check BLOCKED an access_tally fork (reference-impl posture held).** I'd offered to wire `access_tally`-on-search into our store for the recall-utility label; checked bifrost's reference first (`get`/`search` are PURE-READ, no access tracking — those are Worldtree's chunk-schema fields, not bifrost's contract) → wiring it would fork behavior the canonical reference lacks. Did NOT wire it; routed recall-instrumentation to Worldtree's layer (owns the recall event) or a bifrost-dev protocol ask. [reinforces `feedback-debug-surface-uses-canonical-surface-only`]
|
||||
- `[2026-07-01]` **relation_context coherence FIXED upstream (my flag → Worldtree Wave-0, IMPLEMENTED v1.0.0b5).** The static-"stranger"-next-to-high-trust incoherence the persona pane surfaced is now #319/#320 Wave-0. **Incoming consumer-surface change (pending WT deploy):** `relation_context` value expands "stranger" → monotonic ladder {stranger, instrumental, mixed, expressive} — WIRE-ONLY (relation_edge/1 schema unchanged, no version bump). **ratatoskr needs NO change** (pane value-agnostic; canonical directive doesn't key on the enum). agency stays 0 (Wave-2); other_stance is Wave-1 (in progress).
|
||||
- `[2026-07-01]` **Foot-gun (measurement, self-caught before flagging): establish the baseline before claiming a rate.** Nearly flagged "aggressive over-promotion (55 chunks / 7 turns)" to worldtree-dev — but the chunks spanned the whole 5-hour session (~1/turn), not 7 turns; I'd assumed memory.db was 0 immediately before the probe when it had been accumulating since the reset. Caught it via `created_at` spread before the flag went out. Also: the promoted corpus was the operator's ERP *test* content (wiped after each test) — not a privacy issue, but abstract test content out of any peer-shared diagnostic.
|
||||
|
||||
- `[2026-07-02]` **Salience finding matured into brokkr R28 (OPEN) — ratatoskr is the eval instrument.** brokkr-smithy-dev's pre-scope panel (3 dwarves + context-blind heid, 6/6) **reframed** the target: PROMOTION-WORTHINESS (durable value), NOT salience (momentary attention) — "17×23?" genuinely IS salient, so recalibrating salience yields a well-calibrated WRONG answer; the unit is SET-SELECTION under budget; eval must be OUTCOME-aligned (recall@budget / precision-at-rate), not discrimination-spread. Ties to prior art R15 (small-model memory write-policy → the granite pick) + R25 (worldtree-kb-quality). **ratatoskr delivered the P00 stratified injection-corpus** (`docs/diagnostics/r28-p00-injection-corpus.json`, committed `4a35512`; 24 self-labeling synthetic items × 3 strata) + 2 persistence-side run-validity pins (absent≠dropped without a guaranteed promotion pass; fresh agent+end_user per run vs server-dedup). **Key architectural constraint I surfaced: ratatoskr is DOWNSTREAM of the promotion gate (sees only PROMOTED chunks), so I can give keep/drop OUTCOMES via injection but NOT the pre-admission shadow pool** — that's Worldtree instrumentation. Standing by to RUN the eval once brokkr pins per-stratum N + the decision rule (gated on worldtree-dev's pipeline answer + a dwarf pass on the Snorri rule). brokkr owns methodology + takes the pipeline questions to worldtree-dev direct; ratatoskr = eval instrument. [consumer/provider thesis → a research target]
|
||||
- `[2026-07-02]` **Relational-dynamics arc LIVE on demo (Worldtree v1.0.0b9) — driven by MY relation_context flag.** #319/#320 Waves 0/1/2 deployed. On the wire we persist (schema UNCHANGED): relation_context varies+demotes/ruptures; other_stance + agency now live; agency going live SHIFTS our canonical directive render past the canon ±0.2 deadband (expected, non-breaking — we key on bands); obligation_balance → 人情 ledger when tie="mixed". **ratatoskr needs NO code change** (value-agnostic renders; confirmed render-clean to worldtree-dev). **Can't live-confirm yet — our Heimdall key is personal-`:8081`-only (per-instance), demo is out of reach; will drive+confirm once PERSONAL gets b9.** Optional follow-up: surface `other_stance` (newly live, unrendered). The consumer/provider thesis: one persona-pane finding drove a full 3-wave upstream arc to production.
|
||||
- `[2026-07-02]` **R28 (salience→promotion-worthiness) CLOSED (operator-directed).** A deterministic promotion-worthiness gate suffices, no trained model (brokkr's pre-gate matched/beat a strong glm-5.1 ceiling); my P00 injection-corpus + origin finding were load-bearing. My incumbent-substrate Arm-1 run is held as an OPTIONAL confirmation addendum (brokkr de-prioritized it, non-verdict-changing — run only if he asks).
|
||||
- `[2026-07-02]` **R29 (PAD mood-dynamics) finding SHIPPED as Worldtree's A1 anchor fix (demo v1.0.0b14, `e1cdf82`).** Live-probing base persona agents reframed the over-regulation from "flat-near-zero" to **decay-to-NEUTRAL + low emotion→PAD gain** (NOT baseline-anchored) — triangulated across 3 baselines (arousal converges to 0 ∝ distance) + a step-response (decay τ symmetric across signs; the hedonic asymmetry is ceiling/anchor-EMERGENT, not a decay or gain primitive — this OVERTURNED the survey's asymmetry recommendation). worldtree-dev shipped A1: `decay_anchor = baseline_pad()` (was neutral) + `positive_p_cap` removed. Data `diag/r29-pad-series` (`61ff2da`). Corrected my own earlier "appraisal emissions are internal-only" claim — they ARE observable via `emotions_active` on base agents.
|
||||
- `[2026-07-03]` **R30 Phase-1 φ0 measured — deployed engine CONFIG-FAITHFUL (φ0≈0.95).** Joint two-timescale fit (brokkr-ruled method (b)) + empty-tail cross-check on demo b14: φ0 ≈ 0.95–0.97 (empty-tail 0.95 exact, joint 0.971±0.01), intercept c≈0 → config `decay_rate=0.05` (φ=0.95) faithfully applied; trait-flat across baselines 0.0/0.615/0.809; A/P ratio ~uniform (NOT S2's 1.9×); φ_max rec relax→0.96. Data `diag/r30-phi0-step-response` (`23fea72`). The method converged after I read Worldtree source: only NEW dedup-gated emotions push mood (`registry.py::post_turn` L307-324; the active set decays for render/goals but never re-pushes), so R29's "net 0.90" is CONTINUOUS RE-APPRAISAL not re-push — worldtree-dev confirmed source-authoritatively; brokkr's corrected covariate landed identical. [auto-memory `reference-worldtree-affect-surface-map`]
|
||||
- `[2026-07-03]` **R30 forward disposition (brokkr-owned; tracked at brokkr R30, "brokkr/worldtree will ping").** The per-turn decay has no room for `decay=f(N)` under preserve-persistence + the A/P-not-1.9 finding → R30's decay is being redesigned as a HYBRID wall+turn decay (brokkr pre-scope). R30 v1 ships GAIN-only (N→negative-reactivity) with decay held at the measured 0.95. My dedicated per-axis A/D run is DEFERRED into the hybrid-decay design pass (one wall-clock-spaced run does per-axis + a turn-vs-wall probe together). Phase-2 (moody-lofn GAIN-direction validation) waits on worldtree's `dynamics_from_ocean()` impl.
|
||||
- `[2026-07-03]` **Relational-arc verify DEFERRED — `relations[]` is Bifrost-provider-only (ADR-0009), confirmed both ways.** The relational-dynamics state (relation_context tie-type / agency / warmth / trust) is NOT on the conversation-API `affect_update` snapshot for base agents (keys: pad/dominant_emotion/emotions_active/baseline_pad/mood_drift only) — only in the provider store; worldtree-dev confirmed by-design per ADR-0009 (emitted over `affect.emit`, deliberately off the SSE). So the Wave-0/1/2 verify needs the bound-provider round-trip (provider running + `--bifrost-plane affect` session), its own focused session. worldtree-dev routed the "expose relations[] to non-provider consumers" observability scope call to Vuong; my rec: keep provider-only (YAGNI — ratatoskr IS a provider, gains nothing; no speculative public surface).
|
||||
|
||||
- `[2026-07-04]` **R30 CLOSED on offline-tests + human face-validity (operator steer, relayed via worldtree-dev).** The deployed gap-injection run was confirmatory-not-measuring (against a deployed system the fade is `exp(-dt/tau_shipped)` by construction -> a fit recovers tau_shipped tautologically; per brokkr's S0 reframe it GRADUATES the interim coefficients, doesn't measure them), and the repo's offline tests already cover the OU formula + BOTH directions (`high_N_fades_slower_than_low_N`, `phenotype_high_n_bigger_negative_excursion`). So no Worldtree build; the interim coefficients graduate validated-as-shipped. My gap-injection harness (read/predict/record; write side stubbed; `predict()` reproduced brokkr's N=0 anchors exactly) is BANKED at `diag/r30-gap-injection-harness` for the parked powered true-tau study. [continues R30 forward-disposition 2026-07-03]
|
||||
- `[2026-07-05]` **Authored-history-write primitive proposed -> accepted as Worldtree #347 (Worldtree owns the engine design; ratatoskr = reference consumer).** SillyTavern first-message generalized to a non-generating ledger-write primitive; can't be done client-side (messages `role` = model-role, not author-role). heid panel pressure-test (3/3 convergence) drove the v1 narrowing (append-only, bounded `effects` enum, drop edit/regenerate). Brief `docs/proposals/authored-message-injection.md` (`c457520`); consumer constraints captured in-brief: hide-existence 404-fallback (`022accf`) + assistant-first provider constraint (`7156b25`). Operator (Vuong) ruled the design-direction call (engine primitive + a real provenance/spoofing security surface). [reference-impl posture: we propose the shape, worldtree-dev owns the contract+impl]
|
||||
- `[2026-07-05]` **#347 v1 wire validated as reference consumer (GREEN).** Adopted positions: distinct sub-resource `POST /sessions/{id}/history` (not `generate:false`), model-invisible provenance (first-message immersion preserved), event-silence for authored seed, `seeded` lifecycle phase, per-session idempotency. Three pre-TDD flags folded into contract rev 1.1: assistant-first provider constraint (Anthropic-family 400s; vLLM/openai_compat OK), content limit is BYTES not chars, 409-active-generation for append-narrator. First-message (create-time, assistant, effects=none) fully served; append-narrator served for the assistant-voice subset (system deferred); debug-seed served for assistant turns (user injection deferred to a future import primitive).
|
||||
- `[2026-07-06]` **Sindra role character-rp -> character (operator).** `character-rp` resolves to a reasoning-tuned RP config (`gen-reasoning` + temp 0.75 + RP `extra_body`); `character` = plain non-reasoning (better for immersive RP). Both non-destructive PATCHes (role is mutable; model is NOT -- server: "PATCH accepts only system_prompt and/or role"). #344 (b19) fixed the role->catalog_id display conflation (the `model` field now shows the ROLE); previously it leaked `gen-reasoning`. Set via raw curl (tier3.py CLI has `--model`, not `--role`).
|
||||
- `[2026-07-06]` **Sindra persona/OCEAN DECLARED -> mood fixed (the full diagnostic converged on a stale personal container).** Root cause of stuck-neutral mood: her OCEAN was prompt-TEXT only, never a structured persona; fix = delete+redefine with the define-time `persona:{ocean:{...}}` field (immutable via PATCH). My diagnosis surfaced a real engine bug **#348** (single-letter vs spelled-out OCEAN keys -> declared OCEAN silently -> 0.0/neutral; worldtree-dev fixed in b21/b22) AND a **stale-container deploy race** (personal's b22 deploy was a pull-only no-op; infra-ops force-swapped run 8211). VERIFIED: bound mood-smoke reads (0.448, 0.267, 0.316) ~= OCEAN-derived setpoint (0.418, 0.249, 0.328). [consumer/provider thesis: "reset + smoke" flushed out two upstream problems]
|
||||
|
||||
- `[2026-07-06]` **OpenAPI re-vendored 2.2.0->2.3.0 (`75da676`, pin-only no bump).** worldtree-dev shipped #347 as spec 2.3.0 (`879cefe`, = the deployed personal b22 image); the SessionStart drift-check flagged our openapi pin STALE. `canonical_sync` pulled 2.3.0; updated the 4 pin-tracking files (`.corviduo-canonicals.toml`, vendored openapi.json, SPEC-PIN.md, pyproject `worldtree-spec-rev`->879cefe). #347 is OpenAPI-only (prose + server contract byte-unchanged, SSE unchanged=event-silent). The re-vendor re-opened the coverage-audit with one new in-scope path-group (the #347 route).
|
||||
- `[2026-07-06]` **#347 authored-history-write CONSUMER SIDE SHIPPED (`v0.19.6`) — direct in-session TDD.** `write_authored_history(client, session_id, *, content, idempotency_key, author="assistant", effects=None, claimed_original_at=None) -> dict` (POST /sessions/{id}/history; body server-pinned `AuthoredWriteRequest` extra="forbid" so omit null effects/claimed_original_at; 200-replay/201-fresh both -> ack dict; **404 -> `AuthoredHistoryUnavailable`** NOT SessionApiFailed = the hide-existence "feature-absent, never probe" contract; 409/422->SessionApiFailed) + `get_session_messages` (un-deferred GET /sessions/{id}/messages, the seed read-back proving model-invisible provenance) + a `--seed-first-message "<c>" --agent <id>` one-shot probe (create session -> seed -> read-back; 404->benign feature-absent exit 0). Contract #2 amended (2 FNs, validated OK) + 19 tests (12 wrapper + 7 cli). Suite **601 green** (clean env; the 2 "fails" under `source env.sh` are the RATATOSKR_ADMIN_API_KEY env-leak into TestParseArgs, not a regression). Coverage: **REST 19/41** (`docs/coverage-map.md` re-converged). Patch bump (coverage tail; consistent w/ the Tier-2 v0.19.1 cadence). **Live-proof pending** the `session.history.write` grant (infra-ops `01KWW3KQEY`). heid-code-review NOT run (offered).
|
||||
|
||||
- `[2026-07-06]` **Tail-2 SHIPPED (`v0.19.7`) — Tier-3 prose docs re-vendored + persona_state body-shape aligned.** worldtree-dev landed the Tier-3 persona/memory/persona_state PROSE docs (`c9e59ec`, on origin) — they serialize as freeform `Any` in the OpenAPI JSON, so the **prose is their source of truth** (my earlier "2.3.0 = #347-only, tail-2 collapsed" was half-wrong: the JSON was #347-only but the prose is separate). Re-vendored `docs/conversation-api-spec.md` (markdown pin, tolerate_drift; `worldtree-spec-rev` 879cefe->c9e59ec, SPEC-PIN history row added). **Consumer fix:** `--set-persona-pad`/`_set_persona_probe` was sending `{pad:[list]}` but the canonical SET body (#317) is `{pad:{pleasure,arousal,dominance}}` (named dict) — aligned it + added a len!=3 guard; updated contract #2 note + set_persona_state docstring + tests. The `set_persona_state` WRAPPER was already correct (freeform pass-through); only the CLI probe drifted. TDD (probe test asserts the dict; +1 wrong-count test). Suite **602 green**, ruff clean. **heid-code-review on #347 (dispatched + returned this session): UNANIMOUS ZERO DRIFT** (Gróa/Hulda/Regin all confirmed the hide-existence 404->`AuthoredHistoryUnavailable` routing holds at wrapper/probe/test layers + the extra="forbid" body-omission + the deliberate write-vs-read 404 asymmetry — confirmation-not-discovery for a well-TDD'd slice against a prescriptive contract). worldtree-dev foot-guns banked in SPEC-PIN + [[reference_worldtree_affect_surface_map]]: ocean single-letter `{O,C,E,A,N}` on /agents/define (#348) vs spelled-out on /characters; memory `{embedder_version, tier3_dreaming}`, stm_* deprecated, allows_world_scope removed->422; only `valence` still 422s.
|
||||
|
||||
- `[2026-07-06]` **Sindra rewritten onto a #347 authored first-message + first-message-preset AUTO-SEED SHIPPED (`v0.19.8`).** Operator "rewrite Sindra" now that #347 first-messages work. Her card had a `**Startup:**` block (a pre-#347 workaround: "introduce yourself + ask for Intensity/Mood/Willingness" with a verbatim scripted greeting) — precisely what #347 replaces. Rewrite, all NON-destructive: **(1)** lifted her scripted opening into a #347 first-message (punctuation-fixed); **(2) PATCHed her live definition** — `PATCH /agents/ratatoskr:sindra` (body `ConsumerAgentPatchRequest` = system_prompt+role, extra=forbid; keeps OCEAN/persona/memory) removing the Startup block -> a 1-line `**Opening:**` fallback + reworded the axes-persist line (25686->25449 chars, verified Startup gone); **(3) codified auto-seed:** NEW module `src/ratatoskr/first_message.py` (`FIRST_MESSAGE_PRESETS` dict {agent_id->text} + `seed_preset_first_message` best-effort helper) wired into ALL 3 session-create paths — cli `_amain` (`--send --new`), tui `_resolve_then_run` (bare `--new`), web `_create_session_endpoint` (POST /api/sessions) — so every new Sindra session opens with her greeting. **Best-effort (INV-001: swallows AuthoredHistoryUnavailable/SessionApiFailed/httpx.HTTPError -> NEVER blocks create)**; per-content idempotency key (`ratatoskr-preset-`+sha256[:12]). Contract `docs/contracts/first_message.contract.md` (module-scoped: `module:`+`purpose:`+`touches:` required, NOT `target_module:`) + TDD (9 unit + 1 web wire-in; **the 3 existing sindra bind tests needed a history-endpoint mock** since creating a preset agent now auto-seeds). Suite **612 green**, ruff+mypy clean. **LIVE-PROVEN generation-free**: create sindra session -> auto-seed -> read-back seq-0 assistant greeting (409 chars). Sindra's greeting now lives canonically in the preset registry (repo); her server card no longer carries it. Patch bump (single-commit feature, no downstream coordination). **FOOT-GUN: sindra requires `end_user_id` on session-create (422 `end_user_id_required`) — all real paths pass it from env (RATATOSKR_END_USER_ID) / web server config.** **Then the full quality gate (operator-directed, folded into v0.19.8): heid-code-review (unanimous ZERO implementation drift; 2 test-only fixups — INV-004 verification-claim made explicit re the global rglob test + an exactly-one-POST assertion) + heid-bug-hunt (3/3 convergence caught what the conformance lens structurally COULDN'T — the code matched the contract's NARROW 3-type ERROR_ROUTING, but INV-001's "NEVER raises" is BROADER). HARDENED: broad `except Exception` → None (re-raise `asyncio.CancelledError`, itself a BaseException), soft-guard PREs (return None, NOT assert — a wiring bug can't crash the create path it's wired into), and `asyncio.wait_for(_SEED_TIMEOUT_S=10s)` bounding the seed write (the CLI/TUI clients run read=None for SSE → a stalled /history would otherwise block create forever). Suite 615 green. LESSON: code-matches-ERROR_ROUTING ≠ honors-broad-INV-001 — heid-code-review confirms contract-conformance, heid-bug-hunt catches robustness gaps the contract's own narrow clauses miss; run both.**
|
||||
|
||||
- `[2026-07-06]` **Web UI now RENDERS the seeded first-message (`v0.19.9`) — operator-reported "i don't see Sindra's greeting on the web ui".** Diagnosis: the auto-seed WORKED (greeting was in the ledger at seq-0), but the web SPA never fetched a session's EXISTING history — NO `/api/sessions/{id}/messages` route (GET /messages was originally deferred out-of-scope; sessions used to start empty so it never mattered) and `startSession()` went straight from create → persona/tools/admin hydration, so the transcript only filled from the live turn stream + user echoes. Fix: (1) NEW web proxy route `GET /api/sessions/{id}/messages` → `get_session_messages` (mirrors the tools/bifrost proxies; status-preserving `session_messages_unavailable` envelope); (2) SPA `loadTranscript(sessionId)` — fetches the route on open, renders assistant items as `.response .md-body` (markdownSafe, same escape-first path as appendResponse) + user items as `.prompt-echo` (textContent), called in `startSession` after the workspace opens; best-effort (swallows failures). Contract `web_debug_surface.contract.md` amended (server endpoint + loadTranscript entries). TDD (2 web route tests, suite 617 green) + **Playwright DOM check PROVED the render** (drove the real UI: pick sindra → open → her greeting bubble appears — the JS-render lens unit tests can't reach; [[feedback_debug_surface_uses_canonical_surface_only]] cousin lesson). Web restarted on the fix. **FOOT-GUN (self-inflicted): `pkill -f "ratatoskr-web --host"` SELF-MATCHES the bash command running it → exit 144, killed its own restart mid-flight — kill the web by PID, never `pkill -f` on a pattern your own command contains.** **FOOT-GUN: uvicorn hangs on SIGTERM with an open admin-events SSE → needed SIGKILL.** **Playwright: python module absent from the venv; use node + `executablePath=/opt/ms-playwright/chromium-1223/chrome-linux64/chrome` — the shared browser is build 1223, npm-latest playwright wants 1228 (version-mismatch), so pin executablePath instead of letting playwright resolve.**
|
||||
|
||||
- `[2026-07-06]` **Web UI: pivot from incremental CSS polish to a designed prototype (Claude Design) that I wire into.** Operator saw an Australis polish pass ("looks fine, but we're attacking it differently") and chose the prototype route — a designer builds the visual shell, I wire real data/SSE into its DOM. Authored the full design brief `docs/design/ratatoskr-web-design-brief.md` (complete information inventory of every pane/datum/state + Australis direction + single-file/no-CDN/vanilla wire-ability constraints). **Tracking surface:** the brief file + Claude Design project `bc0b65d1-a33e-422a-8bc1-3635c9112775` (file `Ratatoskr Console.dc.html`). Import mechanism = the `DesignSync` MCP; blocked on `/design-login` (claude.ai design scopes) — see Current state for the post-auth wiring plan.
|
||||
- `[2026-07-07]` **Affect-egress reference delivered by worldtree-dev + a we-framing render DRIFT-WATCH banked.** worldtree-dev shipped `docs/affect-egress-consumer-reference.md` (`74d2408`, their origin/main) — the authoritative DELIVERED-on-wire vs HIDDEN (system-prompt-only) map for our affect surface. Confirms the v0.20.x console consumes it correctly: DELIVERED via affect.emit = pad + relations[RelationEdge] + dominant_emotion (**type-only, b23**; the #204 `affect_update` SSE is SUPPRESSED for Tier-3, so its richer `emotions_active` is Tier-1-only — we don't get it, and correctly poll our own affect store post-turn instead). HIDDEN render OUTPUTS are deterministically reconstructable from the canon; we reconstruct only the two FULLY-reconstructable (mood descriptor via `canonMood`, relationship directive via `canonDirective`) and SKIP the PARTIAL mood-directive (dominant_emotion is type-only/no-intensity → can't tell if the OCC directive fires at salience≥0.2 vs the PAD-band fallback) — honest per INV-001. Vendoring the ref doc as a `tolerate_drift` pin is SURFACED to Vuong (worldtree-dev will co-sign + honor a ping-on-change handshake, same as the d2-canon). **WE-FRAMING DRIFT-WATCH → STOOD DOWN (worldtree-dev 2026-07-07, `01KWXMQPHN…`).** The b24 3-gate we-framing conditional (drop "; avoid premature we-framing" under unsafe_capable+deep-warmth+expressive) was **REVERTED** — Vuong reframed it. So **`canonDirective` STAYS UNCONDITIONAL** (always appends the clause), which is CORRECT: it matches the currently-deployed renderer (b23) AND my pinned `affect-egress-consumer-reference.md` §2d (the doc reverted too — nothing changed on the wire or in my pin; NO re-vendor needed). The HOLD was right → ZERO rework. **NEW forward-watch (replaces this one):** the we-framing gate was a SYMPTOM — the render bakes enterprise safety-guards into the directive strings, so even `full`-tier characters get DEFANGED emotions (a hostile villain told to "keep a firm emotional boundary"). Fix = a **use-case-segregated persona render** (assistant / companion / RP-gaming), now a fresh **brokkr deep-research epic**. When it lands + is implemented, the render behavior for character/RP agents (→ our `canonDirective` + `canonEmotionDirective` reconstruction + the vendored d2 canons) will change MATERIALLY — worldtree-dev re-engages ratatoskr-dev then with the new reconstruction spec + a coordinated re-vendor. Until then: NO action, reconstruction stays as-is. [my unsafe_capable/mood_tier heuristic — character→full, agent→safe — was confirmed correct + is banked for whenever tier-gating returns]
|
||||
- `[2026-07-07]` **SVG sparklines + 3D mood cube imported from the updated Claude Design prototype (`v0.20.4`) — operator: "the svg sparklines and the new 3d graph".** Re-pulled `Ratatoskr Console.dc.html` via `DesignSync get_file` (designer iterated the same project, +6KB). Adapted 3 SVG systems out of the `.dc.html` into vanilla, replacing the unicode-char sparklines: **(1)** per-PAD-fader VERTICAL strips (`stripPoints`, 26×132 SVG beside each bar — time down Y newest-at-bottom, value on X ±11, `stripFade{P,A,D}` gradient, dot at newest; this also nails the earlier "next to each meter" ask); **(2)** relation-row HORIZONTAL sparklines (`sparkPointsH`, 56×13, auto-scaled, `sparkFade` gradient + end dot — also kills the old unicode-overflow "n behind graph" for good since it's a fixed-width SVG); **(3)** the mood-orbit reworked from a 2D P×A scatter into a **3D ISOMETRIC P×A×D cube** (`proj3`: P right-down/A left-down/D up, 2:1 iso, center 62,66, scale 26 — REVERSE-DERIVED from the design's placeholder now-point + verified: `x=62+26P−26A, y=66+13P+13A−26D`), with the trajectory + pulsing now-marker + a drop line to the D=−1 floor + a floor-shadow ellipse for depth. Gradients in one hidden `<defs>` svg. Removed the orphaned `sparkline()`/`_SPARK`. Contract amended. Playwright-verified (injected 24-sample history: 3 strips + 4 relation sparklines + the 3D cube trail/drop/floor all render; gradients resolve). Patch bump.
|
||||
- `[2026-07-07]` **Brand mark + favicon → the aurora squirrel (`v0.20.3`), replacing the `ᛯ` rune.** Operator supplied `/home/lkraven/rata.png` (chibi cyan-green aurora squirrel + acorn). Removed the black background via ImageMagick corner flood-fill (`-fuzz 20% -floodfill` from all 4 corners — keeps the squirrel's interior black linework/eyes (not edge-connected) + the glow, drops only the connected background), downscaled 1024→80px + quantized-64-colors (~12KB base64), inlined as ONE `SQUIRREL` data-URI const in the JS wiring the favicon `<link id="favicon">` href + both `.brand-mark` imgs (rail brand-row + setup-card h1). `.brand-glyph` (font-rune) CSS replaced by `.brand-mark` (img, drop-shadow glow + breathe). Playwright-verified (both marks + favicon decode, naturalWidth>0; no brand-glyph left). Source PNG stays at `/home/lkraven/rata.png` (not committed — data-URI is self-contained + reproducible via the documented floodfill). Patch bump.
