Compare commits
10 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 5c1b9816d4 | |||
| 2ba4244e9e | |||
| 0c7660791f | |||
| 1f289098ba | |||
| b798068932 | |||
| 93e4176346 | |||
| a358cc9150 | |||
| e4317f6a73 | |||
| b2e4901264 | |||
| af67ad995c |
@@ -89,3 +89,37 @@ canonical_path = "scripts/contract_drift_check.py"
|
||||
consumer_path = "scripts/contract_drift_check.py"
|
||||
pinned_sha256_16 = "23271287ac488da4"
|
||||
pinned_at = "2026-05-17T05:30:00+00:00"
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Worldtree Conversation-API surface (vendored from ~/development/Worldtree).
|
||||
# The v1 wire is FROZEN (Worldtree #326 / v1-schema-freeze-manifest.md). The
|
||||
# machine-readable OpenAPI + SSE schema are the authoritative drift GATES; the
|
||||
# prose markdown is the human reference and is allowed to lag (tolerate_drift).
|
||||
# These are what ratatoskr's v1 coverage map (docs/coverage-map.md) audits
|
||||
# against. Pin target: Worldtree 5810a26 (v1.0.0b2).
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
[[pins]]
|
||||
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"
|
||||
|
||||
[[pins]]
|
||||
id = "worldtree-conversation-api-sse-events-v1"
|
||||
canonical_source = "Worldtree"
|
||||
canonical_path = "docs/conversation-api-sse-events.schema.json"
|
||||
consumer_path = "docs/conversation-api-sse-events.schema.json"
|
||||
pinned_sha256_16 = "9deeebf404d72f9a"
|
||||
pinned_at = "2026-06-30T22:25:56+00:00"
|
||||
|
||||
[[pins]]
|
||||
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"
|
||||
tolerate_drift = true # prose reference; OpenAPI+SSE are the gates
|
||||
|
||||
+15
-7
@@ -7,24 +7,32 @@ documents the pin, the vendored artifacts, and the bump procedure.
|
||||
|
||||
| Field | Value |
|
||||
|---|---|
|
||||
| Worldtree git SHA | `f1b59f8cd6fe41e497d0be9dad9d3110451f0d9a` |
|
||||
| Worldtree HEAD message | `Merge #299: adopt bifrost v0.6 memory scope wire (scope_any/scope_all)` |
|
||||
| Pinned on | 2026-06-17 |
|
||||
| Pinned by | ratatoskr-dev (bump for #297/#298 — cold recall closed end-to-end) |
|
||||
| Worldtree version at pin | `v0.35.16` |
|
||||
| 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` |
|
||||
|
||||
## Pin history
|
||||
|
||||
| Date | SHA | Version | Notable deltas consumed |
|
||||
|---|---|---|---|
|
||||
| 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 |
|
||||
| 2026-05-20 | `55101e9` | v0.19.0 | initial scaffold pin |
|
||||
|
||||
## Vendored artifacts
|
||||
|
||||
- `docs/conversation-api-spec.md` — copy of `Worldtree/docs/conversation-api-spec.md` at the pinned SHA. This is the **client-facing interface contract** Ratatoskr is built against.
|
||||
- `docs/conversation_api.contract.md` — copy of `Worldtree/docs/contracts/conversation_api.contract.md` at the pinned SHA. 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.
|
||||
**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-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.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
|
||||
the live `~/development/Worldtree` checkout. Update them only when
|
||||
|
||||
@@ -106,7 +106,7 @@ POST: [POST-002 return_value] AsyncIterator yields ≥1 event ending in exactly
|
||||
POST: [POST-003 state_change] every yielded Event has a populated sse_id with both fields >= 1 -- assert all(e.sse_id.turn_id >= 1 and e.sse_id.seq >= 1 for e in events)
|
||||
ERROR_ROUTING:
|
||||
httpx.HTTPStatusError:
|
||||
local_handling: re-raise as SseConnectFailed(status=resp.status_code, body=resp.read()[:1024]) — server returned non-2xx before stream started (e.g., 404 session_not_found)
|
||||
local_handling: re-raise as SseConnectFailed(status=resp.status_code, body=resp.read()[:1024]) — server returned non-2xx before stream started (e.g., 404 session_not_found). EXCEPT the two eager turn-launch failures (Worldtree v1.0.0b1 #331), checked BEFORE raise_for_status and raised as typed SseConnectFailed SUBCLASSES carrying error_code: 409 -> AgentNotAvailable (agent unavailable; pre-b1 this was a 200 + in-stream `error` event), 503 -> TurnLaunchUnavailable (transient turn-launch failure; retryable=True). Subclassing keeps existing `except SseConnectFailed` handlers working with zero changes.