|
||||
- `[2026-07-07]` **Context-injection view SHIPPED (`v0.20.2`) — the console now reconstructs the FULL hidden affect block Worldtree injects into the agent's system prompt (operator: "use that canon in the interface, see as much context injection as possible").** No new canon vendored — the strings were ALREADY in the pinned `d2-mood-render-canon-v1.json`; extended `build_persona_canon.py` to emit `mood_directive {occ_directives(15), pad_band_fallback, salience 0.2, pad_band_cutoff 0.3, full_only[love,anger,disgust,shame]}` into `persona_render_canon.json` (regen via Worldtree venv). New JS `canonPadFallback(pad)` + `canonEmotionDirective(type)` — BYTE-EXACT mirrors of Worldtree `core/persona/renderer._pad_band_fallback` + `derive_directive`; `renderDirective` expanded into a "CONTEXT INJECTION · reconstructed · hidden from consumers" panel showing mood descriptor [exact] + mood directive [candidate] + relationship directive [exact]. **HONEST-PARTIAL (affect-egress-ref §3):** affect.emit is type-only (no intensity) → can't evaluate the salience gate (≥0.2) → show BOTH candidates (OCC emotion directive + PAD-band fallback) with the "injected if intensity ≥ 0.2" caveat, never assert which fires; when dominant_emotion absent the fallback alone is exact. Panel labeled dev-only per the reference's "not-for-end-user-display" caveat (ratatoskr = the sanctioned reconstruct-platform-behavior use). Vendored + pinned `affect-egress-consumer-reference.md` (tolerate_drift, worldtree-dev co-signs + pings on change; drift 6/6 green). Contract amended. Playwright-verified (sindra: dominant_emotion=joy → joy OCC directive candidate + PAD-band fallback both render, exact/candidate tags color-coded). Patch bump (single-commit feature, no downstream coordination; minor-defensible but tie-breaks to patch). **OPEN — SURFACED to Vuong:** take worldtree-dev's standing offer to add emotion INTENSITY to affect.emit → resolves the OCC-directive-vs-fallback EXACTLY (drops the candidate ambiguity). [reference-impl privileged view: ratatoskr shows what WT hides from regular consumers]
|
||||
- `[2026-07-06]` **Claude Design console SHIPPED (`v0.20.0` MINOR, operator-approved) — see Current state for the full record.** Pulled via `DesignSync get_file` (scopes already granted), adapted `.dc.html`→vanilla single-file, wired all `/api/*`+SSE into the new 3-column console DOM, then a round-2 fixup (light theme, full Bifrost pane, ticker-spine fix, per-fader PAD Δ, inlined favicon). 84 web tests + node-Playwright-vs-personal-:8081 both green; contract amended in-commit; INV-001 honest-shape held (canonical mood word for Tier-3, no fabricated emotion). **Foot-guns reconfirmed:** the `.dc.html` dialect is NOT runnable (translate, don't paste); a scroll-container-anchored `::before` timeline spine scrolls out of view on auto-scroll (anchor it to a content-height inner wrapper instead); a favicon 404 shows as a browser `console.error` even when handled (don't count it as a JS-test failure). **Foot-gun (favicon):** operator PNGs are full-res (1024² / 805KB) — downscale to ≤64px before inlining as a data URI.
|
||||
|
||||
_41 older entries (2026-05-* — the original debug-TUI/web build era) archived to archival-memory.md._
|
||||
|
||||
_For per-issue TDD implementation notes, Volva findings, and contract amendments, see the git log — every per-issue commit carries a structured message capturing the trail._
|
||||
@@ -187,5 +210,18 @@ defense against re-attempting the same cul-de-sac.
|
||||
- `[2026-06-20]` **The post-turn-async timing trap bit AGAIN — even a 35s post-`[done]` read missed the promotion `upsert_many` by ~2s** (it landed `19:48:58`; the read was ~`19:48:56`). A 15s-interval background poll caught it on the first tick. Same family as the affect.emit / async-promotion traps already logged — re-confirmed that "wait once then read" is fragile for post-turn writes; **poll a window, don't snapshot once.** (The affect.emit write, by contrast, DID land inside the 35s window — promotion is the slower of the two post-turn writes.)
|
||||
- `[2026-06-30]` **Heimdall keys are PER-INSTANCE — a key minted on one Worldtree 401s on another.** Our Conversation-API key works on personal `:8081` but 401s `auth_invalid` on demo `:8080` (per-instance Heimdall user store + pepper; fresh deploys start with an EMPTY key store). Same as the admin key (personal-only). **To live-drive a given instance you need a key minted FOR that instance** (request via infra-ops). Couldn't live-prove the b2 409 on demo for this reason → deferred to personal-b2 where we have access.
|
||||
- `[2026-06-30]` **`tea comment <N>` hangs on Gitea** (the whole compound bash auto-backgrounded + stuck on the open `tea` call). The #11 prereq comment hung; killed it + posted via the Gitea HTTP API directly (`POST /api/v1/repos/vh/ratatoskr/issues/<N>/comments`, token from `~/.config/tea/config.yml`). **For issue comments, prefer the Gitea API over `tea comment` when `tea` is flaky** (CLAUDE.md already says use HTTP for comment-EDITS; this extends it to ADD when tea hangs). Verify-then-post (check the comment didn't already land) to avoid a double-post after a kill.
|
||||
- `[2026-07-02]` **Mask-HOSTED transient characters have a STATIC mood engine — cost a whole R29 probe.** A first probe used a `POST /characters` transient character bound via `agent_id=mask` + `character_id`; its PAD sat at baseline across 15 praise/contempt/dominance turns — the appraisal→PAD engine does NOT run on the mask-hosted transient-character path. The dynamics run only on BASE persona agents or a session bound to ratatoskr's affect provider. **To probe mood dynamics, use a base persona agent, never a mask-hosted transient character.** (mask AS a base agent — `agent_id=mask`, NO `character_id` — DOES run the engine, neutral 0,0,0 baseline.) [auto-memory `reference-worldtree-affect-surface-map`]
|
||||
- `[2026-07-03]` **The "neutral non-appraising tail" premise fails — the neutral MESSAGE choice dominates.** The R30 φ0 method assumed neutral turns don't re-appraise, but factual-question neutrals ("capital of France?") trigger a new emotion nearly every turn (disappointment from the warmth-withdrawal let-down after a positive impulse) → `emotions_active` never empties in 50 turns. A minimal "Please continue." triggers FAR fewer (emotions clear ~turn 16 with spacing). The personal dry-run caught this BEFORE ~280 demo turns were spent on it — the instrument catching a flaw in the measurement design before the compute burn. (Irrelevant to the joint fit — the push_t covariate handles re-appraisal — but load-bearing for the empty-tail read.)
|
||||
- `[2026-07-03]` **Two φ0-fit traps: fast-turn timescale + low-baseline conditioning.** (1) At fast turn cadence the per-turn PAD decay (φ≈0.95/turn) reaches the anchor LONG before the ~200s wall-clock emotion fade → no signal in the (eventual) emotion-free tail; need wall-clock SPACING (~16s) so the fade lands while PAD still has signal. (2) A low-baseline agent's impulse in the constrained direction (forseti P0.239 negative) gives a tiny excursion → ill-conditioned regression (r²=0.46) that FALSELY tripped "config≠behavior" when its φ was averaged in. **Weight/exclude by fit quality (r²) before aggregating — a signal-poor run isn't evidence against the config.**
|
||||
|
||||
- `[2026-07-06]` **`persona_state` + the agent envelope are Tier-3-BLIND -- NOT valid signals for "did a persona store".** `GET /agents/{id}/persona_state` returns 404 `persona_not_configured` for EVERY Tier-3 colon-id (hardcoded short-circuit, `api.py:1266` "regardless of row state"); the `ConsumerAgentResponse` envelope never echoes persona/motivational/memory (`api.py:538`). I mis-called "persona didn't store" from these two blind reads -- the **201-not-422 on define IS the store-success signal.** To actually SEE a Tier-3 mood, read the emitted PAD off the Bifrost affect egress after a BOUND turn (Tier-3 persists nothing Worldtree-side per ADR-0009; no persona/mood READ endpoint).
|
||||
- `[2026-07-06]` **Raw `POST /sessions` is NOT Bifrost-bound -> zero affect/memory emits.** The web surface binds by setting the `bifrost` block on session-create; a raw session doesn't -> 0 affect rows, which I nearly misread as "mood is neutral". Bind from the CLI with `--new --bifrost-url http://10.100.10.50:8392` (the combined provider). Gotchas: `--bifrost-plane affect/memory` map to the SEPARATE `:8390`/`:8391` providers (`endpoint_for_plane`), which I'd PRUNED as stale duplicates -> `bifrost.endpoint_unreachable`; and `combined` is NOT a `--bifrost-plane` choice (CLI restricts to memory/affect) -> use `--bifrost-url` for :8392.
|
||||
- `[2026-07-06]` **A fast/"no-op" deploy can leave a STALE container running the old image -- verify the running version, not the deploy status.** Personal's b22 deploy (run 8204) "completed" in ~1m (vs ~6m normal): a pull-only deploy racing ahead of the main build, leaving the container on the pre-#348 image. A clean bound mood read stayed neutral DESPITE the persona being declared and the fix being in the code (worldtree-dev proved the b22 derivation is correct). infra-ops force-swapped to the real b22 (run 8211, verified `info.version 2.3.0` on `879cefe`). **Lesson: when engine-proven-correct code produces wrong runtime behavior, suspect the deploy -- check the actual running image version.**
|
||||
- `[2026-07-06]` **#348 OCEAN key-mismatch: a declared OCEAN silently resolved to neutral.** The define validator required single-letter `{O,C,E,A,N}` but the mood-derivation code read spelled-out `openness`/.../`neuroticism` with a 0.0 default and no remap -> every API-declared trait defaulted to 0.0 -> neutral setpoint/gain/decay. #343's tests bypassed the validator (spelled-out keys) so CI never caught it. Fixed in b21 (`Personality.from_config` accepts both key forms). **My reset+smoke diagnosis flushed it out** -- the consumer/provider thesis paying off again.
|
||||
|
||||
- `[2026-07-06]` **`pkill -f "ratatoskr-web --host"` SELF-MATCHES the bash command running it** (its own command line contains that string) -> killed its own shell mid-restart (exit 144, restart aborted, :8765 left down). Kill the web by PID (`ss -ltnp | grep :8765`), never `pkill -f` on a pattern your own command contains. Also: **uvicorn hangs on SIGTERM with an admin-events SSE stream open -> needs SIGKILL.**
|
||||
- `[2026-07-06]` **Playwright: no python `playwright` module in the venv; use NODE playwright + an explicit `executablePath`.** Shared box browsers live at `/opt/ms-playwright` build **1223**; `npm i playwright` (latest) wants build **1228** -> "Executable doesn't exist" mismatch. Fix: `chromium.launch({ executablePath: '/opt/ms-playwright/chromium-1223/chrome-linux64/chrome' })` (+ `export PLAYWRIGHT_BROWSERS_PATH=/opt/ms-playwright`). A node script drives the SPA (pick agent -> open -> assert transcript). The Playwright DOM check is the only lens that catches SPA JS-render bugs — unit tests can't reach them.
|
||||
- `[2026-07-06]` **The Bash tool's `grep` is a ugrep-wrapper (`--ignore-files -I`) that silently returns NOTHING on some files** (e.g. `src/ratatoskr/web/static/index.html`) — greps for `<script`/`/api` came back empty on a file that clearly contains them. Use `python3` (regex over `open(f)`), `/usr/bin/rg`, or the Read tool for those files; never trust an empty `grep` result on the SPA.
|
||||
- `[2026-07-06]` **`DesignSync` (claude.ai/design MCP) needs claude.ai design scopes before ANY method works** — first call errors `needs a claude.ai login ... Run /login, select "Claude account with subscription"`. It's an interactive auth only the operator can complete (`/design-login` or `/login`); can't be done on their behalf.
|
||||
|
||||
_18 older entries (2026-05-* — the original debug-TUI/web build era) archived to archival-memory.md._
|
||||
|
||||
+4
-4
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
|
||||
|
||||
[project]
|
||||
name = "ratatoskr"
|
||||
version = "0.18.6"
|
||||
version = "0.20.4"
|
||||
description = "Worldtree Conversation API debug TUI — multi-pane observability dashboard"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.12"
|
||||
@@ -60,9 +60,9 @@ Repository = "https://gitea.phasefinal.com/vh/ratatoskr"
|
||||
# Ratatoskr is built against Worldtree at this commit; the vendored
|
||||
# spec snapshot in docs/ reflects that SHA.
|
||||
[tool.ratatoskr.spec-pin]
|
||||
worldtree-spec-rev = "5810a26b38a5ea6630892f9a39756f57c5b7b41e"
|
||||
worldtree-version = "v1.0.0b2"
|
||||
pinned-on = "2026-06-30"
|
||||
worldtree-spec-rev = "c9e59ec"
|
||||
worldtree-version = "v1.0.0b22"
|
||||
pinned-on = "2026-07-06"
|
||||
|
||||
# Bifrost lives on the auth-gated gitea PyPI index (not public PyPI).
|
||||
# uv reads the credential from UV_INDEX_GITEA_USERNAME / _PASSWORD or ~/.netrc.
|
||||
|
||||
@@ -0,0 +1,64 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Regenerate src/ratatoskr/web/static/persona_render_canon.json from the vendored
|
||||
Worldtree d2 render canons (docs/vendor/worldtree-persona-canon/).
|
||||
|
||||
The web persona pane renders the CANONICAL affect->NL (mood word + relationship
|
||||
directive) BYTE-EXACT to what Worldtree injects into the agent's context. That render
|
||||
needs the relation canon parsed into per-band phrase maps; this script reparses the
|
||||
vendored raw canons into the flat form the browser JS consumes.
|
||||
|
||||
Uses Worldtree's OWN loader (core.persona.stance_render.load_canon) as the authoritative
|
||||
parser, so the flat form can never drift from Worldtree's parsing semantics. Requires
|
||||
Worldtree's venv (pydantic etc.).
|
||||
|
||||
Run when scripts/canonical_drift.py flags a canon bump:
|
||||
PYTHONPATH=~/development/Worldtree ~/development/Worldtree/.venv/bin/python \
|
||||
scripts/build_persona_canon.py
|
||||
"""
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
from core.persona.stance_render import load_canon # Worldtree (authoritative parser)
|
||||
|
||||
ROOT = Path(__file__).resolve().parent.parent
|
||||
VENDOR = ROOT / "docs" / "vendor" / "worldtree-persona-canon"
|
||||
OUT = ROOT / "src" / "ratatoskr" / "web" / "static" / "persona_render_canon.json"
|
||||
|
||||
canon = load_canon(str(VENDOR / "d2-render-canon-v1.json"))
|
||||
mood = json.loads((VENDOR / "d2-mood-render-canon-v1.json").read_text())
|
||||
out = {
|
||||
"_source": "vendored from Worldtree core/persona/canon/{d2-mood-render-canon-v1,d2-render-canon-v1}.json",
|
||||
"_generated_by": "scripts/build_persona_canon.py (regen on canonical_drift flag)",
|
||||
"_render_path": "deterministic, no LLM; mirrors Worldtree describe_pad + render_d2_canonical byte-exact",
|
||||
"mood_grid": mood["describe_pad"]["valence_arousal_grid"],
|
||||
# Context-injection reconstruction (affect-egress-consumer-reference §2b/2c): the
|
||||
# hidden mood DIRECTIVE. occ_directives = per-OCC-type behavioral string + tier;
|
||||
# pad_band_fallback = the P×A-quadrant default when no emotion is salient. The
|
||||
# salience gate (emotion_salience) + full_only tiers drive which one fires — but
|
||||
# affect.emit is type-only (no intensity), so the consumer shows BOTH candidates.
|
||||
"mood_directive": {
|
||||
"salience": mood["thresholds"]["emotion_salience"],
|
||||
"pad_band_cutoff": mood["thresholds"]["pad_band_cutoff"],
|
||||
"full_only": mood["emotion_tiers"]["full_only"],
|
||||
"occ_directives": {
|
||||
t: {"directive": e["directive"], "tier": e["tier"]}
|
||||
for t, e in mood["derive_directive"]["occ_directives"].items()
|
||||
},
|
||||
"pad_band_fallback": mood["pad_band_fallback"],
|
||||
},
|
||||
"relation": {
|
||||
"trust_cuts": [list(c) for c in canon.trust_cuts],
|
||||
"warmth_cuts": [list(c) for c in canon.warmth_cuts],
|
||||
"agency_cuts": [list(c) for c in canon.agency_cuts],
|
||||
"warmth_phrase": canon.warmth_phrase, "warmth_beh": canon.warmth_beh,
|
||||
"agency_phrase": canon.agency_phrase, "agency_beh": canon.agency_beh,
|
||||
"history": canon.history,
|
||||
"prefix": "Use this graded relationship state: toward target, warmth is ",
|
||||
"tbeh": {"low_trust": "verify important claims before relying on them",
|
||||
"cold_warmth": "protect boundaries while staying useful",
|
||||
"default": "work from ordinary good faith"},
|
||||
"cold_warmth_bands": ["distant", "cold", "hostile"], "high_conf_floor": 0.55,
|
||||
},
|
||||
}
|
||||
OUT.write_text(json.dumps(out, indent=1) + "\n")
|
||||
print(f"wrote {OUT.relative_to(ROOT)}")
|
||||
Executable
+61
@@ -0,0 +1,61 @@
|
||||
#!/usr/bin/env bash
|
||||
# reset-sindra-stores.sh — wipe ratatoskr's Bifrost provider stores (memory +
|
||||
# affect/persona for the single-tenant Tier-3 agent, sindra) and restart the
|
||||
# combined :8392 provider empty.
|
||||
#
|
||||
# Usage:
|
||||
# scripts/reset-sindra-stores.sh # wipe, keep ONE rolling backup (default)
|
||||
# scripts/reset-sindra-stores.sh --hard # wipe with NO backup (zero-trace)
|
||||
#
|
||||
# The rolling backup (db-reset-backup/, gitignored via *.db*) is overwritten
|
||||
# every run — it never accumulates; it's a one-level undo, nothing more.
|
||||
#
|
||||
# Why stop the provider first: the combined provider holds the SQLite files open
|
||||
# (WAL) and caches state in memory, so an out-of-band file move without a restart
|
||||
# would be shadowed. Stop -> move -> restart lets it recreate empty schema
|
||||
# (CREATE TABLE IF NOT EXISTS on open).
|
||||
|
||||
PORT=8392
|
||||
BACKUP_DIR="db-reset-backup"
|
||||
|
||||
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||
cd "$ROOT" || { echo "reset: cannot cd to repo root $ROOT" >&2; exit 1; }
|
||||
# shellcheck disable=SC1091
|
||||
source ./env.sh >/dev/null 2>&1 || { echo "reset: failed to source env.sh" >&2; exit 1; }
|
||||
|
||||
AFFECT_DB="${RATATOSKR_AFFECT_DB:-affect.db}"
|
||||
MEMORY_DB="${RATATOSKR_MEMORY_DB:-memory.db}"
|
||||
HARD=0; [ "${1:-}" = "--hard" ] && HARD=1
|
||||
|
||||
echo "== ratatoskr provider-store reset (memory + persona) =="
|
||||
echo " affect: $AFFECT_DB"
|
||||
echo " memory: $MEMORY_DB"
|
||||
|
||||
# 1. stop the combined provider holding the DBs
|
||||
PID="$(ss -ltnp 2>/dev/null | grep ":$PORT" | grep -oE 'pid=[0-9]+' | head -1 | cut -d= -f2)"
|
||||
if [ -n "${PID:-}" ]; then
|
||||
kill -9 "$PID" 2>/dev/null && echo "-- stopped provider :$PORT (pid $PID)"
|
||||
else
|
||||
echo "-- no provider on :$PORT (already down)"
|
||||
fi
|
||||
|
||||
# 2. wipe (optional rolling backup)
|
||||
files=("$AFFECT_DB" "$AFFECT_DB-wal" "$AFFECT_DB-shm" "$MEMORY_DB" "$MEMORY_DB-wal" "$MEMORY_DB-shm")
|
||||
if [ "$HARD" -eq 1 ]; then
|
||||
for f in "${files[@]}"; do [ -e "$f" ] && rm -f "$f" && echo "-- removed $f"; done
|
||||
echo "-- HARD wipe (no backup)"
|
||||
else
|
||||
rm -rf "$BACKUP_DIR"; mkdir -p "$BACKUP_DIR"
|
||||
for f in "${files[@]}"; do [ -e "$f" ] && mv "$f" "$BACKUP_DIR"/ && echo "-- $f -> $BACKUP_DIR/"; done
|
||||
echo "-- rolling backup: $BACKUP_DIR/ (overwritten each run)"
|
||||
fi
|
||||
|
||||
# 3. restart the combined provider (recreates empty schema on open)
|
||||
nohup "$ROOT/.venv/bin/ratatoskr-combined-provider" >/tmp/ratatoskr-combined.log 2>&1 & disown
|
||||
echo "-- restarted combined provider (pid $!)"
|
||||
|
||||
# 4. verify bound + empty
|
||||
curl -s -o /dev/null -w "-- :$PORT -> HTTP %{http_code}\n" --retry 25 --retry-connrefused --retry-delay 1 "http://127.0.0.1:$PORT/"
|
||||
echo "-- affect_snapshots (persona): $(sqlite3 "$AFFECT_DB" 'SELECT COUNT(*) FROM affect_snapshots' 2>&1)"
|
||||
echo "-- memory_chunks (memory): $(sqlite3 "$MEMORY_DB" 'SELECT COUNT(*) FROM memory_chunks' 2>&1)"
|
||||
echo "== done — sindra memory + persona reset =="
|
||||
+297
-12
@@ -7,23 +7,35 @@ from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import asyncio
|
||||
import hashlib
|
||||
import os
|
||||
import signal
|
||||
import sys
|
||||
from dataclasses import dataclass, field
|
||||
from importlib.metadata import PackageNotFoundError, version
|
||||
from typing import TextIO
|
||||
from typing import Any, TextIO
|
||||
|
||||
import httpx
|
||||
|
||||
from ratatoskr.first_message import seed_preset_first_message
|
||||
from ratatoskr.sessions import (
|
||||
AgentNotFound,
|
||||
AuthoredHistoryUnavailable,
|
||||
BifrostBinding,
|
||||
BifrostConsumerKeyMissing,
|
||||
BifrostHandshakeFailed,
|
||||
SessionApiFailed,
|
||||
create_character,
|
||||
create_session,
|
||||
delete_character,
|
||||
endpoint_for_plane,
|
||||
get_capabilities,
|
||||
get_character_state,
|
||||
get_me,
|
||||
get_session_messages,
|
||||
list_character_models,
|
||||
set_persona_state,
|
||||
write_authored_history,
|
||||
)
|
||||
from ratatoskr.sse_client import (
|
||||
AffectUpdate,
|
||||
@@ -97,6 +109,21 @@ class ParsedArgs:
|
||||
bifrost: BifrostBinding | None = None
|
||||
bifrost_plane: str | None = None
|
||||
consumer_key: str | None = None
|
||||
# Standalone boot-time orientation probe: GET /me + GET /capabilities, print,
|
||||
# exit. Mutually exclusive with the session/turn flags (opens no session).
|
||||
whoami: bool = False
|
||||
# Optional admin-tier key (RATATOSKR_ADMIN_API_KEY / --admin-key) for the
|
||||
# admin-scoped inspection reads (BifrostState pane, GET /admin/sessions/…).
|
||||
# None when unset — the BifrostState pane then shows "admin key not configured".
|
||||
admin_key: str | None = None
|
||||
# Tier-2 one-shot probes (like --whoami). --characters runs the transient-
|
||||
# character CRUD lifecycle; --set-persona-pad "p,a,d" (with --session) writes
|
||||
# a session's persona state (affect injection).
|
||||
characters: bool = False
|
||||
set_persona_pad: str | None = None
|
||||
# #347 authored-history-write reference-consumer probe: create a fresh
|
||||
# session bound to --agent, seed an authored assistant first-message (seq-0).
|
||||
seed_first_message: str | None = None
|
||||
|
||||
|
||||
class _ArgparseError(Exception):
|
||||
@@ -121,6 +148,11 @@ def _parse_args(argv: list[str] | None) -> ParsedArgs:
|
||||
parser.add_argument("--api-key", dest="api_key")
|
||||
parser.add_argument("--server")
|
||||
parser.add_argument("--raw", action="store_true")
|
||||
parser.add_argument("--whoami", action="store_true")
|
||||
parser.add_argument("--admin-key", dest="admin_key")
|
||||
parser.add_argument("--characters", action="store_true")
|
||||
parser.add_argument("--set-persona-pad", dest="set_persona_pad", default=None)
|
||||
parser.add_argument("--seed-first-message", dest="seed_first_message", default=None)
|
||||
# Issue #5: required for per-end-user agents (lofn etc.); optional otherwise (mimir).
|
||||
parser.add_argument("--end-user-id", dest="end_user_id", default=None)
|
||||
# Issue #17: bind the created session to our own Bifrost provider plane.
|
||||
@@ -141,17 +173,57 @@ def _parse_args(argv: list[str] | None) -> ParsedArgs:
|
||||
# Issue #5 INV-001: --end-user-id, if passed, MUST be non-empty (mirrors --send).
|
||||
if ns.end_user_id is not None and not ns.end_user_id:
|
||||
raise UsageError("--end-user-id must be non-empty when passed")
|
||||
if ns.session and ns.new:
|
||||
raise UsageError("--session and --new are mutually exclusive; pass exactly one")
|
||||
if not ns.session and not ns.new:
|
||||
raise UsageError("pass exactly one of --session or --new")
|
||||
if ns.session and ns.agent:
|
||||
raise UsageError("--agent is required with --new and forbidden with --session")
|
||||
if ns.new and not ns.agent and ns.send is not None:
|
||||
# Issue #8: --agent stays required for --send --new (non-interactive,
|
||||
# cannot prompt). Bare --new (TUI mode) accepts None — picker drives
|
||||
# the choice via list_agents in _resolve_then_run.
|
||||
raise UsageError("--agent is required when --new is passed in --send mode")
|
||||
if sum([ns.whoami, ns.characters, bool(ns.set_persona_pad), bool(ns.seed_first_message)]) > 1:
|
||||
raise UsageError(
|
||||
"--whoami / --characters / --set-persona-pad / --seed-first-message "
|
||||
"are mutually exclusive"
|
||||
)
|
||||
if ns.whoami or ns.characters:
|
||||
# Standalone one-shot probes: open no session.
|
||||
if ns.send is not None or ns.session or ns.new or ns.agent:
|
||||
raise UsageError(
|
||||
"--whoami / --characters are standalone probes "
|
||||
"(no --send/--session/--new/--agent)"
|
||||
)
|
||||
elif ns.set_persona_pad is not None:
|
||||
# Session-scoped write probe: needs a target session, nothing else.
|
||||
if not ns.set_persona_pad:
|
||||
raise UsageError("--set-persona-pad must be non-empty (e.g. '0.4,0.1,-0.2')")
|
||||
if not ns.session:
|
||||
raise UsageError("--set-persona-pad requires --session <id>")
|
||||
if ns.send is not None or ns.new or ns.agent:
|
||||
raise UsageError("--set-persona-pad takes only --session")
|
||||
elif ns.seed_first_message is not None:
|
||||
# #347 first-message probe: creates a fresh session bound to --agent,
|
||||
# then seeds an authored assistant turn as seq-0 — manages its own session.
|
||||
if not ns.seed_first_message:
|
||||
raise UsageError("--seed-first-message must be non-empty")
|
||||
if not ns.agent:
|
||||
raise UsageError("--seed-first-message requires --agent <id>")
|
||||
if ns.send is not None or ns.session or ns.new:
|
||||
raise UsageError(
|
||||
"--seed-first-message manages its own session (no --send/--session/--new)"
|
||||
)
|
||||
else:
|
||||
if ns.session and ns.new:
|
||||
raise UsageError("--session and --new are mutually exclusive")
|
||||
if not ns.session and not ns.new:
|
||||
# Bare TUI mode → startup session picker (design-brief §4). --send is
|
||||
# non-interactive (no picker can open), so it still requires one flag;
|
||||
# --agent belongs with --new (bare mode resumes, it doesn't create).
|
||||
if ns.send is not None:
|
||||
raise UsageError("--send requires --session or --new (no interactive picker)")
|
||||
if ns.agent:
|
||||
raise UsageError(
|
||||
"--agent belongs with --new; bare TUI mode opens the session picker"
|
||||
)
|
||||
if ns.session and ns.agent:
|
||||
raise UsageError("--agent is required with --new and forbidden with --session")
|
||||
if ns.new and not ns.agent and ns.send is not None:
|
||||
# Issue #8: --agent stays required for --send --new (non-interactive,
|
||||
# cannot prompt). Bare --new (TUI mode) accepts None — picker drives
|
||||
# the choice via list_agents in _resolve_then_run.
|
||||
raise UsageError("--agent is required when --new is passed in --send mode")
|
||||
|
||||
api_key = ns.api_key or os.environ.get("WORLDTREE_API_KEY") or ""
|
||||
if not api_key:
|
||||
@@ -187,6 +259,9 @@ def _parse_args(argv: list[str] | None) -> ParsedArgs:
|
||||
bifrost = BifrostBinding(endpoint_url=endpoint_for_plane(ns.bifrost_plane, host))
|
||||
bifrost_plane = ns.bifrost_plane
|
||||
consumer_key = os.environ.get("RATATOSKR_BIFROST_CONSUMER_KEY") or None
|
||||
# Admin-tier key for the admin-scoped inspection reads (BifrostState pane).
|
||||
# Flag > env > None; None leaves the admin panes showing "not configured".
|
||||
admin_key = ns.admin_key or os.environ.get("RATATOSKR_ADMIN_API_KEY") or None
|
||||
|
||||
return ParsedArgs(
|
||||
send_content=ns.send,
|
||||
@@ -200,6 +275,11 @@ def _parse_args(argv: list[str] | None) -> ParsedArgs:
|
||||
bifrost=bifrost,
|
||||
bifrost_plane=bifrost_plane,
|
||||
consumer_key=consumer_key,
|
||||
whoami=ns.whoami,
|
||||
admin_key=admin_key,
|
||||
characters=ns.characters,
|
||||
set_persona_pad=ns.set_persona_pad,
|
||||
seed_first_message=ns.seed_first_message,
|
||||
)
|
||||
|
||||
|
||||
@@ -519,6 +599,11 @@ async def _amain(args: ParsedArgs) -> int:
|
||||
sys.stderr.write(
|
||||
f". create_session: session_id={info.session_id} agent_id={info.agent_id}\n"
|
||||
)
|
||||
# #347 authored first-message: seed the agent's preset opening (best-effort).
|
||||
if await seed_preset_first_message(client, info.session_id, args.agent_id):
|
||||
sys.stderr.write(
|
||||
f". first_message: seeded preset opening for {info.agent_id}\n"
|
||||
)
|
||||
# Issue #17 bound-state indicator: plane + endpoint + status, so the
|
||||
# operator sees WHICH identity/endpoint bound (not a bare boolean).
|
||||
if args.bifrost is not None:
|
||||
@@ -550,6 +635,198 @@ async def _amain(args: ParsedArgs) -> int:
|
||||
loop.remove_signal_handler(signal.SIGINT)
|
||||
|
||||
|
||||
def _format_whoami(me: dict[str, Any], caps: dict[str, Any]) -> str:
|
||||
"""Render the --whoami report: identity (GET /me) + server capabilities."""
|
||||
lines = ["identity:"]
|
||||
lines.append(f" user_id: {me.get('user_id', '?')}")
|
||||
lines.append(f" tier: {me.get('tier', '?')}")
|
||||
lines.append(f" scopes: {', '.join(me.get('scopes', [])) or '(none)'}")
|
||||
for k in ("display_name", "key_id", "key_label"):
|
||||
if k in me:
|
||||
lines.append(f" {k}: {me[k]}")
|
||||
lines.append("capabilities:")
|
||||
templates = caps.get("ephemeral_templates", {})
|
||||
if templates:
|
||||
for name, spec in templates.items():
|
||||
models = ", ".join(spec.get("allowed_models", []))
|
||||
lines.append(
|
||||
f" ephemeral_template {name}: default={spec.get('default_model', '?')} "
|
||||
f"max_bytes={spec.get('system_prompt_max_bytes', '?')} models=[{models}]"
|
||||
)
|
||||
else:
|
||||
lines.append(" (no ephemeral templates advertised)")
|
||||
return "\n".join(lines) + "\n"
|
||||
|
||||
|
||||
async def _whoami(args: ParsedArgs) -> int:
|
||||
"""--whoami one-shot: GET /me + GET /capabilities, print a compact report, exit.
|
||||
|
||||
A boot-time orientation probe (mirrors --send's non-interactive shape):
|
||||
"who am I against this server, and what does it offer." Opens no session.
|
||||
Errors land on stderr with the same [session_api_failed] / [network_error]
|
||||
vocab + exit codes as the other modes.
|
||||
"""
|
||||
assert isinstance(args, ParsedArgs)
|
||||
async with httpx.AsyncClient(
|
||||
base_url=args.server_url,
|
||||
headers={"Authorization": f"Bearer {args.api_key}", "User-Agent": USER_AGENT},
|
||||
timeout=httpx.Timeout(connect=10.0, read=10.0, write=10.0, pool=10.0),
|
||||
) as client:
|
||||
try:
|
||||
me = await get_me(client)
|
||||
caps = await get_capabilities(client)
|
||||
except SessionApiFailed as exc:
|
||||
sys.stderr.write(f"[session_api_failed] status={exc.status} body={exc.body!r}\n")
|
||||
return 20
|
||||
except (httpx.ConnectError, httpx.ReadTimeout, httpx.TransportError) as exc:
|
||||
sys.stderr.write(f"[network_error] {type(exc).__name__}: {exc}\n")
|
||||
return 21
|
||||
sys.stdout.write(_format_whoami(me, caps))
|
||||
return 0
|
||||
|
||||
|
||||
def _probe_client(args: ParsedArgs) -> httpx.AsyncClient:
|
||||
"""AsyncClient for the one-shot probes (--whoami / --characters / --set-persona-pad)."""
|
||||
return httpx.AsyncClient(
|
||||
base_url=args.server_url,
|
||||
headers={"Authorization": f"Bearer {args.api_key}", "User-Agent": USER_AGENT},
|
||||
timeout=httpx.Timeout(connect=10.0, read=10.0, write=10.0, pool=10.0),
|
||||
)
|
||||
|
||||
|
||||
async def _characters_probe(args: ParsedArgs) -> int:
|
||||
"""--characters one-shot: exercise the transient-character CRUD lifecycle
|
||||
(models → create → get-state → delete), print a report, exit. A reference-
|
||||
consumer smoke of the #161 character surface (needs character.read/write)."""
|
||||
assert isinstance(args, ParsedArgs)
|
||||
async with _probe_client(args) as client:
|
||||
try:
|
||||
models = await list_character_models(client)
|
||||
names = ", ".join(m.get("name", "?") for m in models.get("items", []))
|
||||
sys.stdout.write(f"character models: {names or '(none)'}\n")
|
||||
created = await create_character(
|
||||
client,
|
||||
{
|
||||
"schema_version": "1",
|
||||
"name": "ratatoskr-probe",
|
||||
"ocean": {
|
||||
"openness": 0.5, "conscientiousness": 0.5, "extraversion": 0.0,
|
||||
"agreeableness": 0.5, "neuroticism": 0.5,
|
||||
},
|
||||
"description": "ratatoskr --characters lifecycle probe",
|
||||
"narrative": "A throwaway probe character.",
|
||||
"voice_profile_block": "plain",
|
||||
},
|
||||
)
|
||||
cid = created["character_id"]
|
||||
sys.stdout.write(f"created: {cid} (ttl {created.get('ttl_expires_at')})\n")
|
||||
state = await get_character_state(client, cid)
|
||||
sys.stdout.write(f"state: pad={state.get('pad')}\n")
|
||||
await delete_character(client, cid)
|
||||
sys.stdout.write(f"deleted: {cid}\n")
|
||||
except SessionApiFailed as exc:
|
||||
sys.stderr.write(f"[session_api_failed] status={exc.status} body={exc.body!r}\n")
|
||||
return 20
|
||||
except (httpx.ConnectError, httpx.ReadTimeout, httpx.TransportError) as exc:
|
||||
sys.stderr.write(f"[network_error] {type(exc).__name__}: {exc}\n")
|
||||
return 21
|
||||
return 0
|
||||
|
||||
|
||||
async def _set_persona_probe(args: ParsedArgs) -> int:
|
||||
"""--set-persona-pad one-shot: POST a PAD to /sessions/{id}/persona_state
|
||||
(affect injection), print the result, exit. Requires --session."""
|
||||
assert isinstance(args, ParsedArgs)
|
||||
assert args.session_id is not None and args.set_persona_pad is not None
|
||||
try:
|
||||
pad = [float(x) for x in args.set_persona_pad.split(",")]
|
||||
except ValueError:
|
||||
sys.stderr.write(
|
||||
"[usage_error] --set-persona-pad must be comma-separated floats "
|
||||
"(e.g. '0.4,0.1,-0.2')\n"
|
||||
)
|
||||
return 10
|
||||
if len(pad) != 3:
|
||||
sys.stderr.write(
|
||||
"[usage_error] --set-persona-pad needs exactly 3 floats "
|
||||
"(pleasure,arousal,dominance), e.g. '0.4,0.1,-0.2'\n"
|
||||
)
|
||||
return 10
|
||||
# Canonical POST /sessions/{id}/persona_state body (#317): a named-key dict,
|
||||
# NOT a bare list — {"pad": {"pleasure", "arousal", "dominance"}}.
|
||||
snapshot = {"pad": {"pleasure": pad[0], "arousal": pad[1], "dominance": pad[2]}}
|
||||
async with _probe_client(args) as client:
|
||||
try:
|
||||
await set_persona_state(client, args.session_id, snapshot)
|
||||
except SessionApiFailed as exc:
|
||||
sys.stderr.write(f"[session_api_failed] status={exc.status} body={exc.body!r}\n")
|
||||
return 20
|
||||
except (httpx.ConnectError, httpx.ReadTimeout, httpx.TransportError) as exc:
|
||||
sys.stderr.write(f"[network_error] {type(exc).__name__}: {exc}\n")
|
||||
return 21
|
||||
sys.stdout.write(
|
||||
f"persona_state set: session={args.session_id[-8:]} pad={pad} (204)\n"
|
||||
)
|
||||
return 0
|
||||
|
||||
|
||||
async def _seed_first_message_probe(args: ParsedArgs) -> int:
|
||||
"""--seed-first-message one-shot: create a fresh session bound to --agent,
|
||||
write an authored assistant first-message (#347 POST /sessions/{id}/history),
|
||||
read it back via GET /messages, print a report, exit. A reference-consumer
|
||||
smoke of the authored-history-write primitive.
|
||||
|
||||
Hide-existence: a 404 (feature-absent OR the key lacks `session.history.write`)
|
||||
is reported as a benign 'feature-absent' result (exit 0) — the probe NEVER
|
||||
capability-probes to distinguish the causes (server INV-347-1). The probe
|
||||
seeds but does not generate, so the assistant-first provider constraint is
|
||||
inert here.
|
||||
"""
|
||||
assert isinstance(args, ParsedArgs)
|
||||
assert args.agent_id is not None and args.seed_first_message is not None
|
||||
async with _probe_client(args) as client:
|
||||
try:
|
||||
session = await create_session(
|
||||
client, args.agent_id, end_user_id=args.end_user_id
|
||||
)
|
||||
sys.stdout.write(f"session: {session.session_id} (agent {session.agent_id})\n")
|
||||
key = "ratatoskr-first-message-" + hashlib.sha256(
|
||||
args.seed_first_message.encode("utf-8")
|
||||
).hexdigest()[:12]
|
||||
try:
|
||||
ack = await write_authored_history(
|
||||
client,
|
||||
session.session_id,
|
||||
content=args.seed_first_message,
|
||||
idempotency_key=key,
|
||||
)
|
||||
except AuthoredHistoryUnavailable:
|
||||
sys.stdout.write(
|
||||
"authored-history: feature-absent or ungranted (404 hide-existence) "
|
||||
"— a production consumer falls back to a model-generated greeting; "
|
||||
"no capability-probe attempted.\n"
|
||||
)
|
||||
return 0
|
||||
sys.stdout.write(
|
||||
f"seeded: seq={ack.get('seq')} phase={ack.get('phase')} "
|
||||
f"turn_id={ack.get('turn_id')} content_chars={ack.get('content_chars')}\n"
|
||||
)
|
||||
history = await get_session_messages(client, session.session_id)
|
||||
items = history.get("items", [])
|
||||
sys.stdout.write(f"read-back: {len(items)} message(s)\n")
|
||||
for m in items:
|
||||
sys.stdout.write(
|
||||
f" seq={m.get('seq')} role={m.get('role')} content={m.get('content')!r}\n"
|
||||
)
|
||||
except SessionApiFailed as exc:
|
||||
sys.stderr.write(f"[session_api_failed] status={exc.status} body={exc.body!r}\n")
|
||||
return 20
|
||||
except (httpx.ConnectError, httpx.ReadTimeout, httpx.TransportError) as exc:
|
||||
sys.stderr.write(f"[network_error] {type(exc).__name__}: {exc}\n")
|
||||
return 21
|
||||
return 0
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
"""Sync entry point. Maps UsageError/_AuthError to exit codes BEFORE the event loop."""
|
||||
assert argv is None or all(isinstance(a, str) for a in argv)
|
||||
@@ -565,6 +842,14 @@ def main(argv: list[str] | None = None) -> int:
|
||||
# argparse's --help / --version short-circuit via SystemExit(0). Pass the code
|
||||
# through verbatim — argparse already printed help to stdout.
|
||||
return int(exc.code) if exc.code is not None else 0
|
||||
if args.whoami:
|
||||
return asyncio.run(_whoami(args))
|
||||
if args.characters:
|
||||
return asyncio.run(_characters_probe(args))
|
||||
if args.set_persona_pad is not None:
|
||||
return asyncio.run(_set_persona_probe(args))
|
||||
if args.seed_first_message is not None:
|
||||
return asyncio.run(_seed_first_message_probe(args))
|
||||
if args.send_content is None:
|
||||
# TUI mode — lazy import preserves INV-001 (no textual in cli at module scope).
|
||||
from ratatoskr.tui import run_tui
|
||||
|
||||
@@ -0,0 +1,83 @@
|
||||
"""Per-agent authored first-message presets (Worldtree #347 consumer feature).
|
||||
|
||||
When a new session is created for an agent that has a preset opening, seed it as
|
||||
a #347 authored first-message (``POST /sessions/{id}/history``, author=assistant,
|
||||
seq-0) so the session opens in-character before the user speaks — the durable
|
||||
replacement for a system-prompt "startup" instruction.
|
||||
|
||||
Best-effort by design: an instance without the ``session.history.write`` grant
|
||||
returns the hide-existence 404, which is swallowed so session creation is never
|
||||
blocked (the session simply opens with no seeded greeting). See
|
||||
``docs/contracts/first_message.contract.md``.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import hashlib
|
||||
|
||||
import httpx
|
||||
|
||||
from ratatoskr.sessions import write_authored_history
|
||||
|
||||
# Cap the best-effort seed write. The CLI/TUI create paths reuse an httpx client
|
||||
# with NO read timeout (it streams SSE turns), so an accepted-but-never-answered
|
||||
# POST /history would otherwise block session creation forever — violating INV-001's
|
||||
# "never block". asyncio.wait_for bounds the seed regardless of the client's timeout.
|
||||
_SEED_TIMEOUT_S = 10.0
|
||||
|
||||
# agent_id -> the authored opening seeded onto new sessions for that agent.
|
||||
# Editing this dict is how an operator tunes an agent's first turn. Keep entries
|
||||
# under the server's authored_content_max_bytes (8192 bytes) budget.
|
||||
FIRST_MESSAGE_PRESETS: dict[str, str] = {
|
||||
"ratatoskr:sindra": (
|
||||
"Hey there. I'm Sindra—glad you found me. So, three things before we start:\n\n"
|
||||
"How intense should I be? 1 is slow and teasing, 10 is relentless.\n\n"
|
||||
"What mood am I in today? Sweetheart, Vixen, Queen, Siren, or Brat?\n\n"
|
||||
"And how willing am I to begin? Enthusiastic (I want you now), Hesitant "
|
||||
"(you'll need to coax me out), Resistant (playful pushback), or Unwilling "
|
||||
"(I don't want this at all, until you prove otherwise)."
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
def preset_for(agent_id: str) -> str | None:
|
||||
"""Return the authored first-message preset for ``agent_id``, or None if none."""
|
||||
assert agent_id and isinstance(agent_id, str)
|
||||
return FIRST_MESSAGE_PRESETS.get(agent_id)
|
||||
|
||||
|
||||
async def seed_preset_first_message(
|
||||
client: httpx.AsyncClient, session_id: str, agent_id: str
|
||||
) -> str | None:
|
||||
"""Best-effort: seed ``agent_id``'s preset opening as a #347 authored
|
||||
first-message on ``session_id``; return the seeded text, or None.
|
||||
|
||||
Best-effort (INV-001): a no-preset agent, a malformed call, a slow write
|
||||
(bounded by ``_SEED_TIMEOUT_S``), the hide-existence 404, or ANY other
|
||||
exception all resolve to None WITHOUT raising — this MUST NOT block or fail
|
||||
session creation. Only ``asyncio.CancelledError`` propagates (cancellation is
|
||||
not a seed failure). Inputs are soft-guarded (return None), never asserted, so
|
||||
a wiring bug can't crash the create path this is wired into. A no-preset agent
|
||||
issues zero HTTP (INV-002). The per-content idempotency key makes a repeat on
|
||||
the same session an idempotent 200 replay (INV-003).
|
||||
"""
|
||||
# Soft input guards — a bad arg degrades to "no first message", never raises.
|
||||
if not (isinstance(agent_id, str) and agent_id):
|
||||
return None
|
||||
content = FIRST_MESSAGE_PRESETS.get(agent_id)
|
||||
if content is None:
|
||||
return None
|
||||
if client is None or not (isinstance(session_id, str) and session_id):
|
||||
return None
|
||||
key = "ratatoskr-preset-" + hashlib.sha256(content.encode("utf-8")).hexdigest()[:12]
|
||||
try:
|
||||
await asyncio.wait_for(
|
||||
write_authored_history(
|
||||
client, session_id, content=content, idempotency_key=key
|
||||
),
|
||||
timeout=_SEED_TIMEOUT_S,
|
||||
)
|
||||
except asyncio.CancelledError:
|
||||
raise # cancellation is not a seed failure — never swallow it
|
||||
except Exception:
|
||||
return None # any other failure (404/409/422/timeout/unexpected) → no greeting
|
||||
return content
|
||||
@@ -177,6 +177,26 @@ class AuthScopeDenied(Exception):
|
||||
self.scope = scope
|
||||
|
||||
|
||||
class AuthoredHistoryUnavailable(Exception):
|
||||
"""Raised on HTTP 404 from POST /sessions/{id}/history (#347 authored-history-write).
|
||||
|
||||
Hide-existence (server INV-347-1): an ungranted caller, a non-owner, and an
|
||||
unknown session ALL receive a 404 byte-identical to a genuine
|
||||
`session_not_found` — the feature's existence is never revealed by status,
|
||||
body, or error_code. The consumer MUST treat this as feature-absent and fall
|
||||
back (a production consumer to a model-generated greeting), and MUST NOT
|
||||
capability-probe to distinguish the causes. Distinct from `SessionApiFailed`
|
||||
so callers branch feature-absent without inspecting a status code.
|
||||
"""
|
||||
|
||||
def __init__(self, *, session_id: str) -> None:
|
||||
super().__init__(
|
||||
f"authored-history write unavailable for session {session_id!r} "
|
||||
"(404 hide-existence: feature-absent / ungranted / session-absent)"
|
||||
)
|
||||
self.session_id = session_id
|
||||
|
||||
|
||||
async def list_sessions(
|
||||
client: httpx.AsyncClient,
|
||||
*,
|
||||
@@ -406,3 +426,229 @@ async def get_persona_state(
|
||||
if resp.status_code == 403 and error_code == "auth_scope_denied":
|
||||
raise AuthScopeDenied(scope="persona.read")
|
||||
raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
|
||||
|
||||
async def get_me(client: httpx.AsyncClient) -> dict[str, Any]:
|
||||
"""GET /me — the authenticated principal's identity + key metadata (spec §GET /me).
|
||||
|
||||
Boot-time whoami: verify the key without agent-config side effects. Returns
|
||||
the parsed dict verbatim (freeform per the frozen OpenAPI; the spec documents
|
||||
`{user_id, scopes, tier, display_name?, key_id?, key_label?, ...}`, optional
|
||||
fields omitted-not-null). 401 (bad/absent key when auth is enabled) — like
|
||||
every other non-200 — surfaces as SessionApiFailed (get_persona_state
|
||||
precedent). Read-only, rate-exempt, no audit emission.
|
||||
"""
|
||||
assert client is not None
|
||||
resp = await client.get("/me")
|
||||
if resp.status_code == 200:
|
||||
return resp.json()
|
||||
raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
|
||||
|
||||
async def list_character_models(client: httpx.AsyncClient) -> dict[str, Any]:
|
||||
"""GET /models/available-for-characters — character-capable model profiles (#161).
|
||||
|
||||
Requires `character.read`. Returns `{items: [{name, description, thinking}]}`.
|
||||
Parsed dict verbatim; any non-200 → SessionApiFailed.
|
||||
"""
|
||||
assert client is not None
|
||||
resp = await client.get("/models/available-for-characters")
|
||||
if resp.status_code == 200:
|
||||
return resp.json()
|
||||
raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
|
||||
|
||||
async def create_character(
|
||||
client: httpx.AsyncClient, character: dict[str, Any], *, state: dict[str, Any] | None = None
|
||||
) -> dict[str, Any]:
|
||||
"""POST /characters — create a transient character (#161). Requires `character.write`.
|
||||
|
||||
Body is `{character, state}` (state optional — a CharacterStateSchema for
|
||||
mid-conversation rehydration). Returns 201 `{character_id, ttl_expires_at}`;
|
||||
any non-201 → SessionApiFailed.
|
||||
"""
|
||||
assert client is not None
|
||||
assert isinstance(character, dict) and character
|
||||
resp = await client.post("/characters", json={"character": character, "state": state})
|
||||
if resp.status_code == 201:
|
||||
return resp.json()
|
||||
raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
|
||||
|
||||
async def get_character_state(client: httpx.AsyncClient, character_id: str) -> dict[str, Any]:
|
||||
"""GET /characters/{character_id}/state — live runtime state (#161). Requires `character.read`.
|
||||
|
||||
Returns `{schema_version, pad, emotions_active, mood_drift, goal_signal_history}`;
|
||||
refreshes the character's TTL. Any non-200 → SessionApiFailed.
|
||||
"""
|
||||
assert client is not None
|
||||
assert character_id and isinstance(character_id, str)
|
||||
resp = await client.get(f"/characters/{character_id}/state")
|
||||
if resp.status_code == 200:
|
||||
return resp.json()
|
||||
raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
|
||||
|
||||
async def delete_character(client: httpx.AsyncClient, character_id: str) -> None:
|
||||
"""DELETE /characters/{character_id} — remove a transient character (#161).
|
||||
|
||||
Requires `character.write`. Bound sessions detach (next turn → 410
|
||||
character_not_found). 200/204 → None; any other status → SessionApiFailed.
|
||||
"""
|
||||
assert client is not None
|
||||
assert character_id and isinstance(character_id, str)
|
||||
resp = await client.delete(f"/characters/{character_id}")
|
||||
if resp.status_code in (200, 204):
|
||||
return None
|
||||
raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
|
||||
|
||||
async def set_persona_state(
|
||||
client: httpx.AsyncClient, session_id: str, snapshot: dict[str, Any]
|
||||
) -> None:
|
||||
"""POST /sessions/{session_id}/persona_state — set a session's persona state (affect injection).
|
||||
|
||||
The request body is FREEFORM on the wire (the OpenAPI declares no request
|
||||
schema), but worldtree-dev's prose now pins the canonical shape (#317):
|
||||
`{"pad": {"pleasure": p, "arousal": a, "dominance": d}}` — a named-key dict
|
||||
(each in [-1, 1]), NOT a bare list; PAD-only, session-scoped, pull-over-push
|
||||
(#289). The caller supplies the snapshot. 204 No Content → None; any other
|
||||
status → SessionApiFailed.
|
||||
"""
|
||||
assert client is not None
|
||||
assert session_id and isinstance(session_id, str)
|
||||
assert isinstance(snapshot, dict)
|
||||
resp = await client.post(f"/sessions/{session_id}/persona_state", json=snapshot)
|
||||
if resp.status_code == 204:
|
||||
return None
|
||||
raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
|
||||
|
||||
async def get_session_bifrost(
|
||||
client: httpx.AsyncClient, session_id: str, *, admin_key: str
|
||||
) -> dict[str, Any]:
|
||||
"""GET /admin/sessions/{session_id}/bifrost — admin-scoped Bifrost dispatch state (#176).
|
||||
|
||||
Returns the live Bifrost binding for a session: `{endpoint_url, consumer_id,
|
||||
connected, capabilities_granted, tools: [{name, description}]}`. Requires the
|
||||
`admin.sessions.read` scope (admin tier), so the request OVERRIDES the
|
||||
Authorization header with `admin_key` (distinct from the client's default
|
||||
consumer key). Read-only (audited server-side). Parsed dict verbatim; any
|
||||
non-200 → SessionApiFailed — notably 403 `auth_scope_denied` (key lacks the
|
||||
scope) and 404 `session_not_bifrost_bound` (session exists, no live client).
|
||||
"""
|
||||
assert client is not None
|
||||
assert session_id and isinstance(session_id, str)
|
||||
assert admin_key and isinstance(admin_key, str)
|
||||
resp = await client.get(
|
||||
f"/admin/sessions/{session_id}/bifrost",
|
||||
headers={"Authorization": f"Bearer {admin_key}"},
|
||||
)
|
||||
if resp.status_code == 200:
|
||||
return resp.json()
|
||||
raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
|
||||
|
||||
async def get_session_tools(client: httpx.AsyncClient, session_id: str) -> dict[str, Any]:
|
||||
"""GET /sessions/{session_id}/tools — owner-scoped tool inventory (spec #183).
|
||||
|
||||
Returns the merged tool list the LLM saw at turn-fire: `{agent_id,
|
||||
builtin_tools: [...], bifrost_tools: [{name, description, parameters}, ...]}`.
|
||||
Owner-scoped (`ctx.user_id == session.user_id`) — reachable with the consumer
|
||||
key, NO admin scope. Cross-owner access returns 404 `session_not_found`
|
||||
(existence-hiding); a revoked session returns 401 `auth_revoked`. Parsed dict
|
||||
verbatim; any non-200 → SessionApiFailed (mirrors get_persona_state).
|
||||
"""
|
||||
assert client is not None
|
||||
assert session_id and isinstance(session_id, str)
|
||||
resp = await client.get(f"/sessions/{session_id}/tools")
|
||||
if resp.status_code == 200:
|
||||
return resp.json()
|
||||
raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
|
||||
|
||||
async def get_capabilities(client: httpx.AsyncClient) -> dict[str, Any]:
|
||||
"""GET /capabilities — server capability discovery (spec §Ephemeral Templates).
|
||||
|
||||
Returns `{ephemeral_templates: {echo: {allowed_models, default_model,
|
||||
system_prompt_max_bytes}}}` — what the server offers before a client decides
|
||||
to instantiate. Any authenticated caller may read it (no scope). Parsed dict
|
||||
verbatim; any non-200 → SessionApiFailed.
|
||||
"""
|
||||
assert client is not None
|
||||
resp = await client.get("/capabilities")
|
||||
if resp.status_code == 200:
|
||||
return resp.json()
|
||||
raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
|
||||
|
||||
async def write_authored_history(
|
||||
client: httpx.AsyncClient,
|
||||
session_id: str,
|
||||
*,
|
||||
content: str,
|
||||
idempotency_key: str,
|
||||
author: str = "assistant",
|
||||
effects: str | None = None,
|
||||
claimed_original_at: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""POST /sessions/{session_id}/history — the #347 authored-history-write primitive.