|
||||
flow_control: abort
|
||||
state_recovery: none (no events yielded yet)
|
||||
httpx.ReadError | httpx.RemoteProtocolError | httpx.ReadTimeout:
|
||||
@@ -129,7 +129,8 @@ ERROR_ROUTING:
|
||||
STEPS:
|
||||
1. [setup, flexibility=prescriptive] Validate inputs per PRE-001..PRE-003
|
||||
2. [sequential, flexibility=prescriptive] Open SSE connection via httpx_sse.aconnect_sse with method="POST", url=f"/sessions/{session_id}/messages", json={"content": content}
|
||||
ON httpx.HTTPStatusError before stream opens:
|
||||
2a. [branch, flexibility=prescriptive] IF response.status_code in (409, 503) (b1 #331 eager turn-launch failures): read the body, parse (error_code, message) from the `{"detail": {...}}` envelope OR a flat `{error_code, message}` body (status-derived default code when absent), then RAISE AgentNotAvailable (409) / TurnLaunchUnavailable (503).
|
||||
ON httpx.HTTPStatusError before stream opens (any other non-2xx):
|
||||
RAISE SseConnectFailed
|
||||
3. [loop, flexibility=prescriptive] FOR EACH sse_event in event_source.aiter_sse():
|
||||
0. [branch, flexibility=prescriptive] IF sse_event.data == "":
|
||||
@@ -162,6 +163,9 @@ TESTS:
|
||||
error_terminal [error]: mock emits one `text` then `error` with `error_code: "llm_output_invalid"` → consumer yields Text then Error; iteration ends; Error.message and Error.error_code are populated
|
||||
cancelled_terminal [error]: mock emits `cancelled` with phase=cancelled → consumer yields Cancelled with turn_id; iteration ends
|
||||
session_not_found [error]: mock returns 404 before stream opens → consumer raises SseConnectFailed(status=404)
|
||||
eager_409_agent_not_available [error]: mock returns 409 {detail:{error_code:"agent_not_available", message}} before stream → consumer raises AgentNotAvailable(status=409, error_code="agent_not_available", retryable absent); isinstance SseConnectFailed
|
||||
eager_503_retryable [error]: mock returns 503 before stream → consumer raises TurnLaunchUnavailable(status=503, retryable=True); isinstance SseConnectFailed
|
||||
eager_409_non_json_body [adversarial]: mock returns 409 with a non-JSON body → consumer raises AgentNotAvailable with the status-derived default error_code "agent_not_available"
|
||||
malformed_id_no_seq [adversarial]: mock event has `id: 42` (missing `:seq`) → consumer raises MalformedSseId; no event yielded
|
||||
malformed_id_alpha [adversarial]: mock event has `id: foo:bar` (non-integer parts) → consumer raises MalformedSseId
|
||||
turn_id_flip [adversarial]: mock emits text events with ids `42:1` then `99:2` → consumer raises TurnIdFlip; only the first event was yielded
|
||||
@@ -293,3 +297,51 @@ TESTS:
|
||||
trailing_whitespace [adversarial]: "42:3 " → ValueError (strict; do not strip; the server emits clean ids)
|
||||
truncation [security]: input is 5000-char string with no colon → ValueError message includes only `raw[:64]` (not the full 5000)
|
||||
```
|
||||
|
||||
## Amendment 2026-06-30 — shared resume orchestration (v1 coverage-audit, slice b1)
|
||||
|
||||
The original contract specs resume as **caller-owned** (§Resume semantics: "the
|
||||
caller MAY invoke `reconnect_turn`"). The v1 coverage-audit found `reconnect_turn`
|
||||
had **no caller** — every presenter (cli/tui/web) let a mid-stream drop propagate
|
||||
instead of resuming, so the "reference SSE-resume implementation" (design-brief
|
||||
§3/§8d) was unreachable. Per design-brief §8b ("share the consumer, branch the
|
||||
presenter") the resume loop is a **single shared orchestration surface**, not
|
||||
duplicated per presenter. This adds `stream_turn_resilient` as that surface;
|
||||
presenters call it instead of `stream_turn` when they want transparent reconnect.
|
||||
`stream_turn` and `reconnect_turn` are unchanged (still the primitives); this is
|
||||
purely additive.
|
||||
|
||||
```contract
|
||||
FN stream_turn_resilient(client: httpx.AsyncClient, session_id: str, content: str, *, max_reconnects: int = 5) -> AsyncIterator[Event]
|
||||
BRIEF: The shared resume-orchestration wrapper over stream_turn + reconnect_turn. Yields a SINGLE continuous typed Event stream; on SseConnectionDropped (mid-stream drop OR clean EOF before terminal), transparently resumes via reconnect_turn from the last-seen sse_id, up to max_reconnects times, until a terminal Done/Error/Cancelled arrives. The one surface all presenters consume for resilient streaming (design-brief §8b). Cross-process resume stays deferred to v2 (§8d): last-seen lives only in this generator's frame.