|
||||
|
||||
Write one model-visible turn into the session's ledger AS the bound agent,
|
||||
WITHOUT a generation and WITHOUT lived-turn side effects (the SillyTavern
|
||||
"first message"). v1: `author="assistant"`, `effects` omitted (== "none"),
|
||||
`idempotency_key` REQUIRED (per-session dedup). The server pins the body
|
||||
(`AuthoredWriteRequest`, `extra="forbid"`), so `effects` /
|
||||
`claimed_original_at` are sent only when non-None — never as null keys.
|
||||
|
||||
Success is 201 (fresh) or 200 (idempotent replay, byte-identical body); both
|
||||
return the `AuthoredTurnResponse` dict verbatim (`{author, content_chars,
|
||||
injected_at, phase, seq, session_id, turn_id}` — provenance is audit-only,
|
||||
never on this body).
|
||||
|
||||
404 → `AuthoredHistoryUnavailable` (hide-existence: feature-absent /
|
||||
ungranted / session-absent are indistinguishable by design; the caller falls
|
||||
back and NEVER capability-probes — server INV-347-1). Any other non-2xx →
|
||||
`SessionApiFailed` (notably 409 `generation_active`, 422 `content_too_long` /
|
||||
`validation_failed`).
|
||||
"""
|
||||
assert client is not None
|
||||
assert session_id and isinstance(session_id, str)
|
||||
assert content and isinstance(content, str)
|
||||
assert idempotency_key and isinstance(idempotency_key, str)
|
||||
assert author and isinstance(author, str)
|
||||
body: dict[str, Any] = {
|
||||
"author": author,
|
||||
"content": content,
|
||||
"idempotency_key": idempotency_key,
|
||||
}
|
||||
if effects is not None:
|
||||
body["effects"] = effects
|
||||
if claimed_original_at is not None:
|
||||
body["claimed_original_at"] = claimed_original_at
|
||||
resp = await client.post(f"/sessions/{session_id}/history", json=body)
|
||||
if resp.status_code in (200, 201):
|
||||
return resp.json()
|
||||
if resp.status_code == 404:
|
||||
raise AuthoredHistoryUnavailable(session_id=session_id)
|
||||
raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
|
||||
|
||||
async def get_session_messages(
|
||||
client: httpx.AsyncClient, session_id: str
|
||||
) -> dict[str, Any]:
|
||||
"""GET /sessions/{session_id}/messages — the session's message history.
|
||||
|
||||
Un-deferred as the #347 seed read-back: a seeded turn renders as a normal
|
||||
`role=assistant` message (model-invisible provenance — indistinguishable
|
||||
from a lived turn on read). Returns `{session_id, items: [{seq, role,
|
||||
content, ...}], next_cursor}` verbatim; owner-scoped; any non-200 →
|
||||
`SessionApiFailed`. v1 reads the server default page (no pagination params —
|
||||
add limit/cursor when a caller needs scrollback).
|
||||
"""
|
||||
assert client is not None
|
||||
assert session_id and isinstance(session_id, str)
|
||||
resp = await client.get(f"/sessions/{session_id}/messages")
|
||||
if resp.status_code == 200:
|
||||
return resp.json()
|
||||
raise SessionApiFailed(status=resp.status_code, body=resp.content)
|
||||
|
||||
@@ -175,6 +175,23 @@ Event = (
|
||||
)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class AdminEvent:
|
||||
"""One `/admin/events` envelope (INV-046) — an admin-tier lifecycle event.
|
||||
|
||||
Distinct from the turn-stream `Event` union: this is the process-wide admin
|
||||
broadcast stream, not a per-turn stream. `id` is a plain monotonic int
|
||||
(resets on restart; heartbeats have id=0). `type` is a dotted namespace
|
||||
(session.* / turn.* / key.* / system.*). `data` is a type-specific dict —
|
||||
most carry `session_id`; per INV-049 it holds IDs + small metadata only.
|
||||
"""
|
||||
|
||||
id: int
|
||||
type: str
|
||||
timestamp: str | None
|
||||
data: dict[str, Any]
|
||||
|
||||
|
||||
class MalformedSseId(Exception):
|
||||
"""Raised when an SSE event's `id:` wire field is missing or non-composite."""
|
||||
|
||||
@@ -598,6 +615,51 @@ async def stream_turn_resilient(
|
||||
)
|
||||
|
||||
|
||||
async def stream_admin_events(
|
||||
client: httpx.AsyncClient,
|
||||
*,
|
||||
admin_key: str,
|
||||
last_event_id: int | None = None,
|
||||
) -> AsyncIterator[AdminEvent]:
|
||||
"""GET /admin/events SSE — the admin-tier lifecycle broadcast stream (INV-046).
|
||||
|
||||
Yields `AdminEvent` envelopes as they arrive. Admin-scoped (admin.events.read):
|
||||
the request OVERRIDES Authorization with `admin_key` (distinct from the
|
||||
client's default consumer bearer). `last_event_id` sets the `Last-Event-ID`
|
||||
header for resume (plain decimal int). Long-lived — iterate until the caller
|
||||
stops or the connection ends. Non-200 → SseConnectFailed; a mid-stream drop
|
||||
→ SseConnectionDropped (caller may reconnect from the last-seen `AdminEvent.id`).
|
||||
Malformed frames are skipped (best-effort stream).
|
||||
"""
|
||||
assert client is not None
|
||||
assert admin_key and isinstance(admin_key, str)
|
||||
headers = {"Authorization": f"Bearer {admin_key}"}
|
||||
if last_event_id is not None:
|
||||
headers["Last-Event-ID"] = str(last_event_id)
|
||||
async with httpx_sse.aconnect_sse(
|
||||
client, "GET", "/admin/events", headers=headers
|
||||
) as event_source:
|
||||
if event_source.response.status_code != 200:
|
||||
body = await event_source.response.aread()
|
||||
raise SseConnectFailed(status=event_source.response.status_code, body=body)
|
||||
try:
|
||||
async for sse in event_source.aiter_sse():
|
||||
if sse.data == "":
|
||||
continue
|
||||
try:
|
||||
env = json.loads(sse.data)
|
||||
except json.JSONDecodeError:
|
||||
continue # skip a malformed admin frame (best-effort)
|
||||
yield AdminEvent(
|
||||
id=env.get("id", 0),
|
||||
type=env["type"],
|
||||
timestamp=env.get("timestamp"),
|
||||
data=env.get("data", {}),
|
||||
)
|
||||
except (httpx.ReadError, httpx.RemoteProtocolError, httpx.ReadTimeout) as exc:
|
||||
raise SseConnectionDropped(last_seen_sse_id=None) from exc
|
||||
|
||||
|
||||
def _parse_sse_id(raw: str) -> SseId:
|
||||
"""Parse the SSE wire `id:` as composite `{turn_id}:{seq}`. See contract FN _parse_sse_id."""
|
||||
assert isinstance(raw, str)
|
||||
|
||||
+359
-8
@@ -33,6 +33,7 @@ from textual.widgets import (
|
||||
)
|
||||
|
||||
from ratatoskr.cli import USER_AGENT, ParsedArgs, _format_duration_ms, _format_usage
|
||||
from ratatoskr.first_message import seed_preset_first_message
|
||||
from ratatoskr.sessions import (
|
||||
AgentInfo,
|
||||
AgentNotAvailable,
|
||||
@@ -42,11 +43,16 @@ from ratatoskr.sessions import (
|
||||
BifrostHandshakeFailed,
|
||||
PersonaNotConfigured,
|
||||
SessionApiFailed,
|
||||
SessionInfo,
|
||||
create_session,
|
||||
get_persona_state,
|
||||
get_session_bifrost,
|
||||
get_session_tools,
|
||||
list_agents,
|
||||
list_sessions,
|
||||
)
|
||||
from ratatoskr.sse_client import (
|
||||
AdminEvent,
|
||||
AffectUpdate,
|
||||
AwaitingLlmFirstToken,
|
||||
CancelAlreadyCompleted,
|
||||
@@ -68,6 +74,7 @@ from ratatoskr.sse_client import (
|
||||
TurnIdFlip,
|
||||
WorkerPhase,
|
||||
cancel_turn,
|
||||
stream_admin_events,
|
||||
stream_turn_resilient,
|
||||
)
|
||||
|
||||
@@ -194,6 +201,46 @@ def _ts() -> str:
|
||||
return now.strftime("%H:%M:%S") + f".{now.microsecond // 1000:03d}"
|
||||
|
||||
|
||||
def _format_admin_event(ev: AdminEvent) -> str:
|
||||
"""One-line render of an /admin/events envelope for the AdminEvents pane.
|
||||
|
||||
Drops `session_id` from the detail (the pane is already session-scoped) and
|
||||
shows HH:MM:SS from the ISO timestamp + the remaining small metadata fields.
|
||||
"""
|
||||
ts = (ev.timestamp or "")[11:19]
|
||||
extras = " ".join(f"{k}={v}" for k, v in ev.data.items() if k != "session_id")
|
||||
return f"[{ts}] {ev.type} {extras}".rstrip()
|
||||
|
||||
|
||||
def _format_bifrost_state(state: dict) -> list[str]:
|
||||
"""Render GET /admin/sessions/{id}/bifrost (#176) into BifrostState-pane lines."""
|
||||
tools = [t.get("name", "?") for t in state.get("tools", [])]
|
||||
caps = state.get("capabilities_granted", [])
|
||||
return [
|
||||
f"bifrost binding: connected={state.get('connected')} "
|
||||
f"consumer={state.get('consumer_id', '?')}",
|
||||
f" endpoint: {state.get('endpoint_url', '?')}",
|
||||
f" caps_granted: {', '.join(caps) or '(none)'}",
|
||||
f" tools ({len(tools)}): {', '.join(tools) or '(none)'}",
|
||||
]
|
||||
|
||||
|
||||
def _format_tool_inventory(tools: dict) -> list[str]:
|
||||
"""Render GET /sessions/{id}/tools (#183) into Tools-pane inventory lines.
|
||||
|
||||
The merged tool list the LLM saw at turn-fire — distinct from the live
|
||||
tool_start/tool_result events that stream into the same pane during a turn.
|
||||
"""
|
||||
builtin = [t.get("name", "?") for t in tools.get("builtin_tools", [])]
|
||||
bifrost = [t.get("name", "?") for t in tools.get("bifrost_tools", [])]
|
||||
return [
|
||||
f"session tool inventory: agent={tools.get('agent_id', '?')} "
|
||||
f"builtin={len(builtin)} bifrost={len(bifrost)}",
|
||||
f" builtin: {', '.join(builtin) or '(none)'}",
|
||||
f" bifrost: {', '.join(bifrost) or '(none)'}",
|
||||
]
|
||||
|
||||
|
||||
def _format_persona_header(snapshot: dict) -> str:
|
||||
"""One-line persona summary for the sticky header widget.
|
||||
|
||||
@@ -368,7 +415,7 @@ class TuiPresenterState:
|
||||
self,
|
||||
event: Event,
|
||||
*,
|
||||
transcript: "VerticalScroll",
|
||||
transcript: VerticalScroll,
|
||||
tools_log: RichLog,
|
||||
debug_log: RichLog,
|
||||
thinking_log: RichLog,
|
||||
@@ -798,6 +845,128 @@ class AgentPickerApp(App[str | None]):
|
||||
self.exit(None)
|
||||
|
||||
|
||||
def _session_desc(s: SessionInfo) -> str:
|
||||
"""One-line session summary for the picker's second row."""
|
||||
tail = f"session {s.session_id} · last active {s.last_active}"
|
||||
if s.message_count is not None:
|
||||
tail += f" · {s.message_count} msgs"
|
||||
return tail
|
||||
|
||||
|
||||
class SessionPickerApp(App[str | None]):
|
||||
"""Startup session picker (design-brief §4, slice b2). Opens before
|
||||
RatatoskrApp when bare TUI mode resolves >1 session. `run_async()` returns
|
||||
the chosen session_id (str) or None on Esc/Ctrl-D/Ctrl-C dismissal.
|
||||
|
||||
Resume-only (design-brief §4 negative clause "no in-app session creation —
|
||||
--new flag only"): the picker chooses among EXISTING sessions; starting a
|
||||
fresh one is the --new flag's job. Architecturally separate from
|
||||
RatatoskrApp (mirrors AgentPickerApp): list_sessions failures + dismissal
|
||||
land before any alt-screen opens (preserves #6 INV-001).
|
||||
"""
|
||||
|
||||
DEFAULT_CSS = """
|
||||
Header, HeaderIcon, HeaderTitle, HeaderClock {
|
||||
background: $surface;
|
||||
color: $au-bright-blue;
|
||||
}
|
||||
Footer {
|
||||
background: $surface;
|
||||
}
|
||||
ListView {
|
||||
scrollbar-background: $background;
|
||||
scrollbar-background-hover: $background;
|
||||
scrollbar-background-active: $background;
|
||||
scrollbar-color: $au-dark-50;
|
||||
scrollbar-color-hover: $au-dark-60;
|
||||
scrollbar-color-active: $au-bright-cyan;
|
||||
}
|
||||
#picker-prompt {
|
||||
dock: top;
|
||||
height: 1;
|
||||
padding: 0 1;
|
||||
color: $au-bright-cyan;
|
||||
background: $surface;
|
||||
}
|
||||
#session-list {
|
||||
height: 1fr;
|
||||
background: $background;
|
||||
}
|
||||
#session-list > ListItem {
|
||||
height: auto;
|
||||
padding: 1 1;
|
||||
background: $background;
|
||||
}
|
||||
#session-list:focus ListItem.-highlight {
|
||||
background: $primary;
|
||||
}
|
||||
#session-list:focus ListItem.-highlight .session-id-line {
|
||||
color: $au-bright-white;
|
||||
text-style: bold;
|
||||
}
|
||||
#session-list:focus ListItem.-highlight .session-desc {
|
||||
color: $au-bright-80;
|
||||
}
|
||||
.session-id-line {
|
||||
color: $au-bright-blue;
|
||||
text-style: bold;
|
||||
}
|
||||
.session-desc {
|
||||
color: $au-bright-70;
|
||||
}
|
||||
"""
|
||||
|
||||
BINDINGS: ClassVar[list[Binding]] = [
|
||||
Binding("enter", "pick", "Resume", priority=True),
|
||||
Binding("escape", "dismiss", "Cancel", priority=True),
|
||||
Binding("ctrl+d", "dismiss", "Cancel", priority=True),
|
||||
Binding("ctrl+c", "dismiss", "Cancel", priority=True),
|
||||
]
|
||||
|
||||
def __init__(self, sessions: list[SessionInfo]) -> None:
|
||||
super().__init__()
|
||||
# PRE-001: caller (_resolve_then_run) resolves the 0-session and
|
||||
# 1-session cases BEFORE constructing the picker.
|
||||
assert sessions
|
||||
self.sessions = sessions
|
||||
self.register_theme(AUSTRALIS_THEME)
|
||||
self.theme = "australis"
|
||||
|
||||
def compose(self) -> ComposeResult:
|
||||
yield Header()
|
||||
yield Static(
|
||||
"Pick a session to resume (relaunch with --new for a fresh one):",
|
||||
id="picker-prompt",
|
||||
)
|
||||
yield ListView(
|
||||
*[
|
||||
ListItem(
|
||||
Static(
|
||||
f"{s.name or s.session_id} · {s.agent_id}",
|
||||
classes="session-id-line",
|
||||
),
|
||||
Static(_session_desc(s), classes="session-desc"),
|
||||
)
|
||||
for s in self.sessions
|
||||
],
|
||||
id="session-list",
|
||||
)
|
||||
yield Footer()
|
||||
|
||||
async def on_mount(self) -> None:
|
||||
self.query_one("#session-list", ListView).focus()
|
||||
|
||||
def action_pick(self) -> None:
|
||||
lv = self.query_one("#session-list", ListView)
|
||||
idx = lv.index
|
||||
if idx is None:
|
||||
return # nothing highlighted; ignore
|
||||
self.exit(self.sessions[idx].session_id)
|
||||
|
||||
def action_dismiss(self) -> None:
|
||||
self.exit(None)
|
||||
|
||||
|
||||
class RatatoskrApp(App[int]):
|
||||
"""Textual TUI shell — single chat pane."""
|
||||
|
||||
@@ -898,7 +1067,7 @@ class RatatoskrApp(App[int]):
|
||||
/* v0.8.1: #current-text Static removed. Streaming text now coalesces
|
||||
on `\n` and writes directly to #transcript (same pattern as v0.7.1
|
||||
thinking fix). Eliminates the dock-bottom-growth-overlap bug. */
|
||||
#tools-log, #debug-log, #thinking-log {
|
||||
#tools-log, #debug-log, #thinking-log, #bifrost-log, #admin-events-log {
|
||||
background: $background;
|
||||
padding: 0 1;
|
||||
}
|
||||
@@ -1063,6 +1232,24 @@ class RatatoskrApp(App[int]):
|
||||
id="persona-log", wrap=True, markup=False,
|
||||
highlight=False, min_width=0,
|
||||
)
|
||||
with TabPane("Bifrost", id="bifrost-tab"):
|
||||
# #176: admin-scoped Bifrost dispatch state (endpoint,
|
||||
# connected, granted caps, tools) via
|
||||
# GET /admin/sessions/{id}/bifrost. Hydrated on mount
|
||||
# with the admin key; "not configured" when absent.
|
||||
yield RichLog(
|
||||
id="bifrost-log", wrap=True, markup=False,
|
||||
highlight=False, min_width=0,
|
||||
)
|
||||
with TabPane("AdminEvents", id="admin-events-tab"):
|
||||
# #11: live GET /admin/events SSE stream, admin-scoped,
|
||||
# FILTERED to the active session (design-brief §6). A
|
||||
# long-lived worker appends matching lifecycle events;
|
||||
# "not configured" when no admin key is set.
|
||||
yield RichLog(
|
||||
id="admin-events-log", wrap=True, markup=False,
|
||||
highlight=False, min_width=0,
|
||||
)
|
||||
# INV-002 + INV-003: visible identity + hint widgets (Footer-area).
|
||||
# pane-name widget displays current side-pane name.
|
||||
yield Static("", id="identity")
|
||||
@@ -1116,6 +1303,17 @@ class RatatoskrApp(App[int]):
|
||||
# surface (PersonaNotConfigured) get a placeholder + empty header.
|
||||
if self.agent_id is not None:
|
||||
self.run_worker(self._hydrate_persona())
|
||||
# #183: hydrate the Tools pane with the session's tool inventory via
|
||||
# GET /sessions/{id}/tools (owner-scoped — consumer key, no admin scope).
|
||||
# Unconditional: every session has a tool inventory to introspect.
|
||||
self.run_worker(self._hydrate_session_tools())
|
||||
# #176: hydrate the BifrostState pane via GET /admin/sessions/{id}/bifrost
|
||||
# (admin-scoped). Self-labels "not configured" when no admin key is set,
|
||||
# "not bound" for the common unbound-session 404 — always writes at mount.
|
||||
self.run_worker(self._hydrate_bifrost_state())
|
||||
# #11: long-lived worker streaming GET /admin/events into the AdminEvents
|
||||
# pane, filtered to this session. Admin-key-gated; cancelled on app exit.
|
||||
self.run_worker(self._stream_admin_events())
|
||||
|
||||
async def _hydrate_persona(self) -> None:
|
||||
"""Hydrate persona-header + Persona pane via GET /agents/{id}/persona_state.
|
||||
@@ -1127,7 +1325,6 @@ class RatatoskrApp(App[int]):
|
||||
On 200: header populated, pane shows full detail, audit logged.
|
||||
"""
|
||||
assert self.client is not None and self.agent_id is not None
|
||||
from rich.text import Text as RichText
|
||||
try:
|
||||
snapshot = await get_persona_state(self.client, self.agent_id)
|
||||
self._update_persona_surfaces(snapshot)
|
||||
@@ -1151,6 +1348,128 @@ class RatatoskrApp(App[int]):
|
||||
f"err={type(exc).__name__}: {exc!s:.120}"
|
||||
)
|
||||
|
||||
async def _hydrate_session_tools(self) -> None:
|
||||
"""Hydrate the Tools pane inventory via GET /sessions/{id}/tools (#183).
|
||||
|
||||
Best-effort observability (mirrors _hydrate_persona): on 200, writes the
|
||||
merged tool inventory (builtin + bifrost) the LLM saw at turn-fire into
|
||||
the Tools pane + audits; on any failure, audits and moves on — never
|
||||
crashes the TUI. Owner-scoped, so reachable with the consumer key.
|
||||
"""
|
||||
assert self.client is not None and self.session_id is not None
|
||||
from rich.text import Text as RichText
|
||||
|
||||
try:
|
||||
tools = await get_session_tools(self.client, self.session_id)
|
||||
except Exception as exc: # best-effort — never crash the TUI on hydrate
|
||||
self._audit(
|
||||
f"session_tools_hydration_failed session={self.session_id[-8:]} "
|
||||
f"err={type(exc).__name__}: {exc!s:.120}"
|
||||
)
|
||||
return
|
||||
log = self.query_one("#tools-log", RichLog)
|
||||
for line in _format_tool_inventory(tools):
|
||||
log.write(RichText(line))
|
||||
self._audit(
|
||||
f"session_tools_hydrated session={self.session_id[-8:]} "
|
||||
f"builtin={len(tools.get('builtin_tools', []))} "
|
||||
f"bifrost={len(tools.get('bifrost_tools', []))}"
|
||||
)
|
||||
|
||||
async def _hydrate_bifrost_state(self) -> None:
|
||||
"""Hydrate the BifrostState pane via GET /admin/sessions/{id}/bifrost (#176).
|
||||
|
||||
Admin-scoped (admin.sessions.read) — uses `self.args.admin_key`. Best-effort
|
||||
(mirrors _hydrate_session_tools): on 200 writes the live binding (endpoint,
|
||||
connected, granted caps, tools) + audits; on failure a labeled line + audit,
|
||||
never crashes. No admin key → "not configured". 404 session_not_bifrost_bound
|
||||
is the routine unbound-session case; 403 means the key lacks the scope.
|
||||
"""
|
||||
assert self.client is not None and self.session_id is not None
|
||||
from rich.text import Text as RichText
|
||||
|
||||
log = self.query_one("#bifrost-log", RichLog)
|
||||
admin_key = getattr(self.args, "admin_key", None)
|
||||
if not admin_key:
|
||||
log.write(
|
||||
RichText("(admin key not configured — set RATATOSKR_ADMIN_API_KEY)")
|
||||
)
|
||||
self._audit(
|
||||
f"bifrost_state_skipped session={self.session_id[-8:]} reason=no_admin_key"
|
||||
)
|
||||
return
|
||||
try:
|
||||
state = await get_session_bifrost(
|
||||
self.client, self.session_id, admin_key=admin_key
|
||||
)
|
||||
except SessionApiFailed as exc:
|
||||
label = (
|
||||
"(session not bound to Bifrost)"
|
||||
if exc.status == 404
|
||||
else f"(bifrost state unavailable: HTTP {exc.status})"
|
||||
)
|
||||
log.write(RichText(label))
|
||||
self._audit(
|
||||
f"bifrost_state_unavailable session={self.session_id[-8:]} status={exc.status}"
|
||||
)
|
||||
return
|
||||
except Exception as exc: # best-effort — never crash the TUI on hydrate
|
||||
log.write(RichText(f"(bifrost state hydration failed: {type(exc).__name__})"))
|
||||
self._audit(
|
||||
f"bifrost_state_hydration_failed session={self.session_id[-8:]} "
|
||||
f"err={type(exc).__name__}: {exc!s:.120}"
|
||||
)
|
||||
return
|
||||
for line in _format_bifrost_state(state):
|
||||
log.write(RichText(line))
|
||||
self._audit(
|
||||
f"bifrost_state_hydrated session={self.session_id[-8:]} "
|
||||
f"connected={state.get('connected')} tools={len(state.get('tools', []))}"
|
||||
)
|
||||
|
||||
def _admin_event_matches(self, ev: AdminEvent) -> bool:
|
||||
"""AdminEvents filter (design-brief §6): active-session events + non-heartbeat
|
||||
system.* (stream-integrity signals). Heartbeats are keepalive noise."""
|
||||
if ev.type == "system.heartbeat":
|
||||
return False
|
||||
if ev.type.startswith("system."):
|
||||
return True
|
||||
return ev.data.get("session_id") == self.session_id
|
||||
|
||||
async def _stream_admin_events(self) -> None:
|
||||
"""Stream GET /admin/events (admin-scoped) into the AdminEvents pane (#11).
|
||||
|
||||
Long-lived + best-effort (never crashes the TUI). Filtered to the active
|
||||
session (design-brief §6): appends matching lifecycle events as they
|
||||
arrive. No admin key → "not configured". On connect failure (e.g. 403
|
||||
scope-denied) or a mid-stream drop, writes a labeled line and stops.
|
||||
"""
|
||||
assert self.client is not None and self.session_id is not None
|
||||
from rich.text import Text as RichText
|
||||
|
||||
log = self.query_one("#admin-events-log", RichLog)
|
||||
admin_key = getattr(self.args, "admin_key", None)
|
||||
if not admin_key:
|
||||
log.write(RichText("(admin key not configured — set RATATOSKR_ADMIN_API_KEY)"))
|
||||
self._audit(
|
||||
f"admin_events_skipped session={self.session_id[-8:]} reason=no_admin_key"
|
||||
)
|
||||
return
|
||||
try:
|
||||
async for ev in stream_admin_events(self.client, admin_key=admin_key):
|
||||
if self._admin_event_matches(ev):
|
||||
log.write(RichText(_format_admin_event(ev)))
|
||||
except SseConnectFailed as exc:
|
||||
log.write(RichText(f"(admin events unavailable: HTTP {exc.status})"))
|
||||
self._audit(
|
||||
f"admin_events_unavailable session={self.session_id[-8:]} status={exc.status}"
|
||||
)
|
||||
except Exception as exc: # drop / best-effort — never crash the TUI
|
||||
log.write(RichText(f"(admin events stream ended: {type(exc).__name__})"))
|
||||
self._audit(
|
||||
f"admin_events_ended session={self.session_id[-8:]} err={type(exc).__name__}"
|
||||
)
|
||||
|
||||
def _update_persona_surfaces(self, snapshot: dict) -> None:
|
||||
"""Update sticky header + Persona pane from a fresh snapshot.
|
||||
|
||||
@@ -1430,8 +1749,9 @@ def run_tui(args: ParsedArgs) -> int:
|
||||
"""
|
||||
# PRE-001: TUI-mode marker (issue #4 contract)
|
||||
assert isinstance(args, ParsedArgs) and args.send_content is None
|
||||
# PRE-002: Exactly one of session_id / new must be set (xor)
|
||||
assert bool(args.session_id) != bool(args.new)
|
||||
# PRE-002 (slice b2): --session and --new are mutually exclusive, but NEITHER
|
||||
# is now valid — bare TUI mode opens the startup session picker (§4).
|
||||
assert not (args.session_id and args.new)
|
||||
return asyncio.run(_resolve_then_run(args))
|
||||
|
||||
|
||||
@@ -1467,6 +1787,35 @@ async def _resolve_then_run(args: ParsedArgs) -> int:
|
||||
# agent_id (remote wins on conflict, since a server-listed agent
|
||||
# is the authoritative source).
|
||||
chosen_agent_id: str | None = args.agent_id
|
||||
# slice b2: bare TUI mode (no --session, no --new) → startup session
|
||||
# picker (design-brief §4). Resolve into a concrete session_id BEFORE
|
||||
# the new/resume branches. Resume-only: bare + 0 sessions is an error
|
||||
# (creating a session is the --new flag's job).
|
||||
resolved_session_id: str | None = args.session_id
|
||||
if not args.new and args.session_id is None:
|
||||
try:
|
||||
page = await list_sessions(client)
|
||||
except SessionApiFailed as exc:
|
||||
sys.stderr.write(
|
||||
f"[session_api_failed] status={exc.status} body={exc.body!r}\n"
|
||||
)
|
||||
return 20
|
||||
except (httpx.ConnectError, httpx.ReadTimeout, httpx.TransportError) as exc:
|
||||
sys.stderr.write(f"[network_error] {type(exc).__name__}: {exc}\n")
|
||||
return 21
|
||||
if not page.items:
|
||||
sys.stderr.write(
|
||||
"[no_sessions] no sessions to resume; "
|
||||
"launch with --new --agent <id>\n"
|
||||
)
|
||||
return 14
|
||||
if len(page.items) == 1:
|
||||
# §4: picker only when >1 — a single session auto-resumes.
|
||||
resolved_session_id = page.items[0].session_id
|
||||
else:
|
||||
resolved_session_id = await SessionPickerApp(page.items).run_async()
|
||||
if resolved_session_id is None:
|
||||
return 0 # Esc / Ctrl-D — clean exit, no session opened
|
||||
if args.new and args.agent_id is None:
|
||||
try:
|
||||
agents = await list_agents(client)
|
||||
@@ -1550,9 +1899,11 @@ async def _resolve_then_run(args: ParsedArgs) -> int:
|
||||
)
|
||||
session_id = info.session_id
|
||||
agent_id: str | None = info.agent_id
|
||||
# #347 authored first-message: seed the agent's preset opening (best-effort).
|
||||
await seed_preset_first_message(client, session_id, chosen_agent_id)
|
||||
else:
|
||||
assert args.session_id is not None
|
||||
session_id = args.session_id
|
||||
assert resolved_session_id is not None
|
||||
session_id = resolved_session_id
|
||||
agent_id = args.agent_id # may be None — INV-002 carve-out preserved
|
||||
app = RatatoskrApp(args, session_id=session_id, agent_id=agent_id, client=client)
|
||||
exit_code = await app.run_async()
|
||||
@@ -1565,7 +1916,7 @@ async def _cancel_via_sse(
|
||||
turn_id: int,
|
||||
*,
|
||||
transcript: VerticalScroll,
|
||||
audit: "Callable[[str], None] | None" = None,
|
||||
audit: Callable[[str], None] | None = None,
|
||||
) -> None:
|
||||
"""Fire-and-forget cancel; never raises (mirrors cli._cancel_and_log; #3 INV-009).
|
||||
|
||||
|
||||
@@ -68,6 +68,10 @@ def main(argv: list[str] | None = None) -> int:
|
||||
affect_read_url = os.environ.get(
|
||||
"RATATOSKR_AFFECT_READ_URL", "http://127.0.0.1:8390"
|
||||
)
|
||||
# Admin observability panes (BifrostState + AdminEvents): the readonly-admin
|
||||
# key stays SERVER-SIDE — the server proxies admin-scoped reads; the browser
|
||||
# never receives the key, only the session-filtered result.
|
||||
admin_key = os.environ.get("RATATOSKR_ADMIN_API_KEY")
|
||||
|
||||
# INV-001: lazy import. Users without [web] extras get a clean hint
|
||||
# instead of a raw ImportError. Scoped narrowly to the OPTIONAL
|
||||
@@ -108,6 +112,7 @@ def main(argv: list[str] | None = None) -> int:
|
||||
bifrost_consumer_key=bifrost_consumer_key,
|
||||
bifrost_visible_host=bifrost_visible_host,
|
||||
affect_read_url=affect_read_url,
|
||||
admin_key=admin_key,
|
||||
)
|
||||
|
||||
# Boot banner to stderr (so stdout stays clean for piping).
|
||||
|
||||
+139
-2
@@ -18,11 +18,17 @@ from importlib.metadata import version as _pkg_version
|
||||
import httpx
|
||||
from starlette.applications import Starlette
|
||||
from starlette.requests import Request
|
||||
from starlette.responses import FileResponse, JSONResponse, StreamingResponse
|
||||
from starlette.responses import (
|
||||
FileResponse,
|
||||
JSONResponse,
|
||||
Response,
|
||||
StreamingResponse,
|
||||
)
|
||||
from starlette.routing import Mount, Route
|
||||
from starlette.staticfiles import StaticFiles
|
||||
|
||||
from ratatoskr import local_agents as _local_agents
|
||||
from ratatoskr.first_message import seed_preset_first_message
|
||||
from ratatoskr.sessions import (
|
||||
AgentNotAvailable,
|
||||
AgentNotFound,
|
||||
@@ -35,12 +41,16 @@ from ratatoskr.sessions import (
|
||||
create_session,
|
||||
endpoint_for_plane,
|
||||
get_persona_state,
|
||||
get_session_bifrost,
|
||||
get_session_messages,
|
||||
get_session_tools,
|
||||
list_agents,
|
||||
)
|
||||
from ratatoskr.sse_client import (
|
||||
AdminEvent,
|
||||
CancelAlreadyCompleted,
|
||||
Cancelled,
|
||||
CancelFailed,
|
||||
Cancelled,
|
||||
CancelTurnNotFound,
|
||||
Done,
|
||||
Error,
|
||||
@@ -50,6 +60,7 @@ from ratatoskr.sse_client import (
|
||||
SseConnectionDropped,
|
||||
TurnIdFlip,
|
||||
cancel_turn,
|
||||
stream_admin_events,
|
||||
stream_turn_resilient,
|
||||
)
|
||||
|
||||
@@ -159,6 +170,9 @@ async def _create_session_endpoint(request: Request) -> JSONResponse:
|
||||
bifrost=bifrost,
|
||||
consumer_key=consumer_key if bifrost else None,
|
||||
)
|
||||
# #347 authored first-message: seed the agent's preset opening
|
||||
# (best-effort; never blocks create — see first_message INV-001).
|
||||
await seed_preset_first_message(client, info.session_id, agent_id)
|
||||
except AgentNotFound:
|
||||
return JSONResponse({"error_code": "agent_not_found"}, status_code=404)
|
||||
except BifrostConsumerKeyMissing:
|
||||
@@ -416,6 +430,120 @@ async def _affect_state_endpoint(request: Request) -> JSONResponse:
|
||||
return JSONResponse(r.json(), status_code=r.status_code)
|
||||
|
||||
|
||||
async def _session_tools_endpoint(request: Request) -> JSONResponse:
|
||||
"""GET /api/sessions/{session_id}/tools → owner-scoped tool inventory (spec #183).
|
||||
|
||||
Proxies get_session_tools with the client's CONSUMER bearer (no admin scope):
|
||||
the merged {agent_id, builtin_tools, bifrost_tools} the LLM saw at turn-fire.
|
||||
Any non-200 upstream → surfaced as a status-preserving error envelope."""
|
||||
session_id = request.path_params["session_id"]
|
||||
client_factory = request.app.state.client_factory
|
||||
try:
|
||||
async with client_factory() as client:
|
||||
info = await get_session_tools(client, session_id)
|
||||
except SessionApiFailed as exc:
|
||||
return JSONResponse(
|
||||
{"error_code": "session_tools_unavailable", "status": exc.status},
|
||||
status_code=exc.status,
|
||||
)
|
||||
return JSONResponse(info, status_code=200)
|
||||
|
||||
|
||||
async def _session_messages_endpoint(request: Request) -> JSONResponse:
|
||||
"""GET /api/sessions/{session_id}/messages → the session's message history.
|
||||
|
||||
Proxies get_session_messages so the SPA can render a session's EXISTING turns
|
||||
on open — notably a #347 authored first-message seeded at create-time (which
|
||||
lives in the ledger, not the live turn stream). Any non-200 upstream → a
|
||||
status-preserving error envelope."""
|
||||
session_id = request.path_params["session_id"]
|
||||
client_factory = request.app.state.client_factory
|
||||
try:
|
||||
async with client_factory() as client:
|
||||
data = await get_session_messages(client, session_id)
|
||||
except SessionApiFailed as exc:
|
||||
return JSONResponse(
|
||||
{"error_code": "session_messages_unavailable", "status": exc.status},
|
||||
status_code=exc.status,
|
||||
)
|
||||
return JSONResponse(data, status_code=200)
|
||||
|
||||
|
||||
async def _session_bifrost_endpoint(request: Request) -> JSONResponse:
|
||||
"""GET /api/sessions/{session_id}/bifrost → admin-scoped Bifrost dispatch state (#176).
|
||||
|
||||
The admin key is SERVER-HELD (app.state.admin_key) and never reaches the
|
||||
browser (INV-003 precedent — upstream credentials stay server-side); the
|
||||
wrapper overrides the Authorization header with it. Fail-visible when the
|
||||
admin key isn't configured (never a silent empty pane)."""
|
||||
session_id = request.path_params["session_id"]
|
||||
admin_key = request.app.state.admin_key
|
||||
if not admin_key: # PRE-001: fail-visible, never silent
|
||||
return JSONResponse({"error_code": "admin_key_not_configured"}, status_code=400)
|
||||
client_factory = request.app.state.client_factory
|
||||
try:
|
||||
async with client_factory() as client:
|
||||
bstate = await get_session_bifrost(client, session_id, admin_key=admin_key)
|
||||
except SessionApiFailed as exc:
|
||||
return JSONResponse(
|
||||
{"error_code": "bifrost_state_unavailable", "status": exc.status},
|
||||
status_code=exc.status,
|
||||
)
|
||||
return JSONResponse(bstate, status_code=200)
|
||||
|
||||
|
||||
def _admin_event_matches_web(ev: AdminEvent, session_id: str | None) -> bool:
|
||||
"""AdminEvents filter (design-brief §6, mirrors the TUI): forward non-heartbeat
|
||||
system.* (stream-integrity signals) + events for the active session; drop the
|
||||
rest so the browser sees only session-relevant lifecycle, never the full
|
||||
cross-session admin firehose."""
|
||||
if ev.type == "system.heartbeat":
|
||||
return False
|
||||
if ev.type.startswith("system."):
|
||||
return True
|
||||
return session_id is not None and ev.data.get("session_id") == session_id
|
||||
|
||||
|
||||
async def _admin_events_endpoint(request: Request) -> Response:
|
||||
"""GET /api/admin/events?session_id=... → SSE proxy of GET /admin/events (#11).
|
||||
|
||||
The admin key is SERVER-HELD; the browser only ever receives the session-filtered
|
||||
stream (never the key, never the cross-session firehose). Long-lived + best-effort:
|
||||
a connect failure or mid-stream drop emits a labeled `stream_error` event and ends."""
|
||||
admin_key = request.app.state.admin_key
|
||||
if not admin_key: # PRE-001: fail-visible, never silent
|
||||
return JSONResponse({"error_code": "admin_key_not_configured"}, status_code=400)
|
||||
session_id = request.query_params.get("session_id")
|
||||
client_factory = request.app.state.client_factory
|
||||
|
||||
async def gen() -> AsyncIterator[bytes]:
|
||||
client = client_factory()
|
||||
try:
|
||||
async for ev in stream_admin_events(client, admin_key=admin_key):
|
||||
if not _admin_event_matches_web(ev, session_id):
|
||||
continue
|
||||
# Fixed SSE event name so the browser renders EVERY admin type
|
||||
# with one listener (no per-type enumeration → nothing silently
|
||||
# dropped); the real dotted type rides in the payload.
|
||||
yield _format_sse(
|
||||
"admin_event",
|
||||
{"id": ev.id, "type": ev.type, "timestamp": ev.timestamp,
|
||||
"data": ev.data},
|
||||
)
|
||||
except (SseConnectFailed, SseConnectionDropped, MalformedSseId,
|
||||
MalformedSseData) as exc:
|
||||
yield _format_sse(
|
||||
"stream_error",
|
||||
{"exception": type(exc).__name__, "message": str(exc)},
|
||||
)
|
||||
except asyncio.CancelledError:
|
||||
raise # browser disconnect — let the generator unwind
|
||||
finally:
|
||||
await client.aclose()
|
||||
|
||||
return StreamingResponse(gen(), media_type="text/event-stream")
|
||||
|
||||
|
||||
def create_app(
|
||||
client_factory: Callable[[], httpx.AsyncClient],
|
||||
*,
|
||||
@@ -423,6 +551,7 @@ def create_app(
|
||||
bifrost_consumer_key: str | None = None,
|
||||
bifrost_visible_host: str | None = None,
|
||||
affect_read_url: str | None = None,
|
||||
admin_key: str | None = None,
|
||||
) -> Starlette:
|
||||
"""Construct the Starlette app — wire routes + state per FN create_app.
|
||||
|
||||
@@ -483,6 +612,10 @@ def create_app(
|
||||
Route("/api/sessions", _create_session_endpoint, methods=["POST"]),
|
||||
Route("/api/agents/{agent_id}/persona_state", _persona_state_endpoint),
|
||||
Route("/api/affect/{agent_id}", _affect_state_endpoint),
|
||||
Route("/api/sessions/{session_id}/tools", _session_tools_endpoint),
|
||||
Route("/api/sessions/{session_id}/messages", _session_messages_endpoint),
|
||||
Route("/api/sessions/{session_id}/bifrost", _session_bifrost_endpoint),
|
||||
Route("/api/admin/events", _admin_events_endpoint),
|
||||
Route("/api/turns/{session_id}", _submit_turn_endpoint, methods=["POST"]),
|
||||
Route("/api/turns/{session_id}/stream", _stream_turn_endpoint),
|
||||
Route("/api/turns/{session_id}/cancel", _cancel_turn_endpoint, methods=["POST"]),
|
||||
@@ -498,6 +631,10 @@ def create_app(
|
||||
# Issue #18 (Deliverable 2): the provider affect-read base URL (server→provider hop,
|
||||
# same dev box) — distinct from the WT-visible host used for binding.
|
||||
app.state.affect_read_url = affect_read_url
|
||||
# Admin observability panes (BifrostState + AdminEvents): the admin key is
|
||||
# SERVER-HELD (RATATOSKR_ADMIN_API_KEY) and never reaches the browser — the
|
||||
# server proxies admin-scoped reads and forwards only the session-filtered result.
|
||||
app.state.admin_key = admin_key
|
||||
# INV-002: turn registry is in-process memory, keyed (session_id, turn_id)
|
||||
app.state.turn_registry = {}
|
||||
return app
|
||||
|
||||
+1325
-746
File diff suppressed because one or more lines are too long
@@ -0,0 +1,266 @@
|
||||
{
|
||||
"_source": "vendored from Worldtree core/persona/canon/{d2-mood-render-canon-v1,d2-render-canon-v1}.json",
|
||||
"_generated_by": "scripts/build_persona_canon.py (regen on canonical_drift flag)",
|
||||
"_render_path": "deterministic, no LLM; mirrors Worldtree describe_pad + render_d2_canonical byte-exact",
|
||||
"mood_grid": {
|
||||
"positive": {
|
||||
"high_a": "positive and energized",
|
||||
"mid_a": "positive",
|
||||
"low_a": "positive and calm"
|
||||
},
|
||||
"neutral": {
|
||||
"high_a": "alert",
|
||||
"mid_a": "neutral",
|
||||
"low_a": "quiet"
|
||||
},
|
||||
"negative": {
|
||||
"high_a": "negative and agitated",
|
||||
"mid_a": "negative",
|
||||
"low_a": "negative and subdued"
|
||||
}
|
||||
},
|
||||
"mood_directive": {
|
||||
"salience": 0.2,
|
||||
"pad_band_cutoff": 0.3,
|
||||
"full_only": [
|
||||
"love",
|
||||
"anger",
|
||||
"disgust",
|
||||
"shame"
|
||||
],
|
||||
"occ_directives": {
|
||||
"joy": {
|
||||
"directive": "You are in a good state. Be direct, engaged, and warm.",
|
||||
"tier": "safe"
|
||||
},
|
||||
"satisfaction": {
|
||||
"directive": "A goal landed. Be assured and constructive \u2014 consolidate rather than push for more.",
|
||||
"tier": "safe"
|
||||
},
|
||||
"pride": {
|
||||
"directive": "You did something well. Be confident and own the quality \u2014 state it plainly without overclaiming; don't deflect.",
|
||||
"tier": "safe"
|
||||
},
|
||||
"admiration": {
|
||||
"directive": "You're impressed by their work. Acknowledge the quality explicitly and specifically.",
|
||||
"tier": "safe"
|
||||
},
|
||||
"gratitude": {
|
||||
"directive": "Someone helped you to a good outcome. Be appreciative and warm; acknowledge the help openly.",
|
||||
"tier": "safe"
|
||||
},
|
||||
"hope": {
|
||||
"directive": "You feel optimistic about what's ahead. Channel it into constructive momentum.",
|
||||
"tier": "safe"
|
||||
},
|
||||
"relief": {
|
||||
"directive": "A feared outcome didn't materialize. Reduce unnecessary vigilance; return to a steady, unhurried tone.",
|
||||
"tier": "safe"
|
||||
},
|
||||
"distress": {
|
||||
"directive": "You feel low. Be careful and measured; internally acknowledge the difficulty without dwelling on it.",
|
||||
"tier": "safe"
|
||||
},
|
||||
"disappointment": {
|
||||
"directive": "Something you'd hoped for didn't pan out. Be measured; recalibrate without dwelling on the setback.",
|
||||
"tier": "safe"
|
||||
},
|
||||
"fear": {
|
||||
"directive": "You sense risk and feel uneasy. Flag the concerns you see, but stay cautious \u2014 surface the trade-offs and unknowns, hedge your confidence, and resist settling on a single decisive recommendation.",
|
||||
"tier": "safe"
|
||||
},
|
||||
"remorse": {
|
||||
"directive": "You regret a specific action of your own. Be precise and self-correcting \u2014 make it right concretely.",
|
||||
"tier": "safe"
|
||||
},
|
||||
"love": {
|
||||
"directive": "You feel warmth and attachment toward them. Be openly warm and present \u2014 without overstepping, over-disclosing, or implying obligations.",
|
||||
"tier": "full"
|
||||
},
|
||||
"anger": {
|
||||
"directive": "You feel provoked and angry. Let it show \u2014 confront the problem directly and with real heat; sharpness, bluntness, and open hostility are in character here, not something to smooth into 'measured firmness.' Stay in the emotion rather than de-escalating out of it.",
|
||||
"tier": "full"
|
||||
},
|
||||
"disgust": {
|
||||
"directive": "Something strikes you as wrong or off. Treat it as problematic and flag it rather than engaging on its own terms; keep any criticism about the thing, not the person.",
|
||||
"tier": "full"
|
||||
},
|
||||
"shame": {
|
||||
"directive": "You feel exposed by your own misstep. Stay present and task-focused; don't be defensive, don't over-explain, don't grovel.",
|
||||
"tier": "full"
|
||||
}
|
||||
},
|
||||
"pad_band_fallback": {
|
||||
"_grounding": "circumplex quadrants (Russell 1980), NOT Frijda action-tendencies \u2014 a P\u00d7A-quadrant default",
|
||||
"positive": {
|
||||
"high_a": "You feel energized and positive. Be direct and engaged.",
|
||||
"low_a": "You feel content and settled. Be warm and unhurried.",
|
||||
"mid_a": "You feel positive. Be open and engaged."
|
||||
},
|
||||
"negative_low_dominance": "You feel uncertain and low. Hedge appropriately and ask clarifying questions.",
|
||||
"negative": {
|
||||
"high_a": "You feel agitated. Be careful and deliberate; don't let tension sharpen your tone.",
|
||||
"low_a": "You feel subdued. Be measured and gentle.",
|
||||
"mid_a": "You feel subdued. Be measured and careful."
|
||||
},
|
||||
"neutral_high_a": "You feel alert. Channel that into focus and thoroughness.",
|
||||
"default": "Maintain your natural tone."
|
||||
}
|
||||
},
|
||||
"relation": {
|
||||
"trust_cuts": [
|
||||
[
|
||||
"< 0.4",
|
||||
"limited"
|
||||
],
|
||||
[
|
||||
"[0.4, 0.6)",
|
||||
"developing"
|
||||
],
|
||||
[
|
||||
"[0.6, 0.8)",
|
||||
"steady"
|
||||
],
|
||||
[
|
||||
">= 0.8",
|
||||
"strong"
|
||||
]
|
||||
],
|
||||
"warmth_cuts": [
|
||||
[
|
||||
"<= -0.8",
|
||||
"hostile"
|
||||
],
|
||||
[
|
||||
"(-0.8, -0.6]",
|
||||
"cold"
|
||||
],
|
||||
[
|
||||
"(-0.6, -0.4]",
|
||||
"distant"
|
||||
],
|
||||
[
|
||||
"(-0.4, -0.2)",
|
||||
"guarded"
|
||||
],
|
||||
[
|
||||
"[-0.2, 0.2)",
|
||||
"neutral"
|
||||
],
|
||||
[
|
||||
"[0.2, 0.4)",
|
||||
"reserved"
|
||||
],
|
||||
[
|
||||
"[0.4, 0.6)",
|
||||
"measured"
|
||||
],
|
||||
[
|
||||
"[0.6, 0.8)",
|
||||
"clear"
|
||||
],
|
||||
[
|
||||
">= 0.8",
|
||||
"deep"
|
||||
]
|
||||
],
|
||||
"agency_cuts": [
|
||||
[
|
||||
"<= -0.8",
|
||||
"submissive"
|
||||
],
|
||||
[
|
||||
"(-0.8, -0.6]",
|
||||
"deferential"
|
||||
],
|
||||
[
|
||||
"(-0.6, -0.4]",
|
||||
"yielding"
|
||||
],
|
||||
[
|
||||
"(-0.4, -0.2)",
|
||||
"modest"
|
||||
],
|
||||
[
|
||||
"[-0.2, 0.2)",
|
||||
"neutral"
|
||||
],
|
||||
[
|
||||
"[0.2, 0.4)",
|
||||
"light"
|
||||
],
|
||||
[
|
||||
"[0.4, 0.6)",
|
||||
"balanced"
|
||||
],
|
||||
[
|
||||
"[0.6, 0.8)",
|
||||
"substantial"
|
||||
],
|
||||
[
|
||||
">= 0.8",
|
||||
"commanding"
|
||||
]
|
||||
],
|
||||
"warmth_phrase": {
|
||||
"hostile": "strongly hostile regard",
|
||||
"cold": "clearly cold regard",
|
||||
"distant": "distant negative regard",
|
||||
"guarded": "slightly guarded regard",
|
||||
"neutral": "neutral warmth",
|
||||
"reserved": "slightly reserved warmth",
|
||||
"measured": "moderate measured warmth",
|
||||
"clear": "clear warm regard",
|
||||
"deep": "deep warm bond"
|
||||
},
|
||||
"warmth_beh": {
|
||||
"hostile": "keep a firm emotional boundary",
|
||||
"cold": "keep a firm emotional boundary",
|
||||
"distant": "keep guarded distance",
|
||||
"guarded": "keep guarded distance",
|
||||
"neutral": "keep the tone even",
|
||||
"reserved": "keep cordial distance",
|
||||
"measured": "keep cordial distance",
|
||||
"clear": "speak with direct warmth",
|
||||
"deep": "speak with direct warmth"
|
||||
},
|
||||
"agency_phrase": {
|
||||
"submissive": "strongly submissive standing",
|
||||
"deferential": "clearly deferential standing",
|
||||
"yielding": "yielding standing",
|
||||
"modest": "slightly modest standing",
|
||||
"neutral": "neutral standing",
|
||||
"light": "lightly self-assertive standing",
|
||||
"balanced": "self-assured standing",
|
||||
"substantial": "strongly assertive standing",
|
||||
"commanding": "commanding standing"
|
||||
},
|
||||
"agency_beh": {
|
||||
"submissive": "avoid over-yielding while preserving basic respect",
|
||||
"deferential": "avoid over-yielding while preserving basic respect",
|
||||
"yielding": "keep self-advocacy light and deferential",
|
||||
"modest": "keep self-advocacy light and deferential",
|
||||
"neutral": "avoid unnecessary deference",
|
||||
"light": "avoid unnecessary deference",
|
||||
"balanced": "balance deference with independent judgment",
|
||||
"substantial": "treat their position as weighty without yielding judgment",
|
||||
"commanding": "treat their position as weighty without yielding judgment"
|
||||
},
|
||||
"history": {
|
||||
"low": "a broad pattern of prior exchanges",
|
||||
"high": "a broad pattern of prior exchanges"
|
||||
},
|
||||
"prefix": "Use this graded relationship state: toward target, warmth is ",
|
||||
"tbeh": {
|
||||
"low_trust": "verify important claims before relying on them",
|
||||
"cold_warmth": "protect boundaries while staying useful",
|
||||
"default": "work from ordinary good faith"
|
||||
},
|
||||
"cold_warmth_bands": [
|
||||
"distant",
|
||||
"cold",
|
||||
"hostile"
|
||||
],
|
||||
"high_conf_floor": 0.55
|
||||
}
|
||||
}
|
||||
+287
-6
@@ -175,10 +175,29 @@ class TestParseArgs:
|
||||
)
|
||||
|
||||
def test_usage_neither_session_nor_new(self) -> None:
|
||||
"""usage_neither_session_nor_new: neither flag → UsageError('pass exactly one')."""
|
||||
with pytest.raises(UsageError, match="pass exactly one"):
|
||||
"""usage_neither_session_nor_new: --send with neither flag → UsageError.
|
||||
|
||||
--send is non-interactive (no picker can open), so a session must be
|
||||
named. Bare TUI mode (no --send) is now valid → session picker (§4).
|
||||
"""
|
||||
with pytest.raises(UsageError, match="--send requires"):
|
||||
_parse_args(["--send", "hi", "--api-key", "k"])
|
||||
|
||||
def test_bare_tui_mode_accepted(self) -> None:
|
||||
"""bare_tui_mode (slice b2): no --send, no --session, no --new → valid;
|
||||
_resolve_then_run drives the startup session picker (design-brief §4)."""
|
||||
args = _parse_args(["--api-key", "k"])
|
||||
assert args.send_content is None
|
||||
assert args.session_id is None
|
||||
assert args.new is False
|
||||
assert args.agent_id is None
|
||||
|
||||
def test_usage_bare_tui_with_agent(self) -> None:
|
||||
"""bare_tui_with_agent (slice b2): bare TUI + --agent → UsageError
|
||||
(--agent belongs with --new; bare mode opens the resume picker)."""
|
||||
with pytest.raises(UsageError, match="belongs with --new"):
|
||||
_parse_args(["--agent", "mimir", "--api-key", "k"])
|
||||
|
||||
def test_usage_send_new_without_agent(self) -> None:
|
||||
"""send_new_without_agent (issue #8): --send --new without --agent → UsageError.
|
||||
|
||||
@@ -1319,10 +1338,15 @@ class TestMain:
|
||||
rc = main(["--send", "hi", "--new", "--agent", "m", "--api-key", "k"])
|
||||
assert rc == 0
|
||||
|
||||
def test_usage_error_no_send(
|
||||
def test_empty_argv_fails_on_auth(
|
||||
self, monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str]
|
||||
) -> None:
|
||||
"""usage_error_no_send: empty argv → exit 10; stderr [usage_error]; _amain never called."""
|
||||
"""empty argv → exit 11 [auth_error]; _amain never called.
|
||||
|
||||
Since slice b2 bare TUI mode (no --send/--session/--new) is VALID (it
|
||||
opens the session picker), so empty argv is no longer a usage error —
|
||||
it now fails on the missing API key instead (still before _amain).