|
||||
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] content is non-empty str -- assert content and isinstance(content, str)
|
||||
PRE: [PRE-004 hard] max_reconnects is a non-negative int -- assert isinstance(max_reconnects, int) and max_reconnects >= 0
|
||||
POST: [POST-001 return_value] yielded events are the concatenation of each attempt's events in wire order; the wrapper does NOT re-yield events it already saw (the server replays only seq>last_seen) -- assert seq is non-decreasing within a turn_id across the seam
|
||||
POST: [POST-002 return_value] a fully-consumed stream terminates at exactly one Done/Error/Cancelled (INV-001 holds across reconnects) -- assert isinstance(events[-1], (Done, Error, Cancelled))
|
||||
POST: [POST-003 state_change] reconnect_turn is invoked with last_event_id == f"{last_seen.turn_id}:{last_seen.seq}" of the most recently yielded event -- assert the Last-Event-ID header on attempt N+1 == the last sse_id yielded before the drop
|
||||
ERROR_ROUTING:
|
||||
SseConnectionDropped (from stream_turn or reconnect_turn):
|
||||
local_handling: IF a last-seen sse_id exists AND reconnects < max_reconnects → increment reconnects, resume via reconnect_turn(last_event_id=f"{turn_id}:{seq}"); ELSE re-raise
|
||||
flow_control: continue (resume) | abort (re-raise when no last-seen id, or budget exhausted)
|
||||
state_recovery: server replays buffered events seq>last_seen then streams live (spec §Reconnect flow)
|
||||
ResumeBufferExpired | ResumeTurnFinished | InvalidLastEventId | TurnIdFlip | SseConnectFailed (from reconnect_turn):
|
||||
local_handling: propagate unchanged — NOT a transient drop; caller policy is abandon/restart (§Resume semantics "surface, not recover")
|
||||
flow_control: abort
|
||||
state_recovery: none
|
||||
STEPS:
|
||||
1. [setup, flexibility=prescriptive] Validate PRE-001..PRE-004; SET last_seen=None, reconnects=0, gen=stream_turn(client, session_id, content)
|
||||
2. [loop, flexibility=prescriptive] async-for event in gen: SET last_seen=event.sse_id; YIELD event. On clean generator completion (terminal reached): RETURN.
|
||||
3. [branch, flexibility=prescriptive] ON SseConnectionDropped d: SET seen = last_seen or d.last_seen_sse_id. IF seen is None OR reconnects >= max_reconnects: RE-RAISE. ELSE: reconnects += 1; gen = reconnect_turn(client, session_id, content, last_event_id=f"{seen.turn_id}:{seen.seq}"); GOTO step 2.
|
||||
4. [error_handler, flexibility=prescriptive] Any non-drop exception from gen (ResumeBufferExpired/ResumeTurnFinished/InvalidLastEventId/TurnIdFlip/SseConnectFailed) is NOT caught — it propagates unchanged.
|
||||
TESTS:
|
||||
happy_no_drop [happy]: stream yields text(42:1), done(42:2) cleanly → wrapper yields exactly those 2; endpoint hit ONCE (no reconnect).
|
||||
resume_after_one_drop [scenario,tracer]: attempt 1 yields text(42:1) then RemoteProtocolError; reconnect replays text(42:2)+done(42:3) → wrapper yields 42:1,42:2,42:3 as ONE stream; 2nd request carried Last-Event-ID "42:1".
|
||||
resume_after_clean_eof [scenario]: attempt 1 yields text(42:1) then clean EOF (no terminal); reconnect yields done(42:2) → continuous (resumes on the INV-001 clean-eof drop too).
|
||||
two_drops_then_done [scenario]: drops after 42:1 then after 42:2; third attempt yields done(42:3) → all 3 events; reconnects==2; Last-Event-ID headers "42:1" then "42:2".
|
||||
unresumable_zero_event_drop [adversarial]: attempt 1 drops with ZERO events seen (last_seen None) → SseConnectionDropped propagates; only 1 request issued.
|
||||
max_reconnects_exhausted [adversarial]: every attempt drops after one event; max_reconnects=2 → after initial + 2 reconnects (3 requests), SseConnectionDropped propagates.
|
||||
buffer_expired_propagates [error]: attempt 1 drops after 42:1; reconnect returns 412 → ResumeBufferExpired propagates (not retried as a transient drop).
|
||||
zero_budget_no_resume [adversarial]: max_reconnects=0; attempt 1 drops after 42:1 → SseConnectionDropped propagates immediately (no reconnect attempted).
|
||||
```
|
||||
|
||||
@@ -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.