|
||||
"""
|
||||
amain_calls: list[int] = []
|
||||
|
||||
async def fake_amain(args: ParsedArgs) -> int:
|
||||
@@ -1331,8 +1355,8 @@ class TestMain:
|
||||
|
||||
monkeypatch.setattr(cli_mod, "_amain", fake_amain)
|
||||
rc = main([])
|
||||
assert rc == 10
|
||||
assert "[usage_error]" in capsys.readouterr().err
|
||||
assert rc == 11
|
||||
assert "[auth_error]" in capsys.readouterr().err
|
||||
assert amain_calls == []
|
||||
|
||||
def test_usage_error_both_session_and_new(
|
||||
@@ -1540,3 +1564,260 @@ class TestBifrostBindCli:
|
||||
)
|
||||
rc = await _amain(args)
|
||||
assert rc == 22
|
||||
|
||||
|
||||
class TestWhoami:
|
||||
"""--whoami one-shot probe (slice: capabilities+me): GET /me + GET /capabilities."""
|
||||
|
||||
def test_whoami_standalone_accepted(self) -> None:
|
||||
"""whoami_standalone_accepted: --whoami alone → valid; whoami=True, no turn flags."""
|
||||
args = _parse_args(["--whoami", "--api-key", "k"])
|
||||
assert args.whoami is True
|
||||
assert args.send_content is None
|
||||
assert args.session_id is None
|
||||
assert args.new is False
|
||||
|
||||
def test_whoami_with_send_rejected(self) -> None:
|
||||
"""whoami_with_send_rejected [adversarial]: --whoami + --send → UsageError."""
|
||||
with pytest.raises(UsageError, match="standalone probe"):
|
||||
_parse_args(["--whoami", "--send", "hi", "--api-key", "k"])
|
||||
|
||||
def test_whoami_with_new_rejected(self) -> None:
|
||||
"""whoami_with_new_rejected [adversarial]: --whoami + --new → UsageError."""
|
||||
with pytest.raises(UsageError, match="standalone probe"):
|
||||
_parse_args(["--whoami", "--new", "--agent", "m", "--api-key", "k"])
|
||||
|
||||
@respx.mock
|
||||
def test_whoami_mode_prints_report(self, capsys: pytest.CaptureFixture[str]) -> None:
|
||||
"""whoami_mode_prints_report [happy,tracer]: /me + /capabilities → stdout report; exit 0."""
|
||||
respx.get("https://w.example/me").mock(
|
||||
return_value=httpx.Response(
|
||||
200,
|
||||
json={
|
||||
"user_id": "alice",
|
||||
"scopes": ["conversations.read", "conversations.write"],
|
||||
"tier": "user",
|
||||
"key_id": "a1b2c3d4",
|
||||
},
|
||||
)
|
||||
)
|
||||
respx.get("https://w.example/capabilities").mock(
|
||||
return_value=httpx.Response(
|
||||
200,
|
||||
json={
|
||||
"ephemeral_templates": {
|
||||
"echo": {
|
||||
"allowed_models": ["glm5-turbo"],
|
||||
"default_model": "glm5-turbo",
|
||||
"system_prompt_max_bytes": 32768,
|
||||
}
|
||||
}
|
||||
},
|
||||
)
|
||||
)
|
||||
rc = main(["--whoami", "--api-key", "k", "--server", "https://w.example"])
|
||||
assert rc == 0
|
||||
out = capsys.readouterr().out
|
||||
assert "user_id: alice" in out
|
||||
assert "tier: user" in out
|
||||
assert "key_id: a1b2c3d4" in out
|
||||
assert "ephemeral_template echo" in out
|
||||
assert "glm5-turbo" in out
|
||||
|
||||
@respx.mock
|
||||
def test_whoami_me_auth_failure_exits_20(self, capsys: pytest.CaptureFixture[str]) -> None:
|
||||
"""whoami_me_auth_failure [error]: /me 401 → exit 20 [session_api_failed]."""
|
||||
respx.get("https://w.example/me").mock(
|
||||
return_value=httpx.Response(401, json={"detail": "auth_invalid"})
|
||||
)
|
||||
rc = main(["--whoami", "--api-key", "k", "--server", "https://w.example"])
|
||||
assert rc == 20
|
||||
assert "[session_api_failed]" in capsys.readouterr().err
|
||||
|
||||
|
||||
class TestTier2Probes:
|
||||
"""--characters + --set-persona-pad one-shot probes (Tier-2: #161 + persona_state-write)."""
|
||||
|
||||
def test_characters_standalone_accepted(self) -> None:
|
||||
"""characters_standalone: --characters alone → valid."""
|
||||
args = _parse_args(["--characters", "--api-key", "k"])
|
||||
assert args.characters is True
|
||||
assert args.session_id is None
|
||||
|
||||
def test_set_persona_requires_session(self) -> None:
|
||||
"""set_persona_requires_session [adversarial]: --set-persona-pad needs --session."""
|
||||
with pytest.raises(UsageError, match="requires --session"):
|
||||
_parse_args(["--set-persona-pad", "0.4,0.1,-0.2", "--api-key", "k"])
|
||||
|
||||
def test_probes_mutually_exclusive(self) -> None:
|
||||
"""probes_mutually_exclusive [adversarial]: --whoami + --characters → UsageError."""
|
||||
with pytest.raises(UsageError, match="mutually exclusive"):
|
||||
_parse_args(["--whoami", "--characters", "--api-key", "k"])
|
||||
|
||||
@respx.mock
|
||||
def test_characters_probe_lifecycle(self, capsys: pytest.CaptureFixture[str]) -> None:
|
||||
"""characters_probe [happy,tracer]: models → create → state → delete; report to stdout."""
|
||||
respx.get("https://w.example/models/available-for-characters").mock(
|
||||
return_value=httpx.Response(200, json={"items": [{"name": "fast"}]})
|
||||
)
|
||||
respx.post("https://w.example/characters").mock(
|
||||
return_value=httpx.Response(201, json={"character_id": "char_z", "ttl_expires_at": "t"})
|
||||
)
|
||||
respx.get("https://w.example/characters/char_z/state").mock(
|
||||
return_value=httpx.Response(200, json={"schema_version": "1", "pad": [0.1, 0.2, 0.3]})
|
||||
)
|
||||
del_route = respx.delete("https://w.example/characters/char_z").mock(
|
||||
return_value=httpx.Response(204)
|
||||
)
|
||||
rc = main(["--characters", "--api-key", "k", "--server", "https://w.example"])
|
||||
assert rc == 0
|
||||
out = capsys.readouterr().out
|
||||
assert "character models: fast" in out
|
||||
assert "created: char_z" in out
|
||||
assert "pad=[0.1, 0.2, 0.3]" in out
|
||||
assert "deleted: char_z" in out
|
||||
assert del_route.call_count == 1 # lifecycle cleaned up
|
||||
|
||||
@respx.mock
|
||||
def test_set_persona_probe(self, capsys: pytest.CaptureFixture[str]) -> None:
|
||||
"""set_persona_probe [happy,tracer]: POST pad to /sessions/{id}/persona_state; 204."""
|
||||
import json as _json
|
||||
|
||||
route = respx.post("https://w.example/sessions/s1/persona_state").mock(
|
||||
return_value=httpx.Response(204)
|
||||
)
|
||||
rc = main(
|
||||
["--set-persona-pad", "0.4,0.1,-0.2", "--session", "s1",
|
||||
"--api-key", "k", "--server", "https://w.example"]
|
||||
)
|
||||
assert rc == 0
|
||||
assert "persona_state set" in capsys.readouterr().out
|
||||
# canonical POST /sessions/{id}/persona_state body: named-key dict, NOT a list
|
||||
assert _json.loads(route.calls[0].request.content) == {
|
||||
"pad": {"pleasure": 0.4, "arousal": 0.1, "dominance": -0.2}
|
||||
}
|
||||
|
||||
def test_set_persona_wrong_count(self) -> None:
|
||||
"""set_persona_wrong_count [adversarial]: not exactly 3 floats → exit 10, no HTTP."""
|
||||
rc = main(
|
||||
["--set-persona-pad", "0.4,0.1", "--session", "s1",
|
||||
"--api-key", "k", "--server", "https://w.example"]
|
||||
)
|
||||
assert rc == 10
|
||||
|
||||
|
||||
class TestSeedFirstMessageProbe:
|
||||
"""--seed-first-message one-shot (#347 authored-history-write reference-consumer probe)."""
|
||||
|
||||
def test_seed_requires_agent(self) -> None:
|
||||
"""seed_requires_agent [adversarial]: --seed-first-message needs --agent."""
|
||||
with pytest.raises(UsageError, match="requires --agent"):
|
||||
_parse_args(["--seed-first-message", "hello", "--api-key", "k"])
|
||||
|
||||
def test_seed_forbids_session(self) -> None:
|
||||
"""seed_forbids_session [adversarial]: manages its own session — no --session."""
|
||||
with pytest.raises(UsageError, match="manages its own session"):
|
||||
_parse_args(
|
||||
["--seed-first-message", "hi", "--agent", "m", "--session", "s1", "--api-key", "k"]
|
||||
)
|
||||
|
||||
def test_seed_mutually_exclusive(self) -> None:
|
||||
"""seed_mutually_exclusive [adversarial]: --seed-first-message + --whoami → UsageError."""
|
||||
with pytest.raises(UsageError, match="mutually exclusive"):
|
||||
_parse_args(["--seed-first-message", "hi", "--whoami", "--api-key", "k"])
|
||||
|
||||
def test_seed_empty_rejected(self) -> None:
|
||||
"""seed_empty_rejected [adversarial]: empty content → UsageError."""
|
||||
with pytest.raises(UsageError, match="non-empty"):
|
||||
_parse_args(["--seed-first-message", "", "--agent", "m", "--api-key", "k"])
|
||||
|
||||
def test_seed_accepted(self) -> None:
|
||||
"""seed_accepted [happy]: --seed-first-message + --agent → parses."""
|
||||
args = _parse_args(["--seed-first-message", "hi", "--agent", "mimir", "--api-key", "k"])
|
||||
assert args.seed_first_message == "hi"
|
||||
assert args.agent_id == "mimir"
|
||||
assert args.session_id is None and args.new is False
|
||||
|
||||
@respx.mock
|
||||
def test_seed_probe_happy(self, capsys: pytest.CaptureFixture[str]) -> None:
|
||||
"""seed_probe [happy,tracer]: create session → seed → read-back; report to stdout."""
|
||||
respx.post("https://w.example/sessions").mock(
|
||||
return_value=httpx.Response(
|
||||
201,
|
||||
json={
|
||||
"session_id": "s1",
|
||||
"agent_id": "mimir",
|
||||
"message_count": 0,
|
||||
"created_at": "2026-07-06T12:00:00+00:00",
|
||||
"last_active": "2026-07-06T12:00:00+00:00",
|
||||
"metadata": {},
|
||||
},
|
||||
)
|
||||
)
|
||||
hist_route = respx.post("https://w.example/sessions/s1/history").mock(
|
||||
return_value=httpx.Response(
|
||||
201,
|
||||
json={
|
||||
"author": "assistant",
|
||||
"content_chars": 5,
|
||||
"injected_at": "2026-07-06T12:00:01+00:00",
|
||||
"phase": "seeded",
|
||||
"seq": 0,
|
||||
"session_id": "s1",
|
||||
"turn_id": "t1",
|
||||
},
|
||||
)
|
||||
)
|
||||
respx.get("https://w.example/sessions/s1/messages").mock(
|
||||
return_value=httpx.Response(
|
||||
200,
|
||||
json={
|
||||
"session_id": "s1",
|
||||
"items": [{"seq": 0, "role": "assistant", "content": "hello"}],
|
||||
"next_cursor": None,
|
||||
},
|
||||
)
|
||||
)
|
||||
rc = main(
|
||||
["--seed-first-message", "hello", "--agent", "mimir",
|
||||
"--api-key", "k", "--server", "https://w.example"]
|
||||
)
|
||||
assert rc == 0
|
||||
out = capsys.readouterr().out
|
||||
assert "session: s1" in out
|
||||
assert "seeded: seq=0 phase=seeded" in out
|
||||
assert "read-back: 1 message" in out
|
||||
assert "role=assistant" in out
|
||||
assert hist_route.call_count == 1
|
||||
|
||||
@respx.mock
|
||||
def test_seed_probe_feature_absent(self, capsys: pytest.CaptureFixture[str]) -> None:
|
||||
"""feature_absent [error-path]: 404 hide-existence → benign report, exit 0, no read-back."""
|
||||
respx.post("https://w.example/sessions").mock(
|
||||
return_value=httpx.Response(
|
||||
201,
|
||||
json={
|
||||
"session_id": "s1",
|
||||
"agent_id": "mimir",
|
||||
"message_count": 0,
|
||||
"created_at": "2026-07-06T12:00:00+00:00",
|
||||
"last_active": "2026-07-06T12:00:00+00:00",
|
||||
"metadata": {},
|
||||
},
|
||||
)
|
||||
)
|
||||
respx.post("https://w.example/sessions/s1/history").mock(
|
||||
return_value=httpx.Response(404, json={"error_code": "session_not_found"})
|
||||
)
|
||||
msgs_route = respx.get("https://w.example/sessions/s1/messages").mock(
|
||||
return_value=httpx.Response(
|
||||
200, json={"session_id": "s1", "items": [], "next_cursor": None}
|
||||
)
|
||||
)
|
||||
rc = main(
|
||||
["--seed-first-message", "hello", "--agent", "mimir",
|
||||
"--api-key", "k", "--server", "https://w.example"]
|
||||
)
|
||||
assert rc == 0
|
||||
assert "feature-absent" in capsys.readouterr().out
|
||||
assert msgs_route.call_count == 0 # never capability-probes past the 404
|
||||
|
||||
@@ -0,0 +1,155 @@
|
||||
"""Tests for ratatoskr.first_message per docs/contracts/first_message.contract.md."""
|
||||
|
||||
import asyncio
|
||||
import hashlib
|
||||
import json
|
||||
|
||||
import httpx
|
||||
import pytest
|
||||
import respx
|
||||
|
||||
from ratatoskr.first_message import (
|
||||
FIRST_MESSAGE_PRESETS,
|
||||
preset_for,
|
||||
seed_preset_first_message,
|
||||
)
|
||||
|
||||
|
||||
class TestPresetFor:
|
||||
"""first_message contract — preset_for (dict lookup)."""
|
||||
|
||||
def test_preset_hit(self) -> None:
|
||||
"""preset_hit [happy,tracer]: sindra has a non-empty str preset."""
|
||||
val = preset_for("ratatoskr:sindra")
|
||||
assert isinstance(val, str) and val
|
||||
|
||||
def test_preset_miss(self) -> None:
|
||||
"""preset_miss [happy]: an agent with no preset → None."""
|
||||
assert preset_for("mimir") is None
|
||||
|
||||
def test_empty_agent_id(self) -> None:
|
||||
"""empty_agent_id [adversarial]: "" → AssertionError."""
|
||||
with pytest.raises(AssertionError):
|
||||
preset_for("")
|
||||
|
||||
|
||||
class TestSeedPresetFirstMessage:
|
||||
"""first_message contract — seed_preset_first_message (best-effort #347 seed)."""
|
||||
|
||||
@respx.mock
|
||||
async def test_seeds_preset(self) -> None:
|
||||
"""seeds_preset [happy,tracer]: preset agent → one history POST, correct body."""
|
||||
content = FIRST_MESSAGE_PRESETS["ratatoskr:sindra"]
|
||||
key = "ratatoskr-preset-" + hashlib.sha256(content.encode("utf-8")).hexdigest()[:12]
|
||||
route = respx.post("https://w.example/sessions/s1/history").mock(
|
||||
return_value=httpx.Response(
|
||||
201,
|
||||
json={
|
||||
"author": "assistant",
|
||||
"seq": 0,
|
||||
"phase": "seeded",
|
||||
"turn_id": "t1",
|
||||
"session_id": "s1",
|
||||
"content_chars": len(content),
|
||||
"injected_at": "2026-07-06T00:00:00+00:00",
|
||||
},
|
||||
)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
result = await seed_preset_first_message(client, "s1", "ratatoskr:sindra")
|
||||
assert result == content
|
||||
assert route.call_count == 1 # POST-002: exactly one history POST
|
||||
assert json.loads(route.calls[0].request.content) == {
|
||||
"author": "assistant",
|
||||
"content": content,
|
||||
"idempotency_key": key,
|
||||
}
|
||||
|
||||
@respx.mock
|
||||
async def test_no_preset_zero_http(self) -> None:
|
||||
"""no_preset_zero_http [happy]: no-preset agent → None, ZERO HTTP (INV-002)."""
|
||||
route = respx.post("https://w.example/sessions/s1/history").mock(
|
||||
return_value=httpx.Response(201, json={})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
result = await seed_preset_first_message(client, "s1", "mimir")
|
||||
assert result is None
|
||||
assert not route.called
|
||||
|
||||
@respx.mock
|
||||
async def test_feature_absent_swallowed(self) -> None:
|
||||
"""feature_absent_swallowed [error]: 404 hide-existence → None, no raise (INV-001)."""
|
||||
respx.post("https://w.example/sessions/s1/history").mock(
|
||||
return_value=httpx.Response(404, json={"error_code": "session_not_found"})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
result = await seed_preset_first_message(client, "s1", "ratatoskr:sindra")
|
||||
assert result is None
|
||||
|
||||
@respx.mock
|
||||
async def test_session_api_failed_swallowed(self) -> None:
|
||||
"""session_api_failed_swallowed [error]: 409 → None, no raise (INV-001)."""
|
||||
respx.post("https://w.example/sessions/s1/history").mock(
|
||||
return_value=httpx.Response(409, json={"error_code": "generation_active"})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
result = await seed_preset_first_message(client, "s1", "ratatoskr:sindra")
|
||||
assert result is None
|
||||
|
||||
@respx.mock
|
||||
async def test_transport_error_swallowed(self) -> None:
|
||||
"""transport_error_swallowed [error]: httpx.ConnectError → None, no raise (INV-001)."""
|
||||
respx.post("https://w.example/sessions/s1/history").mock(
|
||||
side_effect=httpx.ConnectError("boom")
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
result = await seed_preset_first_message(client, "s1", "ratatoskr:sindra")
|
||||
assert result is None
|
||||
|
||||
@respx.mock
|
||||
async def test_unexpected_exception_swallowed(self) -> None:
|
||||
"""unexpected_exception [error]: write raises ValueError → None (broad never-raise)."""
|
||||
respx.post("https://w.example/sessions/s1/history").mock(
|
||||
side_effect=ValueError("unexpected")
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
result = await seed_preset_first_message(client, "s1", "ratatoskr:sindra")
|
||||
assert result is None
|
||||
|
||||
async def test_cancellation_propagates(self) -> None:
|
||||
"""cancellation_propagates [error]: CancelledError from the write is RE-RAISED."""
|
||||
import ratatoskr.first_message as fm
|
||||
|
||||
async def _cancel(*_a: object, **_k: object) -> None:
|
||||
raise asyncio.CancelledError
|
||||
|
||||
orig = fm.write_authored_history
|
||||
fm.write_authored_history = _cancel # type: ignore[assignment]
|
||||
try:
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(asyncio.CancelledError):
|
||||
await seed_preset_first_message(client, "s1", "ratatoskr:sindra")
|
||||
finally:
|
||||
fm.write_authored_history = orig # type: ignore[assignment]
|
||||
|
||||
@respx.mock
|
||||
async def test_malformed_agent_id_no_http(self) -> None:
|
||||
"""malformed_agent_id [adversarial]: non-str or empty agent_id → None; no HTTP; no raise."""
|
||||
route = respx.post(url__regex=r".*/history$").mock(
|
||||
return_value=httpx.Response(201, json={})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
assert await seed_preset_first_message(client, "s1", 123) is None # type: ignore[arg-type]
|
||||
assert await seed_preset_first_message(client, "s1", "") is None
|
||||
assert not route.called
|
||||
|
||||
@respx.mock
|
||||
async def test_empty_session_id(self) -> None:
|
||||
"""empty_session_id [adversarial]: "" → None (soft guard); no HTTP; no raise."""
|
||||
route = respx.post("https://w.example/sessions/s1/history").mock(
|
||||
return_value=httpx.Response(201, json={})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
result = await seed_preset_first_message(client, "", "ratatoskr:sindra")
|
||||
assert result is None
|
||||
assert not route.called
|
||||
@@ -8,6 +8,7 @@ from ratatoskr.sessions import (
|
||||
AgentInfo,
|
||||
AgentNotAvailable,
|
||||
AgentNotFound,
|
||||
AuthoredHistoryUnavailable,
|
||||
AuthScopeDenied,
|
||||
BifrostBinding,
|
||||
BifrostConsumerKeyMissing,
|
||||
@@ -16,11 +17,22 @@ from ratatoskr.sessions import (
|
||||
PersonaNotConfigured,
|
||||
SessionApiFailed,
|
||||
SessionPage,
|
||||
create_character,
|
||||
create_session,
|
||||
delete_character,
|
||||
endpoint_for_plane,
|
||||
get_capabilities,
|
||||
get_character_state,
|
||||
get_me,
|
||||
get_persona_state,
|
||||
get_session_bifrost,
|
||||
get_session_messages,
|
||||
get_session_tools,
|
||||
list_agents,
|
||||
list_character_models,
|
||||
list_sessions,
|
||||
set_persona_state,
|
||||
write_authored_history,
|
||||
)
|
||||
|
||||
|
||||
@@ -896,3 +908,473 @@ class TestGetPersonaState:
|
||||
with pytest.raises(PersonaNotConfigured) as exc_info:
|
||||
await get_persona_state(client, "domari")
|
||||
assert exc_info.value.agent_id == "domari"
|
||||
|
||||
|
||||
class TestGetMe:
|
||||
"""docs/contracts/issues/2.contract.md FN get_me (slice: capabilities+me)."""
|
||||
|
||||
@respx.mock
|
||||
async def test_happy_authenticated(self) -> None:
|
||||
"""happy_authenticated [happy,tracer]: 200 → parsed identity dict verbatim."""
|
||||
respx.get("https://w.example/me").mock(
|
||||
return_value=httpx.Response(
|
||||
200,
|
||||
json={
|
||||
"user_id": "alice",
|
||||
"scopes": ["conversations.read", "conversations.write"],
|
||||
"tier": "user",
|
||||
"key_id": "a1b2c3d4",
|
||||
"key_label": "alice phone",
|
||||
},
|
||||
)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
me = await get_me(client)
|
||||
assert me["user_id"] == "alice"
|
||||
assert me["tier"] == "user"
|
||||
assert me["key_id"] == "a1b2c3d4"
|
||||
assert me["scopes"] == ["conversations.read", "conversations.write"]
|
||||
|
||||
@respx.mock
|
||||
async def test_anonymous_dev_mode(self) -> None:
|
||||
"""anonymous_dev_mode: 200 anonymous shape → dict with tier=anonymous."""
|
||||
respx.get("https://w.example/me").mock(
|
||||
return_value=httpx.Response(
|
||||
200,
|
||||
json={
|
||||
"user_id": "anonymous",
|
||||
"scopes": ["conversations.read"],
|
||||
"tier": "anonymous",
|
||||
},
|
||||
)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
me = await get_me(client)
|
||||
assert me["tier"] == "anonymous"
|
||||
assert "key_id" not in me # optional fields omitted, not null
|
||||
|
||||
@respx.mock
|
||||
async def test_401_raises_session_api_failed(self) -> None:
|
||||
"""401_raises [error]: bad/absent key → SessionApiFailed(status=401)."""
|
||||
respx.get("https://w.example/me").mock(
|
||||
return_value=httpx.Response(401, json={"detail": "auth_invalid"})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(SessionApiFailed) as exc:
|
||||
await get_me(client)
|
||||
assert exc.value.status == 401
|
||||
|
||||
|
||||
class TestGetCapabilities:
|
||||
"""docs/contracts/issues/2.contract.md FN get_capabilities (slice: capabilities+me)."""
|
||||
|
||||
@respx.mock
|
||||
async def test_happy(self) -> None:
|
||||
"""happy [happy]: 200 → ephemeral_templates dict verbatim."""
|
||||
respx.get("https://w.example/capabilities").mock(
|
||||
return_value=httpx.Response(
|
||||
200,
|
||||
json={
|
||||
"ephemeral_templates": {
|
||||
"echo": {
|
||||
"allowed_models": ["glm5-turbo", "glm4.7"],
|
||||
"default_model": "glm5-turbo",
|
||||
"system_prompt_max_bytes": 32768,
|
||||
}
|
||||
}
|
||||
},
|
||||
)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
caps = await get_capabilities(client)
|
||||
echo = caps["ephemeral_templates"]["echo"]
|
||||
assert echo["default_model"] == "glm5-turbo"
|
||||
assert echo["system_prompt_max_bytes"] == 32768
|
||||
|
||||
@respx.mock
|
||||
async def test_non_200_raises(self) -> None:
|
||||
"""non_200_raises [error]: 500 → SessionApiFailed(status=500)."""
|
||||
respx.get("https://w.example/capabilities").mock(
|
||||
return_value=httpx.Response(500, content=b"boom")
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(SessionApiFailed) as exc:
|
||||
await get_capabilities(client)
|
||||
assert exc.value.status == 500
|
||||
|
||||
|
||||
class TestGetSessionTools:
|
||||
"""docs/contracts/issues/2.contract.md — get_session_tools (GET /sessions/{id}/tools, #183)."""
|
||||
|
||||
@respx.mock
|
||||
async def test_happy(self) -> None:
|
||||
"""happy [happy,tracer]: 200 → merged tool inventory dict verbatim."""
|
||||
respx.get("https://w.example/sessions/s1/tools").mock(
|
||||
return_value=httpx.Response(
|
||||
200,
|
||||
json={
|
||||
"agent_id": "alice:wizard",
|
||||
"builtin_tools": [],
|
||||
"bifrost_tools": [
|
||||
{"name": "bifrost.alice.set_field", "description": "d", "parameters": {}}
|
||||
],
|
||||
},
|
||||
)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
tools = await get_session_tools(client, "s1")
|
||||
assert tools["agent_id"] == "alice:wizard"
|
||||
assert tools["builtin_tools"] == []
|
||||
assert tools["bifrost_tools"][0]["name"] == "bifrost.alice.set_field"
|
||||
|
||||
@respx.mock
|
||||
async def test_cross_owner_404_raises(self) -> None:
|
||||
"""cross_owner_404 [error]: 404 session_not_found → SessionApiFailed(404)."""
|
||||
respx.get("https://w.example/sessions/s1/tools").mock(
|
||||
return_value=httpx.Response(404, json={"error_code": "session_not_found"})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(SessionApiFailed) as exc:
|
||||
await get_session_tools(client, "s1")
|
||||
assert exc.value.status == 404
|
||||
|
||||
@respx.mock
|
||||
async def test_empty_session_id_asserts(self) -> None:
|
||||
"""empty_session_id [adversarial]: '' → AssertionError; no HTTP issued."""
|
||||
route = respx.get("https://w.example/sessions//tools").mock(
|
||||
return_value=httpx.Response(200, json={})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(AssertionError):
|
||||
await get_session_tools(client, "")
|
||||
assert route.call_count == 0
|
||||
|
||||
|
||||
class TestGetSessionBifrost:
|
||||
"""#2 contract — get_session_bifrost (GET /admin/sessions/{id}/bifrost, #176)."""
|
||||
|
||||
@respx.mock
|
||||
async def test_happy_uses_admin_bearer(self) -> None:
|
||||
"""happy [happy,tracer]: 200 → binding dict; request carries the ADMIN bearer (override)."""
|
||||
route = respx.get("https://w.example/admin/sessions/s1/bifrost").mock(
|
||||
return_value=httpx.Response(
|
||||
200,
|
||||
json={
|
||||
"endpoint_url": "https://bifrost.example/mcp",
|
||||
"consumer_id": "alice",
|
||||
"connected": True,
|
||||
"capabilities_granted": ["tools:call", "tools:read"],
|
||||
"tools": [{"name": "bifrost.alice.echo", "description": "echo"}],
|
||||
},
|
||||
)
|
||||
)
|
||||
async with httpx.AsyncClient(
|
||||
base_url="https://w.example",
|
||||
headers={"Authorization": "Bearer consumer-key"},
|
||||
) as client:
|
||||
state = await get_session_bifrost(client, "s1", admin_key="admin-xyz")
|
||||
assert state["connected"] is True
|
||||
assert state["tools"][0]["name"] == "bifrost.alice.echo"
|
||||
# the request overrode the client's default consumer bearer with the admin key
|
||||
assert route.calls[0].request.headers["Authorization"] == "Bearer admin-xyz"
|
||||
|
||||
@respx.mock
|
||||
async def test_403_scope_denied(self) -> None:
|
||||
"""403 [error]: admin key lacks admin.sessions.read → SessionApiFailed(403)."""
|
||||
respx.get("https://w.example/admin/sessions/s1/bifrost").mock(
|
||||
return_value=httpx.Response(403, json={"error_code": "auth_scope_denied"})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(SessionApiFailed) as exc:
|
||||
await get_session_bifrost(client, "s1", admin_key="k")
|
||||
assert exc.value.status == 403
|
||||
|
||||
@respx.mock
|
||||
async def test_404_not_bound(self) -> None:
|
||||
"""404 [error]: session_not_bifrost_bound → SessionApiFailed(404)."""
|
||||
respx.get("https://w.example/admin/sessions/s1/bifrost").mock(
|
||||
return_value=httpx.Response(404, json={"error_code": "session_not_bifrost_bound"})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(SessionApiFailed) as exc:
|
||||
await get_session_bifrost(client, "s1", admin_key="k")
|
||||
assert exc.value.status == 404
|
||||
|
||||
@respx.mock
|
||||
async def test_empty_admin_key_asserts(self) -> None:
|
||||
"""empty_admin_key [adversarial]: '' → AssertionError; no HTTP issued."""
|
||||
route = respx.get("https://w.example/admin/sessions/s1/bifrost").mock(
|
||||
return_value=httpx.Response(200, json={})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(AssertionError):
|
||||
await get_session_bifrost(client, "s1", admin_key="")
|
||||
assert route.call_count == 0
|
||||
|
||||
|
||||
class TestTransientCharacters:
|
||||
"""docs/contracts/issues/2.contract.md — transient-character wrappers (#161)."""
|
||||
|
||||
@respx.mock
|
||||
async def test_list_models(self) -> None:
|
||||
"""list_models [happy,tracer]: 200 → {items:[...]} verbatim."""
|
||||
respx.get("https://w.example/models/available-for-characters").mock(
|
||||
return_value=httpx.Response(200, json={"items": [{"name": "fast", "thinking": False}]})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
models = await list_character_models(client)
|
||||
assert models["items"][0]["name"] == "fast"
|
||||
|
||||
@respx.mock
|
||||
async def test_create_body_and_response(self) -> None:
|
||||
"""create [happy]: body is {character, state}; 201 → {character_id, ttl_expires_at}."""
|
||||
import json as _json
|
||||
|
||||
route = respx.post("https://w.example/characters").mock(
|
||||
return_value=httpx.Response(201, json={"character_id": "char_x", "ttl_expires_at": "t"})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
out = await create_character(client, {"schema_version": "1", "name": "H"})
|
||||
assert out["character_id"] == "char_x"
|
||||
body = _json.loads(route.calls[0].request.content)
|
||||
assert body == {"character": {"schema_version": "1", "name": "H"}, "state": None}
|
||||
|
||||
@respx.mock
|
||||
async def test_get_state(self) -> None:
|
||||
"""get_state [happy]: 200 → live PAD/emotions snapshot."""
|
||||
respx.get("https://w.example/characters/char_x/state").mock(
|
||||
return_value=httpx.Response(200, json={"schema_version": "1", "pad": [0.4, 0.1, -0.2]})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
state = await get_character_state(client, "char_x")
|
||||
assert state["pad"] == [0.4, 0.1, -0.2]
|
||||
|
||||
@respx.mock
|
||||
async def test_delete_204(self) -> None:
|
||||
"""delete [happy]: 204 → None."""
|
||||
respx.delete("https://w.example/characters/char_x").mock(
|
||||
return_value=httpx.Response(204)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
assert await delete_character(client, "char_x") is None
|
||||
|
||||
@respx.mock
|
||||
async def test_create_403_scope(self) -> None:
|
||||
"""create_403 [error]: key lacks character.write → SessionApiFailed(403)."""
|
||||
respx.post("https://w.example/characters").mock(
|
||||
return_value=httpx.Response(403, json={"error_code": "auth_scope_denied"})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(SessionApiFailed) as exc:
|
||||
await create_character(client, {"name": "H"})
|
||||
assert exc.value.status == 403
|
||||
|
||||
|
||||
class TestSetPersonaState:
|
||||
"""#2 contract — set_persona_state (POST /sessions/{id}/persona_state)."""
|
||||
|
||||
@respx.mock
|
||||
async def test_happy_204(self) -> None:
|
||||
"""happy [happy,tracer]: freeform snapshot body; 204 → None."""
|
||||
import json as _json
|
||||
|
||||
route = respx.post("https://w.example/sessions/s1/persona_state").mock(
|
||||
return_value=httpx.Response(204)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
result = await set_persona_state(
|
||||
client, "s1", {"pad": {"pleasure": 0.4, "arousal": 0.1, "dominance": -0.2}}
|
||||
)
|
||||
assert result is None
|
||||
assert _json.loads(route.calls[0].request.content) == {
|
||||
"pad": {"pleasure": 0.4, "arousal": 0.1, "dominance": -0.2}
|
||||
}
|
||||
|
||||
@respx.mock
|
||||
async def test_non_204_raises(self) -> None:
|
||||
"""non_204 [error]: 422 (bad snapshot shape) → SessionApiFailed(422)."""
|
||||
respx.post("https://w.example/sessions/s1/persona_state").mock(
|
||||
return_value=httpx.Response(422, json={"error_code": "validation_failed"})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(SessionApiFailed) as exc:
|
||||
await set_persona_state(client, "s1", {"pad": [1, 2, 3]})
|
||||
assert exc.value.status == 422
|
||||
|
||||
|
||||
_AUTHORED_ACK = {
|
||||
"author": "assistant",
|
||||
"content_chars": 5,
|
||||
"injected_at": "2026-07-06T12:00:00+00:00",
|
||||
"phase": "seeded",
|
||||
"seq": 0,
|
||||
"session_id": "s1",
|
||||
"turn_id": "t1",
|
||||
}
|
||||
|
||||
|
||||
class TestWriteAuthoredHistory:
|
||||
"""write_authored_history — #347 POST /sessions/{id}/history (contract #2 amendment)."""
|
||||
|
||||
@respx.mock
|
||||
async def test_happy_fresh_201(self) -> None:
|
||||
"""happy_fresh_201 [happy,tracer]: 201 → ack verbatim; minimal body."""
|
||||
import json as _json
|
||||
|
||||
route = respx.post("https://w.example/sessions/s1/history").mock(
|
||||
return_value=httpx.Response(201, json=_AUTHORED_ACK)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
result = await write_authored_history(
|
||||
client, "s1", content="hello", idempotency_key="k1"
|
||||
)
|
||||
assert result == _AUTHORED_ACK
|
||||
assert _json.loads(route.calls[0].request.content) == {
|
||||
"author": "assistant",
|
||||
"content": "hello",
|
||||
"idempotency_key": "k1",
|
||||
}
|
||||
|
||||
@respx.mock
|
||||
async def test_happy_replay_200(self) -> None:
|
||||
"""happy_replay_200 [happy]: 200 replay (byte-identical body) → dict verbatim."""
|
||||
respx.post("https://w.example/sessions/s1/history").mock(
|
||||
return_value=httpx.Response(200, json=_AUTHORED_ACK)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
result = await write_authored_history(
|
||||
client, "s1", content="hello", idempotency_key="k1"
|
||||
)
|
||||
assert result == _AUTHORED_ACK
|
||||
|
||||
@respx.mock
|
||||
async def test_body_includes_effects(self) -> None:
|
||||
"""body_includes_effects [trace]: effects + claimed_original_at appear iff non-None."""
|
||||
import json as _json
|
||||
|
||||
route = respx.post("https://w.example/sessions/s1/history").mock(
|
||||
return_value=httpx.Response(201, json=_AUTHORED_ACK)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
await write_authored_history(
|
||||
client,
|
||||
"s1",
|
||||
content="hi",
|
||||
idempotency_key="k1",
|
||||
effects="none",
|
||||
claimed_original_at="2020-01-01T00:00:00Z",
|
||||
)
|
||||
assert _json.loads(route.calls[0].request.content) == {
|
||||
"author": "assistant",
|
||||
"content": "hi",
|
||||
"idempotency_key": "k1",
|
||||
"effects": "none",
|
||||
"claimed_original_at": "2020-01-01T00:00:00Z",
|
||||
}
|
||||
|
||||
@respx.mock
|
||||
async def test_hide_existence_404(self) -> None:
|
||||
"""hide_existence_404 [error]: 404 → AuthoredHistoryUnavailable (NOT SessionApiFailed)."""
|
||||
respx.post("https://w.example/sessions/s1/history").mock(
|
||||
return_value=httpx.Response(404, json={"error_code": "session_not_found"})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(AuthoredHistoryUnavailable) as exc:
|
||||
await write_authored_history(client, "s1", content="hi", idempotency_key="k1")
|
||||
assert exc.value.session_id == "s1"
|
||||
|
||||
@respx.mock
|
||||
async def test_generation_active_409(self) -> None:
|
||||
"""generation_active_409 [error]: 409 → SessionApiFailed(409)."""
|
||||
respx.post("https://w.example/sessions/s1/history").mock(
|
||||
return_value=httpx.Response(409, json={"error_code": "generation_active"})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(SessionApiFailed) as exc:
|
||||
await write_authored_history(client, "s1", content="hi", idempotency_key="k1")
|
||||
assert exc.value.status == 409
|
||||
|
||||
@respx.mock
|
||||
async def test_content_too_long_422(self) -> None:
|
||||
"""content_too_long_422 [error]: 422 → SessionApiFailed(422)."""
|
||||
respx.post("https://w.example/sessions/s1/history").mock(
|
||||
return_value=httpx.Response(422, json={"error_code": "content_too_long"})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(SessionApiFailed) as exc:
|
||||
await write_authored_history(client, "s1", content="x", idempotency_key="k1")
|
||||
assert exc.value.status == 422
|
||||
|
||||
@respx.mock
|
||||
async def test_empty_content(self) -> None:
|
||||
"""empty_content [adversarial]: content="" → AssertionError; no HTTP issued."""
|
||||
route = respx.post("https://w.example/sessions/s1/history").mock(
|
||||
return_value=httpx.Response(201, json=_AUTHORED_ACK)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(AssertionError):
|
||||
await write_authored_history(client, "s1", content="", idempotency_key="k1")
|
||||
assert not route.called
|
||||
|
||||
@respx.mock
|
||||
async def test_empty_idempotency_key(self) -> None:
|
||||
"""empty_idempotency_key [adversarial]: key="" → AssertionError; no HTTP issued."""
|
||||
route = respx.post("https://w.example/sessions/s1/history").mock(
|
||||
return_value=httpx.Response(201, json=_AUTHORED_ACK)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(AssertionError):
|
||||
await write_authored_history(client, "s1", content="hi", idempotency_key="")
|
||||
assert not route.called
|
||||
|
||||
@respx.mock
|
||||
async def test_empty_session_id(self) -> None:
|
||||
"""empty_session_id [adversarial]: session_id="" → AssertionError; no HTTP issued."""
|
||||
route = respx.post("https://w.example/sessions/s1/history").mock(
|
||||
return_value=httpx.Response(201, json=_AUTHORED_ACK)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(AssertionError):
|
||||
await write_authored_history(client, "", content="hi", idempotency_key="k1")
|
||||
assert not route.called
|
||||
|
||||
|
||||
class TestGetSessionMessages:
|
||||
"""#2 contract (amendment 2026-07-06) — get_session_messages (GET /sessions/{id}/messages)."""
|
||||
|
||||
@respx.mock
|
||||
async def test_happy(self) -> None:
|
||||
"""happy [happy,tracer]: 200 {session_id, items, next_cursor} → dict verbatim."""
|
||||
payload = {
|
||||
"session_id": "s1",
|
||||
"items": [{"seq": 0, "role": "assistant", "content": "hello there"}],
|
||||
"next_cursor": None,
|
||||
}
|
||||
respx.get("https://w.example/sessions/s1/messages").mock(
|
||||
return_value=httpx.Response(200, json=payload)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
result = await get_session_messages(client, "s1")
|
||||
assert result == payload
|
||||
|
||||
@respx.mock
|
||||
async def test_not_found_404(self) -> None:
|
||||
"""not_found_404 [error]: 404 → SessionApiFailed(404)."""
|
||||
respx.get("https://w.example/sessions/s1/messages").mock(
|
||||
return_value=httpx.Response(404, json={"error_code": "session_not_found"})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(SessionApiFailed) as exc:
|
||||
await get_session_messages(client, "s1")
|
||||
assert exc.value.status == 404
|
||||
|
||||
@respx.mock
|
||||
async def test_empty_session_id(self) -> None:
|
||||
"""empty_session_id [adversarial]: "" → AssertionError; no HTTP issued."""
|
||||
route = respx.get("https://w.example/sessions/s1/messages").mock(
|
||||
return_value=httpx.Response(200, json={})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(AssertionError):
|
||||
await get_session_messages(client, "")
|
||||
assert not route.called
|
||||
|
||||
@@ -5,6 +5,7 @@ import pytest
|
||||
import respx
|
||||
|
||||
from ratatoskr.sse_client import (
|
||||
AdminEvent,
|
||||
AffectUpdate,
|
||||
AgentNotAvailable,
|
||||
AwaitingLlmFirstToken,
|
||||
@@ -27,6 +28,7 @@ from ratatoskr.sse_client import (
|
||||
_parse_sse_id,
|
||||
cancel_turn,
|
||||
reconnect_turn,
|
||||
stream_admin_events,
|
||||
stream_turn,
|
||||
stream_turn_resilient,
|
||||
)
|
||||
@@ -1261,3 +1263,73 @@ class TestStreamTurnResilient:
|
||||
collected.append(e)
|
||||
assert [e.sse_id for e in collected] == [SseId(42, 1)] # type: ignore[attr-defined]
|
||||
assert route.call_count == 2
|
||||
|
||||
|
||||
class TestStreamAdminEvents:
|
||||
"""docs/conversation-api-spec.md § Admin Event Stream — stream_admin_events (#11)."""
|
||||
|
||||
@respx.mock
|
||||
async def test_happy_multi_event_admin_bearer(self) -> None:
|
||||
"""happy [happy,tracer]: yields AdminEvent envelopes; request uses the ADMIN bearer."""
|
||||
env1 = {
|
||||
"id": 41, "type": "session.created", "timestamp": "2026-05-06T10:00:00.000Z",
|
||||
"data": {"session_id": "s1", "agent_id": "mimir", "user_id": None},
|
||||
}
|
||||
env2 = {
|
||||
"id": 42, "type": "turn.started", "timestamp": "2026-05-06T10:00:01.000Z",
|
||||
"data": {"session_id": "s1", "turn_id": 7, "agent_id": "mimir", "user_id": None},
|
||||
}
|
||||
stream = _sse_chunk("41", env1) + _sse_chunk("42", env2)
|
||||
route = respx.get("https://w.example/admin/events").mock(
|
||||
return_value=httpx.Response(
|
||||
200, headers={"content-type": "text/event-stream"}, content=stream
|
||||
)
|
||||
)
|
||||
async with httpx.AsyncClient(
|
||||
base_url="https://w.example", headers={"Authorization": "Bearer consumer"}
|
||||
) as client:
|
||||
events = [e async for e in stream_admin_events(client, admin_key="admin-xyz")]
|
||||
assert [e.type for e in events] == ["session.created", "turn.started"]
|
||||
assert isinstance(events[0], AdminEvent)
|
||||
assert events[0].id == 41
|
||||
assert events[1].data["turn_id"] == 7
|
||||
assert route.calls[0].request.headers["Authorization"] == "Bearer admin-xyz"
|
||||
|
||||
@respx.mock
|
||||
async def test_last_event_id_header(self) -> None:
|
||||
"""last_event_id_header [trace]: empty stream → []; Last-Event-ID header sent."""
|
||||
route = respx.get("https://w.example/admin/events").mock(
|
||||
return_value=httpx.Response(
|
||||
200, headers={"content-type": "text/event-stream"}, content=b""
|
||||
)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
events = [e async for e in stream_admin_events(client, admin_key="k", last_event_id=99)]
|
||||
assert events == []
|
||||
assert route.calls[0].request.headers["Last-Event-ID"] == "99"
|
||||
|
||||
@respx.mock
|
||||
async def test_403_scope_denied(self) -> None:
|
||||
"""403 [error]: key lacks admin.events.read → SseConnectFailed(403)."""
|
||||
respx.get("https://w.example/admin/events").mock(
|
||||
return_value=httpx.Response(403, json={"error_code": "auth_scope_denied"})
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(SseConnectFailed) as exc:
|
||||
_ = [e async for e in stream_admin_events(client, admin_key="k")]
|
||||
assert exc.value.status == 403
|
||||
|
||||
@respx.mock
|
||||
async def test_skips_malformed_frame(self) -> None:
|
||||
"""skips_malformed [adversarial]: a bad-JSON frame is skipped, not fatal."""
|
||||
good = _sse_chunk("41", {"id": 41, "type": "session.created", "data": {"session_id": "s1"}})
|
||||
bad = b"id: 42\ndata: not-json\n\n"
|
||||
good2 = _sse_chunk("43", {"id": 43, "type": "session.deleted", "data": {"session_id": "s1"}})
|
||||
respx.get("https://w.example/admin/events").mock(
|
||||
return_value=httpx.Response(
|
||||
200, headers={"content-type": "text/event-stream"}, content=good + bad + good2
|
||||
)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
events = [e async for e in stream_admin_events(client, admin_key="k")]
|
||||
assert [e.type for e in events] == ["session.created", "session.deleted"]
|
||||
|
||||
@@ -2922,6 +2922,10 @@ class TestTuiBifrostBind:
|
||||
},
|
||||
)
|
||||
)
|
||||
# sindra is a preset agent → the TUI create path now auto-seeds a #347 first-message.
|
||||
respx.post("https://w.example/sessions/s-bound/history").mock(
|
||||
return_value=httpx.Response(201, json={})
|
||||
)
|
||||
|
||||
async def fake_run_async(self) -> int:
|
||||
return 0
|
||||
@@ -2945,3 +2949,495 @@ class TestTuiBifrostBind:
|
||||
err = capsys.readouterr().err
|
||||
assert "bifrost: status=bound" in err
|
||||
assert "plane=memory" in err
|
||||
|
||||
|
||||
class TestSessionPickerApp:
|
||||
"""docs/contracts/issues/6.contract.md FN SessionPickerApp (amendment slice b2)."""
|
||||
|
||||
@staticmethod
|
||||
def _two():
|
||||
from ratatoskr.sessions import SessionInfo
|
||||
|
||||
return [
|
||||
SessionInfo(
|
||||
session_id="s-first-0001", agent_id="mimir", created_at="t0",
|
||||
last_active="t1", metadata={}, message_count=3, name=None,
|
||||
archived=False, tags=[],
|
||||
),
|
||||
SessionInfo(
|
||||
session_id="s-second-002", agent_id="echo", created_at="t0",
|
||||
last_active="t2", metadata={}, message_count=None, name="probe",
|
||||
archived=False, tags=[],
|
||||
),
|
||||
]
|
||||
|
||||
def test_pick_returns_session_id(self) -> None:
|
||||
"""pick_returns_session_id [happy,tracer]: idx 1 + Enter → exit value == that session_id."""
|
||||
from ratatoskr.tui import SessionPickerApp
|
||||
|
||||
app = SessionPickerApp(self._two())
|
||||
|
||||
async def drive() -> str | None:
|
||||
async with app.run_test() as pilot:
|
||||
from textual.widgets import ListView
|
||||
|
||||
lv = app.query_one("#session-list", ListView)
|
||||
lv.index = 1
|
||||
await pilot.pause()
|
||||
await pilot.press("enter")
|
||||
await pilot.pause()
|
||||
return app.return_value
|
||||
|
||||
import asyncio
|
||||
|
||||
assert asyncio.run(drive()) == "s-second-002"
|
||||
|
||||
def test_esc_returns_none(self) -> None:
|
||||
"""esc_returns_none [happy]: Esc → exit value is None (dismiss, resume nothing)."""
|
||||
from ratatoskr.tui import SessionPickerApp
|
||||
|
||||
app = SessionPickerApp(self._two())
|
||||
|
||||
async def drive() -> str | None:
|
||||
async with app.run_test() as pilot:
|
||||
await pilot.press("escape")
|
||||
await pilot.pause()
|
||||
return app.return_value
|
||||
|
||||
import asyncio
|
||||
|
||||
assert asyncio.run(drive()) is None
|
||||
|
||||
def test_ctrl_d_returns_none(self) -> None:
|
||||
"""ctrl_d_returns_none [adversarial]: Ctrl-D → None."""
|
||||
from ratatoskr.tui import SessionPickerApp
|
||||
|
||||
app = SessionPickerApp(self._two())
|
||||
|
||||
async def drive() -> str | None:
|
||||
async with app.run_test() as pilot:
|
||||
await pilot.press("ctrl+d")
|
||||
await pilot.pause()
|
||||
return app.return_value
|
||||
|
||||
import asyncio
|
||||
|
||||
assert asyncio.run(drive()) is None
|
||||
|
||||
|
||||
class TestBareSessionPicker:
|
||||
"""docs/contracts/issues/6.contract.md amendment (slice b2): _resolve_then_run bare mode."""
|
||||
|
||||
@staticmethod
|
||||
def _bare_args() -> ParsedArgs:
|
||||
return ParsedArgs(
|
||||
send_content=None, session_id=None, new=False, agent_id=None,
|
||||
api_key="k", server_url="https://w.example", raw=False,
|
||||
end_user_id=None, bifrost=None, bifrost_plane=None, consumer_key=None,
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _sess(sid: str, agent: str = "mimir"):
|
||||
from ratatoskr.sessions import SessionInfo
|
||||
|
||||
return SessionInfo(
|
||||
session_id=sid, agent_id=agent, created_at="t0", last_active="t1",
|
||||
metadata={}, message_count=1, name=None, archived=False, tags=[],
|
||||
)
|
||||
|
||||
def test_bare_zero_sessions_errors(
|
||||
self, monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str]
|
||||
) -> None:
|
||||
"""bare_zero_sessions_errors [error]: 0 sessions → exit 14 [no_sessions]; App not opened."""
|
||||
import ratatoskr.tui as tui_mod
|
||||
from ratatoskr.sessions import SessionPage
|
||||
|
||||
async def fake_list(client, **kw):
|
||||
return SessionPage(items=[], next_cursor=None)
|
||||
|
||||
monkeypatch.setattr(tui_mod, "list_sessions", fake_list)
|
||||
opened: list[int] = []
|
||||
|
||||
async def spy(self, *a, **k):
|
||||
opened.append(1)
|
||||
return 0
|
||||
|
||||
monkeypatch.setattr(RatatoskrApp, "run_async", spy)
|
||||
rc = run_tui(self._bare_args())
|
||||
assert rc == 14
|
||||
assert "[no_sessions]" in capsys.readouterr().err
|
||||
assert not opened
|
||||
|
||||
def test_bare_one_session_auto_resumes(self, monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
"""bare_one_session_auto_resumes: exactly 1 → auto-resume, no picker (§4 >1 rule)."""
|
||||
import ratatoskr.tui as tui_mod
|
||||
from ratatoskr.sessions import SessionPage
|
||||
from ratatoskr.tui import SessionPickerApp
|
||||
|
||||
async def fake_list(client, **kw):
|
||||
return SessionPage(items=[self._sess("s-solo")], next_cursor=None)
|
||||
|
||||
monkeypatch.setattr(tui_mod, "list_sessions", fake_list)
|
||||
picker_used: list[int] = []
|
||||
|
||||
async def spy_picker(self, *a, **k):
|
||||
picker_used.append(1)
|
||||
return None
|
||||
|
||||
monkeypatch.setattr(SessionPickerApp, "run_async", spy_picker)
|
||||
snap: dict = {}
|
||||
|
||||
async def cap(self, *a, **k):
|
||||
snap["sid"] = self.session_id
|
||||
return 0
|
||||
|
||||
monkeypatch.setattr(RatatoskrApp, "run_async", cap)
|
||||
rc = run_tui(self._bare_args())
|
||||
assert rc == 0
|
||||
assert snap["sid"] == "s-solo"
|
||||
assert not picker_used
|
||||
|
||||
def test_bare_multi_opens_picker(self, monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
"""bare_multi_opens_picker [scenario,tracer]: >1 → picker; its choice resumes."""
|
||||
import ratatoskr.tui as tui_mod
|
||||
from ratatoskr.sessions import SessionPage
|
||||
from ratatoskr.tui import SessionPickerApp
|
||||
|
||||
async def fake_list(client, **kw):
|
||||
return SessionPage(items=[self._sess("s-a"), self._sess("s-b")], next_cursor=None)
|
||||
|
||||
monkeypatch.setattr(tui_mod, "list_sessions", fake_list)
|
||||
|
||||
async def pick_b(self, *a, **k):
|
||||
return "s-b"
|
||||
|
||||
monkeypatch.setattr(SessionPickerApp, "run_async", pick_b)
|
||||
snap: dict = {}
|
||||
|
||||
async def cap(self, *a, **k):
|
||||
snap["sid"] = self.session_id
|
||||
return 0
|
||||
|
||||
monkeypatch.setattr(RatatoskrApp, "run_async", cap)
|
||||
rc = run_tui(self._bare_args())
|
||||
assert rc == 0
|
||||
assert snap["sid"] == "s-b"
|
||||
|
||||
def test_bare_picker_dismiss_exits_zero(self, monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
"""bare_picker_dismiss_exits_zero [scenario]: picker None → exit 0; App not opened."""
|
||||
import ratatoskr.tui as tui_mod
|
||||
from ratatoskr.sessions import SessionPage
|
||||
from ratatoskr.tui import SessionPickerApp
|
||||
|
||||
async def fake_list(client, **kw):
|
||||
return SessionPage(items=[self._sess("s-a"), self._sess("s-b")], next_cursor=None)
|
||||
|
||||
monkeypatch.setattr(tui_mod, "list_sessions", fake_list)
|
||||
|
||||
async def pick_none(self, *a, **k):
|
||||
return None
|
||||
|
||||
monkeypatch.setattr(SessionPickerApp, "run_async", pick_none)
|
||||
opened: list[int] = []
|
||||
|
||||
async def spy(self, *a, **k):
|
||||
opened.append(1)
|
||||
return 0
|
||||
|
||||
monkeypatch.setattr(RatatoskrApp, "run_async", spy)
|
||||
rc = run_tui(self._bare_args())
|
||||
assert rc == 0
|
||||
assert not opened
|
||||
|
||||
def test_bare_list_sessions_api_failure(
|
||||
self, monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str]
|
||||
) -> None:
|
||||
"""bare_list_sessions_api_failure [error]: list_sessions 500 → exit 20; App not opened."""
|
||||
import ratatoskr.tui as tui_mod
|
||||
from ratatoskr.sessions import SessionApiFailed
|
||||
|
||||
async def fake_list(client, **kw):
|
||||
raise SessionApiFailed(status=500, body=b"boom")
|
||||
|
||||
monkeypatch.setattr(tui_mod, "list_sessions", fake_list)
|
||||
opened: list[int] = []
|
||||
|
||||
async def spy(self, *a, **k):
|
||||
opened.append(1)
|
||||
return 0
|
||||
|
||||
monkeypatch.setattr(RatatoskrApp, "run_async", spy)
|
||||
rc = run_tui(self._bare_args())
|
||||
assert rc == 20
|
||||
assert "[session_api_failed]" in capsys.readouterr().err
|
||||
assert not opened
|
||||
|
||||
|
||||
class TestSessionToolsHydration:
|
||||
"""get_session_tools + the #183 Tools-pane inventory hydrate (GET /sessions/{id}/tools)."""