|
||||
```
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,265 @@
|
||||
{
|
||||
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
||||
"description": "Server-Sent Events emitted on POST /sessions/{id}/messages. Each event is an object discriminated on `type`; all carry `turn_id`.",
|
||||
"discriminator": {
|
||||
"propertyName": "type"
|
||||
},
|
||||
"oneOf": [
|
||||
{
|
||||
"additionalProperties": true,
|
||||
"properties": {
|
||||
"phase": {
|
||||
"enum": [
|
||||
"BuildingPrompt",
|
||||
"CallingLLM",
|
||||
"ProcessingTools",
|
||||
"Streaming",
|
||||
"Finishing"
|
||||
],
|
||||
"type": "string"
|
||||
},
|
||||
"turn_id": {
|
||||
"description": "The turn this event belongs to.",
|
||||
"type": [
|
||||
"integer",
|
||||
"string"
|
||||
]
|
||||
},
|
||||
"type": {
|
||||
"const": "worker_phase"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"type",
|
||||
"turn_id"
|
||||
],
|
||||
"type": "object"
|
||||
},
|
||||
{
|
||||
"additionalProperties": true,
|
||||
"properties": {
|
||||
"turn_id": {
|
||||
"description": "The turn this event belongs to.",
|
||||
"type": [
|
||||
"integer",
|
||||
"string"
|
||||
]
|
||||
},
|
||||
"type": {
|
||||
"const": "awaiting_llm_first_token"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"type",
|
||||
"turn_id"
|
||||
],
|
||||
"type": "object"
|
||||
},
|
||||
{
|
||||
"additionalProperties": true,
|
||||
"properties": {
|
||||
"content": {
|
||||
"type": "string"
|
||||
},
|
||||
"turn_id": {
|
||||
"description": "The turn this event belongs to.",
|
||||
"type": [
|
||||
"integer",
|
||||
"string"
|
||||
]
|
||||
},
|
||||
"type": {
|
||||
"const": "thinking"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"type",
|
||||
"turn_id"
|
||||
],
|
||||
"type": "object"
|
||||
},
|
||||
{
|
||||
"additionalProperties": true,
|
||||
"properties": {
|
||||
"content": {
|
||||
"type": "string"
|
||||
},
|
||||
"turn_id": {
|
||||
"description": "The turn this event belongs to.",
|
||||
"type": [
|
||||
"integer",
|
||||
"string"
|
||||
]
|
||||
},
|
||||
"type": {
|
||||
"const": "text"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"type",
|
||||
"turn_id"
|
||||
],
|
||||
"type": "object"
|
||||
},
|
||||
{
|
||||
"additionalProperties": true,
|
||||
"properties": {
|
||||
"turn_id": {
|
||||
"description": "The turn this event belongs to.",
|
||||
"type": [
|
||||
"integer",
|
||||
"string"
|
||||
]
|
||||
},
|
||||
"type": {
|
||||
"const": "text_boundary"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"type",
|
||||
"turn_id"
|
||||
],
|
||||
"type": "object"
|
||||
},
|
||||
{
|
||||
"additionalProperties": true,
|
||||
"properties": {
|
||||
"name": {
|
||||
"type": "string"
|
||||
},
|
||||
"turn_id": {
|
||||
"description": "The turn this event belongs to.",
|
||||
"type": [
|
||||
"integer",
|
||||
"string"
|
||||
]
|
||||
},
|
||||
"type": {
|
||||
"const": "tool_start"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"type",
|
||||
"turn_id"
|
||||
],
|
||||
"type": "object"
|
||||
},
|
||||
{
|
||||
"additionalProperties": true,
|
||||
"properties": {
|
||||
"name": {
|
||||
"type": "string"
|
||||
},
|
||||
"result": {},
|
||||
"turn_id": {
|
||||
"description": "The turn this event belongs to.",
|
||||
"type": [
|
||||
"integer",
|
||||
"string"
|
||||
]
|
||||
},
|
||||
"type": {
|
||||
"const": "tool_result"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"type",
|
||||
"turn_id"
|
||||
],
|
||||
"type": "object"
|
||||
},
|
||||
{
|
||||
"additionalProperties": true,
|
||||
"properties": {
|
||||
"turn_id": {
|
||||
"description": "The turn this event belongs to.",
|
||||
"type": [
|
||||
"integer",
|
||||
"string"
|
||||
]
|
||||
},
|
||||
"type": {
|
||||
"const": "affect_update"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"type",
|
||||
"turn_id"
|
||||
],
|
||||
"type": "object"
|
||||
},
|
||||
{
|
||||
"additionalProperties": true,
|
||||
"properties": {
|
||||
"turn_id": {
|
||||
"description": "The turn this event belongs to.",
|
||||
"type": [
|
||||
"integer",
|
||||
"string"
|
||||
]
|
||||
},
|
||||
"type": {
|
||||
"const": "done"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"type",
|
||||
"turn_id"
|
||||
],
|
||||
"type": "object"
|
||||
},
|
||||
{
|
||||
"additionalProperties": true,
|
||||
"properties": {
|
||||
"phase": {
|
||||
"type": "string"
|
||||
},
|
||||
"reason": {
|
||||
"type": "string"
|
||||
},
|
||||
"turn_id": {
|
||||
"description": "The turn this event belongs to.",
|
||||
"type": [
|
||||
"integer",
|
||||
"string"
|
||||
]
|
||||
},
|
||||
"type": {
|
||||
"const": "cancelled"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"type",
|
||||
"turn_id"
|
||||
],
|
||||
"type": "object"
|
||||
},
|
||||
{
|
||||
"additionalProperties": true,
|
||||
"properties": {
|
||||
"error_code": {
|
||||
"type": "string"
|
||||
},
|
||||
"message": {
|
||||
"type": "string"
|
||||
},
|
||||
"turn_id": {
|
||||
"description": "The turn this event belongs to.",
|
||||
"type": [
|
||||
"integer",
|
||||
"string"
|
||||
]
|
||||
},
|
||||
"type": {
|
||||
"const": "error"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"type",
|
||||
"turn_id"
|
||||
],
|
||||
"type": "object"
|
||||
}
|
||||
],
|
||||
"title": "Worldtree Conversation API — SSE turn-stream events"
|
||||
}
|
||||
@@ -0,0 +1,247 @@
|
||||
# Ratatoskr v1 coverage map
|
||||
|
||||
_The v1 convergence-target ledger. Ratatoskr has **no self-defined feature
|
||||
roadmap**: v1 = consume all of Worldtree's I/O points, reached when Worldtree
|
||||
hits 1.0 (operator, 2026-06-19; auto-memory
|
||||
`project-ratatoskr-v1-derived-from-worldtree-io-coverage`). This file is that
|
||||
coverage map — every Worldtree v1-frozen I/O point × ratatoskr's coverage
|
||||
status, so "are we at v1?" is a ledger lookup, not a judgement call._
|
||||
|
||||
**First authored:** 2026-06-30 (the v1 coverage-audit kickoff).
|
||||
|
||||
---
|
||||
|
||||
## Frozen target
|
||||
|
||||
Worldtree is at **v1.0.0b2** — approaching 1.0, with its wire surfaces now
|
||||
**FROZEN** (Worldtree `docs/v1-schema-freeze-manifest.md`, #326). The audit
|
||||
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 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) |
|
||||
|
||||
> **Pin drift (finding P-1) — REMEDIATED 2026-06-30.** Ratatoskr formerly
|
||||
> vendored only the **prose markdown** (`docs/conversation-api-spec.md`), which
|
||||
> is byte-identical to live Worldtree's but frozen at v0.35.16-era content (last
|
||||
> WT edit 2026-05-31) and does **not** document the b2 surface (7 endpoints
|
||||
> below, the 409/503 on messages-POST #331, the unified error envelope #328, the
|
||||
> SSE schema). Remediated: the **OpenAPI 2.2.0 + SSE-schema JSON are now vendored
|
||||
> and pinned** (`.corviduo-canonicals.toml` → `canonical_drift.py` gate); the
|
||||
> prose markdown is the `tolerate_drift` reference. Spec pin advanced to
|
||||
> 5810a26 (v1.0.0b2). See § Pin remediation.
|
||||
|
||||
**7 endpoints new in b2 OpenAPI, absent from our vendored markdown:**
|
||||
`/admin/keys/bulk`, `/admin/persona/archive`, `/admin/persona/erase`,
|
||||
`/admin/usage`, `/embed`, `/judgments`, `/me/usage`.
|
||||
|
||||
---
|
||||
|
||||
## Scorecard
|
||||
|
||||
**Scope mandate: A (ledger-mandate), locked by operator 2026-06-30.** v1 "done"
|
||||
= every frozen I/O point is **classified** (covered or excluded-with-rationale),
|
||||
zero unaccounted. NOT "feature-complete client." All scope-pending rows are now
|
||||
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 |
|
||||
| SSE events | 11 | 11 | 0 | 0 |
|
||||
| Bifrost provider planes | 8 verbs | 8 | 0 | (10 gated verbs deferred) |
|
||||
|
||||
**Legend.** ✅ consumed in code AND live-proven against real Worldtree · ⬜ a
|
||||
debug-observability I/O point we should cover but don't yet (the convergence
|
||||
frontier) · 🚫 deliberate non-goal per the design-brief negative clauses + the A
|
||||
mandate. Counts are at the **path-group** level; mixed-method groups are
|
||||
footnoted (e.g. `/sessions` POST is ✅ but its `GET` picker is an unwired
|
||||
sub-gap).