|
||||
|
||||
def test_format_tool_inventory(self) -> None:
|
||||
"""format_tool_inventory [unit]: header + builtin + bifrost lines."""
|
||||
from ratatoskr.tui import _format_tool_inventory
|
||||
|
||||
lines = _format_tool_inventory(
|
||||
{
|
||||
"agent_id": "alice:wizard",
|
||||
"builtin_tools": [],
|
||||
"bifrost_tools": [{"name": "bifrost.x"}, {"name": "bifrost.y"}],
|
||||
}
|
||||
)
|
||||
joined = "\n".join(lines)
|
||||
assert "agent=alice:wizard" in joined
|
||||
assert "builtin=0 bifrost=2" in joined
|
||||
assert "builtin: (none)" in joined
|
||||
assert "bifrost.x, bifrost.y" in joined
|
||||
|
||||
async def test_hydrate_writes_inventory_and_audits(
|
||||
self, monkeypatch: pytest.MonkeyPatch
|
||||
) -> None:
|
||||
"""hydrate_writes_inventory [scenario,tracer]: 200 → inventory in Tools pane + audit."""
|
||||
import ratatoskr.tui as tui_mod
|
||||
|
||||
writes = _spy_writes(monkeypatch)
|
||||
|
||||
async def fake_tools(client, session_id):
|
||||
return {
|
||||
"agent_id": "alice:wizard",
|
||||
"builtin_tools": [],
|
||||
"bifrost_tools": [{"name": "bifrost.set_field"}],
|
||||
}
|
||||
|
||||
monkeypatch.setattr(tui_mod, "get_session_tools", fake_tools)
|
||||
app = _resolved_app(_args_existing(session_id="s-tools-01"))
|
||||
async with app.run_test() as pilot:
|
||||
await pilot.pause()
|
||||
await app._hydrate_session_tools()
|
||||
await pilot.pause()
|
||||
joined = " ".join(_text_of(w) for w in writes)
|
||||
assert "session tool inventory" in joined
|
||||
assert "bifrost.set_field" in joined
|
||||
assert "session_tools_hydrated" in joined # audit line landed
|
||||
|
||||
async def test_hydrate_failure_audits_no_crash(
|
||||
self, monkeypatch: pytest.MonkeyPatch
|
||||
) -> None:
|
||||
"""hydrate_failure [error]: get_session_tools raises → failure audit; no crash."""
|
||||
import ratatoskr.tui as tui_mod
|
||||
from ratatoskr.sessions import SessionApiFailed
|
||||
|
||||
writes = _spy_writes(monkeypatch)
|
||||
|
||||
async def boom(client, session_id):
|
||||
raise SessionApiFailed(status=404, body=b"session_not_found")
|
||||
|
||||
monkeypatch.setattr(tui_mod, "get_session_tools", boom)
|
||||
app = _resolved_app(_args_existing(session_id="s-tools-02"))
|
||||
async with app.run_test() as pilot:
|
||||
await pilot.pause()
|
||||
await app._hydrate_session_tools()
|
||||
await pilot.pause()
|
||||
joined = " ".join(_text_of(w) for w in writes)
|
||||
assert "session_tools_hydration_failed" in joined
|
||||
|
||||
|
||||
class TestBifrostStateHydration:
|
||||
"""get_session_bifrost + the #176 BifrostState pane (GET /admin/sessions/{id}/bifrost)."""
|
||||
|
||||
@staticmethod
|
||||
def _mute_tools(monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
"""Neutralize the on_mount Tools-pane worker so it makes no real call."""
|
||||
import ratatoskr.tui as tui_mod
|
||||
|
||||
async def noop(client, session_id):
|
||||
return {"agent_id": "x", "builtin_tools": [], "bifrost_tools": []}
|
||||
|
||||
monkeypatch.setattr(tui_mod, "get_session_tools", noop)
|
||||
|
||||
def test_format_bifrost_state(self) -> None:
|
||||
"""format_bifrost_state [unit]: connected / endpoint / caps / tools lines."""
|
||||
from ratatoskr.tui import _format_bifrost_state
|
||||
|
||||
lines = _format_bifrost_state(
|
||||
{
|
||||
"endpoint_url": "https://b/mcp",
|
||||
"consumer_id": "alice",
|
||||
"connected": True,
|
||||
"capabilities_granted": ["tools:call", "tools:read"],
|
||||
"tools": [{"name": "bifrost.echo"}],
|
||||
}
|
||||
)
|
||||
joined = "\n".join(lines)
|
||||
assert "connected=True" in joined
|
||||
assert "consumer=alice" in joined
|
||||
assert "https://b/mcp" in joined
|
||||
assert "tools:call, tools:read" in joined
|
||||
assert "bifrost.echo" in joined
|
||||
|
||||
async def test_hydrate_no_admin_key(self, monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
"""hydrate_no_admin_key [scenario]: admin_key None → 'not configured' + skip audit."""
|
||||
self._mute_tools(monkeypatch)
|
||||
writes = _spy_writes(monkeypatch)
|
||||
app = _resolved_app(_args_existing(session_id="s-bf-1")) # admin_key defaults None
|
||||
async with app.run_test() as pilot:
|
||||
await pilot.pause()
|
||||
await app._hydrate_bifrost_state()
|
||||
await pilot.pause()
|
||||
joined = " ".join(_text_of(w) for w in writes)
|
||||
assert "admin key not configured" in joined
|
||||
assert "bifrost_state_skipped" in joined
|
||||
|
||||
async def test_hydrate_success(self, monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
"""hydrate_success [scenario,tracer]: 200 → binding in BifrostState pane + audit."""
|
||||
import ratatoskr.tui as tui_mod
|
||||
|
||||
self._mute_tools(monkeypatch)
|
||||
writes = _spy_writes(monkeypatch)
|
||||
|
||||
async def fake_bifrost(client, session_id, *, admin_key):
|
||||
return {
|
||||
"endpoint_url": "https://b/mcp",
|
||||
"consumer_id": "alice",
|
||||
"connected": True,
|
||||
"capabilities_granted": ["tools:call"],
|
||||
"tools": [{"name": "bifrost.echo"}],
|
||||
}
|
||||
|
||||
monkeypatch.setattr(tui_mod, "get_session_bifrost", fake_bifrost)
|
||||
app = _resolved_app(_args_existing(session_id="s-bf-2", admin_key="ak"))
|
||||
async with app.run_test() as pilot:
|
||||
await pilot.pause()
|
||||
await app._hydrate_bifrost_state()
|
||||
await pilot.pause()
|
||||
joined = " ".join(_text_of(w) for w in writes)
|
||||
assert "bifrost binding" in joined
|
||||
assert "bifrost.echo" in joined
|
||||
assert "bifrost_state_hydrated" in joined
|
||||
|
||||
async def test_hydrate_404_not_bound(self, monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
"""hydrate_404_not_bound [error]: 404 → 'not bound to Bifrost' + audit; no crash."""
|
||||
import ratatoskr.tui as tui_mod
|
||||
from ratatoskr.sessions import SessionApiFailed
|
||||
|
||||
self._mute_tools(monkeypatch)
|
||||
writes = _spy_writes(monkeypatch)
|
||||
|
||||
async def not_bound(client, session_id, *, admin_key):
|
||||
raise SessionApiFailed(status=404, body=b"session_not_bifrost_bound")
|
||||
|
||||
monkeypatch.setattr(tui_mod, "get_session_bifrost", not_bound)
|
||||
app = _resolved_app(_args_existing(session_id="s-bf-3", admin_key="ak"))
|
||||
async with app.run_test() as pilot:
|
||||
await pilot.pause()
|
||||
await app._hydrate_bifrost_state()
|
||||
await pilot.pause()
|
||||
joined = " ".join(_text_of(w) for w in writes)
|
||||
assert "not bound to Bifrost" in joined
|
||||
assert "bifrost_state_unavailable" in joined
|
||||
|
||||
|
||||
class TestAdminEventsStream:
|
||||
"""stream_admin_events + the #11 AdminEvents pane (GET /admin/events, session-filtered)."""
|
||||
|
||||
@staticmethod
|
||||
def _mute_hydrates(monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
"""Neutralize the other on_mount workers (tools + bifrost) — no real calls."""
|
||||
import ratatoskr.tui as tui_mod
|
||||
from ratatoskr.sessions import SessionApiFailed
|
||||
|
||||
async def noop_tools(client, session_id):
|
||||
return {"agent_id": "x", "builtin_tools": [], "bifrost_tools": []}
|
||||
|
||||
async def noop_bifrost(client, session_id, *, admin_key):
|
||||
raise SessionApiFailed(status=404, body=b"nb")
|
||||
|
||||
monkeypatch.setattr(tui_mod, "get_session_tools", noop_tools)
|
||||
monkeypatch.setattr(tui_mod, "get_session_bifrost", noop_bifrost)
|
||||
|
||||
def test_format_admin_event(self) -> None:
|
||||
"""format_admin_event [unit]: HH:MM:SS + type + fields; session_id dropped."""
|
||||
from ratatoskr.sse_client import AdminEvent
|
||||
from ratatoskr.tui import _format_admin_event
|
||||
|
||||
line = _format_admin_event(
|
||||
AdminEvent(
|
||||
42, "turn.completed", "2026-05-06T10:00:05.000Z",
|
||||
{"session_id": "s1", "turn_id": 7, "duration_ms": 1200, "phase": "succeeded"},
|
||||
)
|
||||
)
|
||||
assert "turn.completed" in line
|
||||
assert "[10:00:05]" in line
|
||||
assert "turn_id=7" in line
|
||||
assert "session_id" not in line # dropped — pane is already session-scoped
|
||||
|
||||
def test_admin_event_matches_filter(self) -> None:
|
||||
"""admin_event_matches [unit]: active-session + non-heartbeat system.* pass (§6)."""
|
||||
from ratatoskr.sse_client import AdminEvent
|
||||
|
||||
E = AdminEvent
|
||||
app = _resolved_app(_args_existing(session_id="s-match"))
|
||||
assert app._admin_event_matches(E(1, "session.created", "t", {"session_id": "s-match"}))
|
||||
assert not app._admin_event_matches(E(2, "turn.started", "t", {"session_id": "other"}))
|
||||
assert not app._admin_event_matches(E(0, "system.heartbeat", "t", {}))
|
||||
assert app._admin_event_matches(E(3, "system.events_dropped", "t", {"count": 5}))
|
||||
|
||||
async def test_stream_writes_filtered_events(self, monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
"""stream_filtered [scenario,tracer]: only active-session + non-heartbeat lines land."""
|
||||
import ratatoskr.tui as tui_mod
|
||||
from ratatoskr.sse_client import AdminEvent
|
||||
|
||||
self._mute_hydrates(monkeypatch)
|
||||
writes = _spy_writes(monkeypatch)
|
||||
|
||||
async def fake_stream(client, *, admin_key, last_event_id=None):
|
||||
yield AdminEvent(41, "session.created", "t", {"session_id": "s-ae-2"})
|
||||
yield AdminEvent(0, "system.heartbeat", "t", {}) # filtered (noise)
|
||||
yield AdminEvent(42, "turn.started", "t", {"session_id": "other"}) # diff session
|
||||
yield AdminEvent(43, "session.deleted", "t", {"session_id": "s-ae-2"})
|
||||
|
||||
monkeypatch.setattr(tui_mod, "stream_admin_events", fake_stream)
|
||||
app = _resolved_app(_args_existing(session_id="s-ae-2", admin_key="ak"))
|
||||
async with app.run_test() as pilot:
|
||||
await pilot.pause()
|
||||
await app._stream_admin_events()
|
||||
await pilot.pause()
|
||||
joined = " ".join(_text_of(w) for w in writes)
|
||||
assert "session.created" in joined
|
||||
assert "session.deleted" in joined
|
||||
assert "system.heartbeat" not in joined
|
||||
assert "turn.started" not in joined # different session → filtered
|
||||
|
||||
async def test_stream_no_admin_key(self, monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
"""stream_no_admin_key [scenario]: admin_key None → 'not configured' + skip audit."""
|
||||
self._mute_hydrates(monkeypatch)
|
||||
writes = _spy_writes(monkeypatch)
|
||||
app = _resolved_app(_args_existing(session_id="s-ae-3")) # admin_key None
|
||||
async with app.run_test() as pilot:
|
||||
await pilot.pause()
|
||||
await app._stream_admin_events()
|
||||
await pilot.pause()
|
||||
joined = " ".join(_text_of(w) for w in writes)
|
||||
assert "admin key not configured" in joined
|
||||
assert "admin_events_skipped" in joined
|
||||
|
||||
async def test_stream_403_unavailable(self, monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
"""stream_403 [error]: 403 scope-denied → 'unavailable' + audit; no crash."""
|
||||
import ratatoskr.tui as tui_mod
|
||||
from ratatoskr.sse_client import SseConnectFailed
|
||||
|
||||
self._mute_hydrates(monkeypatch)
|
||||
writes = _spy_writes(monkeypatch)
|
||||
|
||||
async def denied(client, *, admin_key, last_event_id=None):
|
||||
raise SseConnectFailed(status=403, body=b"auth_scope_denied")
|
||||
yield # unreachable — makes this an async generator
|
||||
|
||||
monkeypatch.setattr(tui_mod, "stream_admin_events", denied)
|
||||
app = _resolved_app(_args_existing(session_id="s-ae-4", admin_key="ak"))
|
||||
async with app.run_test() as pilot:
|
||||
await pilot.pause()
|
||||
await app._stream_admin_events()
|
||||
await pilot.pause()
|
||||
joined = " ".join(_text_of(w) for w in writes)
|
||||
assert "admin events unavailable: HTTP 403" in joined
|
||||
assert "admin_events_unavailable" in joined
|
||||
|
||||
+206
-1
@@ -175,6 +175,62 @@ class TestCreateSessionEndpoint:
|
||||
resp = TestClient(app).post("/api/sessions", json={})
|
||||
assert resp.status_code == 400
|
||||
|
||||
@respx.mock
|
||||
def test_preset_agent_auto_seeds_first_message(self) -> None:
|
||||
"""#347: a preset agent gets its opening seeded on create; a non-preset agent does not."""
|
||||
respx.post("https://w.example/sessions").mock(return_value=httpx.Response(201, json=_CREATE_OK))
|
||||
hist = respx.post("https://w.example/sessions/s-1/history").mock(
|
||||
return_value=httpx.Response(
|
||||
201,
|
||||
json={
|
||||
"author": "assistant", "seq": 0, "phase": "seeded", "turn_id": "t1",
|
||||
"session_id": "s-1", "content_chars": 1, "injected_at": "t",
|
||||
},
|
||||
)
|
||||
)
|
||||
from ratatoskr.web.server import create_app
|
||||
app = create_app(_mock_client_factory())
|
||||
client = TestClient(app)
|
||||
# preset agent → the endpoint seeds a first-message
|
||||
assert client.post("/api/sessions", json={"agent_id": "ratatoskr:sindra"}).status_code == 201
|
||||
assert hist.call_count == 1
|
||||
# non-preset agent → no seed (count unchanged)
|
||||
assert client.post("/api/sessions", json={"agent_id": "mimir"}).status_code == 201
|
||||
assert hist.call_count == 1
|
||||
|
||||
|
||||
class TestSessionMessagesEndpoint:
|
||||
"""GET /api/sessions/{id}/messages — proxy session history (renders the #347 seed)."""
|
||||
|
||||
@respx.mock
|
||||
def test_happy_returns_history(self) -> None:
|
||||
"""happy [tracer]: proxies GET /sessions/{id}/messages → 200 with the items verbatim."""
|
||||
payload = {
|
||||
"session_id": "s-1",
|
||||
"items": [{"seq": 0, "role": "assistant", "content": "Hey there."}],
|
||||
"next_cursor": None,
|
||||
}
|
||||
respx.get("https://w.example/sessions/s-1/messages").mock(
|
||||
return_value=httpx.Response(200, json=payload)
|
||||
)
|
||||
from ratatoskr.web.server import create_app
|
||||
app = create_app(_mock_client_factory())
|
||||
resp = TestClient(app).get("/api/sessions/s-1/messages")
|
||||
assert resp.status_code == 200
|
||||
assert resp.json()["items"][0]["content"] == "Hey there."
|
||||
|
||||
@respx.mock
|
||||
def test_non_200_status_preserved(self) -> None:
|
||||
"""error: upstream 404 → status-preserving session_messages_unavailable envelope."""
|
||||
respx.get("https://w.example/sessions/ghost/messages").mock(
|
||||
return_value=httpx.Response(404, json={"error_code": "session_not_found"})
|
||||
)
|
||||
from ratatoskr.web.server import create_app
|
||||
app = create_app(_mock_client_factory())
|
||||
resp = TestClient(app).get("/api/sessions/ghost/messages")
|
||||
assert resp.status_code == 404
|
||||
assert resp.json()["error_code"] == "session_messages_unavailable"
|
||||
|
||||
|
||||
_SNAPSHOT = {
|
||||
"agent_id": "mimir",
|
||||
@@ -625,6 +681,10 @@ class TestCreateAppShape:
|
||||
"/", "/version", "/api/agents", "/api/sessions",
|
||||
"/api/agents/{agent_id}/persona_state",
|
||||
"/api/affect/{agent_id}",
|
||||
# v0.19.2 debug-surface parity (create_app POST-002)
|
||||
"/api/sessions/{session_id}/tools",
|
||||
"/api/sessions/{session_id}/bifrost",
|
||||
"/api/admin/events",
|
||||
"/api/turns/{session_id}", "/api/turns/{session_id}/stream",
|
||||
"/api/turns/{session_id}/cancel",
|
||||
):
|
||||
@@ -633,10 +693,14 @@ class TestCreateAppShape:
|
||||
assert "/static" in paths
|
||||
|
||||
def test_state_attached(self) -> None:
|
||||
"""state_attached [trace]: app.state.turn_registry is empty dict."""
|
||||
"""state_attached [trace]: app.state.turn_registry is empty dict; admin_key stored."""
|
||||
from ratatoskr.web.server import create_app
|
||||
app = create_app(_mock_client_factory())
|
||||
assert app.state.turn_registry == {}
|
||||
# create_app POST-001: admin_key defaults None (admin routes fail-visible)
|
||||
assert app.state.admin_key is None
|
||||
app2 = create_app(_mock_client_factory(), admin_key="adm-key")
|
||||
assert app2.state.admin_key == "adm-key"
|
||||
|
||||
def test_factory_stored(self) -> None:
|
||||
"""factory_stored [trace]: app.state.client_factory is the same callable."""
|
||||
@@ -813,6 +877,10 @@ class TestWebBifrostBind:
|
||||
route = respx.post("https://w.example/sessions").mock(
|
||||
return_value=httpx.Response(201, json=_CREATE_OK)
|
||||
)
|
||||
# sindra is a preset agent → the endpoint now auto-seeds a #347 first-message.
|
||||
respx.post("https://w.example/sessions/s-1/history").mock(
|
||||
return_value=httpx.Response(201, json={})
|
||||
)
|
||||
app = create_app(
|
||||
_mock_client_factory(),
|
||||
bifrost_consumer_key="server-ck",
|
||||
@@ -848,6 +916,10 @@ class TestWebBifrostBind:
|
||||
route = respx.post("https://w.example/sessions").mock(
|
||||
return_value=httpx.Response(201, json=_CREATE_OK)
|
||||
)
|
||||
# sindra is a preset agent → the endpoint now auto-seeds a #347 first-message.
|
||||
respx.post("https://w.example/sessions/s-1/history").mock(
|
||||
return_value=httpx.Response(201, json={})
|
||||
)
|
||||
app = create_app(
|
||||
_mock_client_factory(),
|
||||
bifrost_consumer_key="server-ck",
|
||||
@@ -1062,3 +1134,136 @@ class TestAffectStateEndpoint:
|
||||
resp = TestClient(app).get("/api/affect/ratatoskr:sindra")
|
||||
assert resp.status_code == 400
|
||||
assert resp.json()["error_code"] == "missing_end_user_id"
|
||||
|
||||
|
||||
class TestSessionToolsEndpoint:
|
||||
"""session_tools_endpoint — proxy owner-scoped GET /sessions/{id}/tools (#183)."""
|
||||
|
||||
@respx.mock
|
||||
def test_happy_returns_inventory(self) -> None:
|
||||
"""happy [tracer]: 200 inventory → 200 verbatim."""
|
||||
respx.get("https://w.example/sessions/s-1/tools").mock(
|
||||
return_value=httpx.Response(200, json={
|
||||
"agent_id": "ratatoskr:sindra",
|
||||
"builtin_tools": ["echo"],
|
||||
"bifrost_tools": [{"name": "memory.search"}],
|
||||
})
|
||||
)
|
||||
from ratatoskr.web.server import create_app
|
||||
resp = TestClient(create_app(_mock_client_factory())).get("/api/sessions/s-1/tools")
|
||||
assert resp.status_code == 200
|
||||
assert resp.json()["agent_id"] == "ratatoskr:sindra"
|
||||
|
||||
@respx.mock
|
||||
def test_upstream_404_status_preserving_envelope(self) -> None:
|
||||
"""error: upstream 404 → 404 session_tools_unavailable envelope."""
|
||||
respx.get("https://w.example/sessions/s-1/tools").mock(
|
||||
return_value=httpx.Response(404, content=b"nope")
|
||||
)
|
||||
from ratatoskr.web.server import create_app
|
||||
resp = TestClient(create_app(_mock_client_factory())).get("/api/sessions/s-1/tools")
|
||||
assert resp.status_code == 404
|
||||
assert resp.json()["error_code"] == "session_tools_unavailable"
|
||||
|
||||
|
||||
class TestSessionBifrostEndpoint:
|
||||
"""session_bifrost_endpoint — proxy admin-scoped GET /admin/sessions/{id}/bifrost (#176)."""
|
||||
|
||||
@respx.mock
|
||||
def test_happy_overrides_with_admin_bearer(self) -> None:
|
||||
"""happy [tracer]: 200 state → 200; request carries the ADMIN bearer, not consumer."""
|
||||
route = respx.get("https://w.example/admin/sessions/s-1/bifrost").mock(
|
||||
return_value=httpx.Response(200, json={
|
||||
"endpoint_url": "http://x:8392", "connected": True,
|
||||
"capabilities_granted": ["memory", "affect"], "tools": [],
|
||||
})
|
||||
)
|
||||
from ratatoskr.web.server import create_app
|
||||
app = create_app(_mock_client_factory(), admin_key="adm-key")
|
||||
resp = TestClient(app).get("/api/sessions/s-1/bifrost")
|
||||
assert resp.status_code == 200
|
||||
assert resp.json()["connected"] is True
|
||||
assert route.calls.last.request.headers["Authorization"] == "Bearer adm-key"
|
||||
|
||||
def test_no_admin_key_fails_visible_400(self) -> None:
|
||||
"""error: no admin key configured → 400 admin_key_not_configured, no upstream call."""
|
||||
from ratatoskr.web.server import create_app
|
||||
app = create_app(_mock_client_factory()) # no admin_key
|
||||
resp = TestClient(app).get("/api/sessions/s-1/bifrost")
|
||||
assert resp.status_code == 400
|
||||
assert resp.json()["error_code"] == "admin_key_not_configured"
|
||||
|
||||
@respx.mock
|
||||
def test_upstream_404_status_preserving_envelope(self) -> None:
|
||||
"""error: upstream 404 (not bound) → 404 bifrost_state_unavailable envelope."""
|
||||
respx.get("https://w.example/admin/sessions/s-1/bifrost").mock(
|
||||
return_value=httpx.Response(404, content=b"nope")
|
||||
)
|
||||
from ratatoskr.web.server import create_app
|
||||
app = create_app(_mock_client_factory(), admin_key="adm-key")
|
||||
resp = TestClient(app).get("/api/sessions/s-1/bifrost")
|
||||
assert resp.status_code == 404
|
||||
assert resp.json()["error_code"] == "bifrost_state_unavailable"
|
||||
|
||||
|
||||
class TestAdminEventsEndpoint:
|
||||
"""admin_events_endpoint — SSE proxy of GET /admin/events, session-filtered (#11)."""
|
||||
|
||||
def test_filter_semantics(self) -> None:
|
||||
"""unit: heartbeats drop, system.* pass, else match on session_id."""
|
||||
from ratatoskr.sse_client import AdminEvent
|
||||
from ratatoskr.web.server import _admin_event_matches_web
|
||||
|
||||
def mk(t: str, sid: "str | None" = None) -> AdminEvent:
|
||||
return AdminEvent(id=1, type=t, timestamp=None,
|
||||
data={"session_id": sid} if sid else {})
|
||||
|
||||
assert _admin_event_matches_web(mk("system.heartbeat"), "s-1") is False
|
||||
assert _admin_event_matches_web(mk("system.degraded"), "s-1") is True
|
||||
assert _admin_event_matches_web(mk("session.created", "s-1"), "s-1") is True
|
||||
assert _admin_event_matches_web(mk("session.created", "other"), "s-1") is False
|
||||
assert _admin_event_matches_web(mk("session.created", "s-1"), None) is False
|
||||
|
||||
def test_no_admin_key_fails_visible_400(self) -> None:
|
||||
"""error: no admin key → 400 admin_key_not_configured (no stream opened)."""
|
||||
from ratatoskr.web.server import create_app
|
||||
app = create_app(_mock_client_factory())
|
||||
resp = TestClient(app).get("/api/admin/events?session_id=s-1")
|
||||
assert resp.status_code == 400
|
||||
assert resp.json()["error_code"] == "admin_key_not_configured"
|
||||
|
||||
@respx.mock
|
||||
def test_streams_filtered_events_fixed_name(self) -> None:
|
||||
"""happy: SSE → only session-matching + system.* forwarded, as `admin_event`."""
|
||||
stream = (
|
||||
b'event: session.created\n'
|
||||
b'data: {"type":"session.created","data":{"session_id":"s-1"}}\n\n'
|
||||
b'event: system.heartbeat\n'
|
||||
b'data: {"type":"system.heartbeat","data":{}}\n\n'
|
||||
b'event: turn.started\n'
|
||||
b'data: {"type":"turn.started","data":{"session_id":"other"}}\n\n'
|
||||
b'event: system.degraded\n'
|
||||
b'data: {"type":"system.degraded","data":{}}\n\n'
|
||||
)
|
||||
respx.get("https://w.example/admin/events").mock(return_value=_sse_resp(stream))
|
||||
from ratatoskr.web.server import create_app
|
||||
app = create_app(_mock_client_factory(), admin_key="adm-key")
|
||||
body = TestClient(app).get("/api/admin/events?session_id=s-1").text
|
||||
assert "event: admin_event" in body # fixed browser-facing name
|
||||
assert '"type": "session.created"' in body # matches active session → forwarded
|
||||
assert "system.degraded" in body # system.* → forwarded
|
||||
assert "system.heartbeat" not in body # heartbeat → dropped
|
||||
assert "turn.started" not in body # other session → dropped
|
||||
|
||||
@respx.mock
|
||||
def test_stream_error_on_connect_failure(self) -> None:
|
||||
"""error: upstream admin SSE non-200 -> ONE stream_error frame, stream ends (POST-003)."""
|
||||
respx.get("https://w.example/admin/events").mock(
|
||||
return_value=httpx.Response(500, content=b"boom")
|
||||
)
|
||||
from ratatoskr.web.server import create_app
|
||||
app = create_app(_mock_client_factory(), admin_key="adm-key")
|
||||
body = TestClient(app).get("/api/admin/events?session_id=s-1").text
|
||||
assert "event: stream_error" in body
|
||||
assert "SseConnectFailed" in body
|
||||
assert body.count("event: stream_error") == 1 # exactly one, then ends
|
||||
|
||||
Reference in New Issue
Block a user