|
||||
|
||||
---
|
||||
|
||||
## Surface 1 — Conversation REST API (OpenAPI 2.2.0)
|
||||
|
||||
### Covered — client path (ratatoskr's core identity)
|
||||
|
||||
| Endpoint | Status | Where consumed | Note |
|
||||
|---|---|---|---|
|
||||
| `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}/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 |
|
||||
|
||||
**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):
|
||||
- `GET /sessions` — `sessions.py:198` `list_sessions` exists, **no caller**: the
|
||||
startup session-picker (design-brief §4 v1) was never wired.
|
||||
- `POST /sessions/{id}/messages` + `Last-Event-ID` — `sse_client.py:524`
|
||||
`reconnect_turn` exists, **no caller**: the reference SSE-resume impl
|
||||
(design-brief §8d) was never wired.
|
||||
- `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)
|
||||
|
||||
**Tier 1 — the debug-observability core (design-brief'd for v1, unbuilt):**
|
||||
|
||||
| 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 |
|
||||
|
||||
**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 |
|
||||
|
||||
### 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/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) |
|
||||
| `POST /admin/users/{id}/tier` | 🚫 | admin user mgmt |
|
||||
| `GET /me/usage` · `GET /admin/usage` | 🚫 | usage metering — not turn-flow observability (new in b2) |
|
||||
| `GET /healthz` · `GET /readyz` | 🚫 | liveness probes — low debug value (could become a connect preflight; park) |
|
||||
| `GET /search` | 🚫 | §5: consumer-product feature, not turn-flow (was "defer to v2") |
|
||||
| `GET/POST /uploads` · `DELETE/GET /uploads/{id}` | 🚫 | §6: no uploads — consumer-product feature |
|
||||
| `GET /pending` · `GET /sessions/{id}/pending` | 🚫 | §5: poll-only, no turn-flow signal (was "optional, skip") |
|
||||
| `POST /embed` | 🚫 | embedding utility — no turn flows through it |
|
||||
| `POST /judgments` | 🚫 | LLM-as-judge A/B eval (`response_a`/`response_b`/`rubric`) — standalone eval utility, not turn-flow |
|
||||
|
||||
### Scope-resolution record (the 11 ❓ rows, resolved under A)
|
||||
|
||||
The 2026-05-20 design-brief deferred several surfaces; the 2026-06-19 reframe
|
||||
("v1 = full I/O coverage") put them back in tension. **Resolved 2026-06-30 under
|
||||
mandate A** (debug-observability identity intact; classify, don't build-all):
|
||||
|
||||
| Endpoint(s) | Resolution |
|
||||
|---|---|
|
||||
| `GET /search` · `uploads` (×2) · `pending` (×2) · `POST /embed` · `POST /judgments` | 🚫 **excluded** — consumer-product / eval / poll utilities, not turn-flow observability |
|
||||
| `characters` (×4) · `POST /sessions/{id}/persona_state` | ⬜ **in-scope** (frontier Tier 2) — session-routing + affect-injection debug paths |
|
||||
|
||||
Nothing remains ❓. The ⬜-vs-🚫 line follows the debug-observability test: *does
|
||||
a turn flow through it / is it a layer worth watching live?*
|
||||
|
||||
---
|
||||
|
||||
## Surface 2 — SSE events (11/11 ✅)
|
||||
|
||||
Every frozen SSE event type is parsed in `sse_client.py:_envelope_for_type`
|
||||
(342-411) and rendered by all three presenters (cli/tui/web). **Full coverage.**
|
||||
|
||||
`text` · `worker_phase` · `thinking` · `text_boundary` · `tool_start` ·
|
||||
`tool_result` · `done` · `error` · `cancelled` · `awaiting_llm_first_token` ·
|
||||
`affect_update`
|
||||
|
||||
> Caveat (not a gap): `affect_update` is wire-verified to emit **zero** events
|
||||
> for consumer (Tier-3) agents — the persona-strip SSE path never populates for
|
||||
> them (memory 2026-06-18). The handler is correct; the upstream emitter is
|
||||
> silent. PAD for consumer agents is surfaced via our own provider read route
|
||||
> (`GET /affect/state/{id}`, #18 D2), not this event.
|
||||
|
||||
---
|
||||
|
||||
## Surface 3 — Bifrost provider planes (8/8 ✅, live-proven)
|
||||
|
||||
Ratatoskr **implements** the provider side; Worldtree dispatches into it.
|
||||
Live-proven end-to-end through real WT turns (#17/#18 smokes; combined `:8392`
|
||||
WT-driven smoke 2026-06-20).
|
||||
|
||||
**Memory plane** — covers the entire `bifrost.memory.MemoryDataStore` protocol
|
||||
(required: `describe_store`, `get`, `get_many`, `search`, `upsert_many`) **plus**
|
||||
`delete_many`:
|
||||
|
||||
| Verb | Where | |
|
||||
|---|---|---|
|
||||
| `describe_store` | `memory_store.py:140` | advertises caps (sync) |
|
||||
| `search` | `memory_store.py:224` | vector recall; scope_all AND / scope_any OR |
|
||||
| `get` / `get_many` | `memory_store.py:293` / `:305` | point reads |
|
||||
| `upsert_many` | `memory_store.py:150` | idempotent batch write; optimistic lock |
|
||||
| `delete_many` | `memory_store.py:314` | transactional delete |
|
||||
|
||||
**Affect plane** — covers `bifrost…InMemoryAffectStore` (`emit`, `fetch`):
|
||||
|
||||
| Verb | Where | |
|
||||
|---|---|---|
|
||||
| `emit` | `affect_store.py:47` | conduit-opaque snapshot upsert (LWW) |
|
||||
| `fetch` | `affect_store.py:116` | `{found, snapshot}`; mandatory since bifrost 0.10.0 strong-or-absent gate |
|
||||
|
||||
Plus the non-wire PAD read route `GET /affect/state/{agent_id}`
|
||||
(`affect_store.py:189`) and the combined `:8392` endpoint advertising both caps
|
||||
by store-presence (`combined.py:46`).
|
||||
|
||||
**Deferred-gated (advertised-unsupported, correctly out-of-scope for the basic
|
||||
plane):** `scan`, `get_edges_for`, `upsert_edges`, `mark_invalid`,
|
||||
`mark_superseded`, `patch_many`, `commit_checkpoint`, `lease_job`,
|
||||
`read_checkpoint`, `health`. These live only in the bifrost reference
|
||||
*extended* store, not the `MemoryDataStore` protocol; deferred per the #294
|
||||
re-scope (memory 2026-06-15). Re-evaluate only if Worldtree's Tier-3 path
|
||||
starts exercising them.
|
||||
|
||||
---
|
||||
|
||||
## Convergence frontier (the v1 to-do)
|
||||
|
||||
**Tier 1 — debug-observability core**, in dependency order:
|
||||
|
||||
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 2 — rounds out coverage** (lower priority):
|
||||
|
||||
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`**.
|
||||
|
||||
---
|
||||
|
||||
## Pin remediation (finding P-1) — DONE 2026-06-30
|
||||
|
||||
Re-pinned to the frozen machine-readable artifacts (the chosen option):
|
||||
`conversation-api-openapi.json` (2.2.0) + `conversation-api-sse-events.schema.json`
|
||||
are vendored under `docs/` and pinned in `.corviduo-canonicals.toml`
|
||||
(`worldtree-conversation-api-openapi-v2`, `-sse-events-v1`), drift-gated by
|
||||
`canonical_drift.py`. The prose markdown stays as a `tolerate_drift` reference
|
||||
(`-spec-v1`). `pyproject.toml` spec pin advanced f1b59f8 → 5810a26 (v1.0.0b2);
|
||||
`docs/SPEC-PIN.md` records the bump. This map now audits a frozen, diffable
|
||||
target — re-running the audit is a `canonical_drift.py` check away.
|
||||
|
||||
---
|
||||
|
||||
## Decisions
|
||||
|
||||
1. **Scope mandate — RESOLVED 2026-06-30: A (ledger-mandate).** v1 "done" = every
|
||||
frozen I/O point classified, zero unaccounted; NOT feature-complete client.
|
||||
The ⬜-vs-🚫 line for the 11 formerly-pending rows is locked above (§
|
||||
Scope-resolution record).
|
||||
2. **Pin remediation (P-1) — RESOLVED 2026-06-30 (re-pin to machine-readable).**
|
||||
Vendored `conversation-api-openapi.json` (2.2.0) + `conversation-api-sse-events.schema.json`
|
||||
as the authoritative drift gates (pinned in `.corviduo-canonicals.toml`,
|
||||
`canonical_drift.py` green); prose markdown kept as `tolerate_drift`
|
||||
reference. Spec pin advanced f1b59f8 (v0.35.16) → 5810a26 (v1.0.0b2). This
|
||||
map now audits against a frozen, diffable target.
|
||||
+17
-1
@@ -1,6 +1,6 @@
|
||||
# Persistent memory — ratatoskr
|
||||
|
||||
_Last updated: 2026-06-20_
|
||||
_Last updated: 2026-06-30_
|
||||
|
||||
This file captures durable intent and supporting evidence (goals, decisions,
|
||||
foot-gun warnings, in-flight state) across context resets. Read it at session
|
||||
@@ -138,6 +138,20 @@ decision. Captures rationale that won't be obvious from code alone.
|
||||
- `[2026-06-19]` **Ratatoskr v1 is DERIVED from Worldtree I/O coverage (operator) — no self-defined feature ROADMAP.** v1 = consume all of Worldtree's I/O points, reached when Worldtree hits 1.0; the convergence target is a coverage map, not a 3–7 capability list. [auto-memory `project-ratatoskr-v1-derived-from-worldtree-io-coverage`]
|
||||
- `[2026-06-20]` **#18's final leg PROVEN — composite `:8392` WT-driven smoke ran end-to-end + persisted.** infra-ops allowlisted `10.100.10.50:8392` on the personal WT (`01KVHWJGTT…`); a real WT turn (session `b83a66b6`, `ratatoskr:sindra`, fresh end_user `resmoke-choco-1`) dispatched the full both-plane lifecycle through ONE endpoint — handshake (both caps) → `affect.fetch` + `memory.search` → `affect.emit` (`stored:true`) → `memory.upsert_many` (`upserted:1`) — both writes verified in our SQLite (`affect_snapshots` PAD row + `memory_chunks` chunk `2df1b79…`). First attempt blocked by a `model_unavailable` outage on the personal WT (both agents' models down), operator-fixed mid-session, then clean. The composite has no open legs.
|
||||
- `[2026-06-20]` **#17 CLOSED in the tracker.** Shipped end-to-end (`v0.17.8`–`.13` + op-feed field fix `v0.17.17`); the 2026-06-20 composite smoke re-exercised its op-feed live. Closing comment captures the full both-plane proof. Open issues now just #11 (scope-blocked) + #10 (watch).
|
||||
- `[2026-06-20]` **Sindra has real PAD but ~empty memory — the affect/memory persistence asymmetry, confirmed on real sessions.** affect EMITS every turn (persona always accumulates: vuong 8→14 interactions across the session); memory only writes on a PROMOTION trigger (salience / turn_count≥6 / idle-≥10min flush). Two real vuong sessions through the combined bind (`04d6414c`, `433541fe`) drove affect emits + memory SEARCHES but ZERO promotion upserts → `memory.db` holds only the smoke fixture, zero vuong chunks. Operator: acceptable (server-takedown = "Sindra bonked on the head"; transient memory loss WAD). Operational catch: combined-as-default web bind saves persona reliably but silently LOSES memory if a session closes before a promotion trigger fires.
|
||||
- `[2026-06-29]` **Web SPA combined-bind default (`v0.18.1`, `719e4d6`) — operator-caught gap.** #18 shipped the composite `:8392` provider but never exposed it in the web bind dropdown (only memory/affect single-plane). Added `combined (:8392)` as the DEFAULT option (both planes in one session), kept single-plane for isolation diagnostics; wired `endpoint_for_plane` combined→8392 + server validation + the dropdown. Direct TDD; #17 contract updated (the governing spec for the web bind). Restarted `:8765` on current code (env.sh + provider.env + `RATATOSKR_AFFECT_READ_URL=:8392`).
|
||||
- `[2026-06-29]` **bifrost repinned 1.0.0 (`v0.18.2`, `af67ad9`).** bifrost-dev shipped its first stable release; wire v0.6 now STABLE/FROZEN. Non-breaking (byte-identical to 0.10.0); switched the floor pin → exact `==1.0.0` per the stable-substrate posture. Post-1.0 breaking changes ride a bifrost MAJOR + new wire (v0.7+); a v0.6-pinned consumer is stable indefinitely. (Also this session: althing migrated to v0.15.0+ lean-bus / schema v4 — moderation retired, chamber/redis ripped; our tooling auto-updated to 0.17.4.)
|
||||
- `[2026-06-30]` **Worldtree v1.0.0b1→b2 consumer adaptation: eager turn-launch statuses (`v0.18.3` `b2e4901`, `v0.18.4` `e4317f6`).** Worldtree #331 decoupled turn execution from the SSE connection → turn-launch failures now arrive EAGERLY as a status before any stream: 409 `agent_not_available` (pre-b1 a 200 + in-stream error event), 503 retryable. Mapped both in `stream_turn` to typed `SseConnectFailed` subclasses keyed on STATUS, parsing the `{detail:{error_code,message}}` envelope — POST-003 preserved (no synthetic event yielded), existing handlers still catch (the design fork vs yield-an-Error-event was decided by POST-003). **DEFERRED follow-ups** (tracked here; bundle with the v1 coverage-audit): (1) live-prove the 409/503 end-to-end on personal-b2 (now unblocked — personal on b2, my key works there); (2) full `conversation-api-spec.md` markdown re-vendor to the b2 era (ratatoskr vendors the markdown, not the OpenAPI JSON).
|
||||
- `[2026-06-30]` **Verify-against-the-real-spec-before-committing caught a real upstream gap.** Holding the v0.18.3 commit to verify against demo's OpenAPI surfaced that the FROZEN OpenAPI 2.1.0 didn't document the 409/503 the heads-up described (`agent_not_available` was in the ErrorCode enum, but NO 503/turn-launch code). worldtree-dev confirmed it was THEIR gap (#331 added the statuses without extending the #328 `openapi()` override), shipped the fix in **v1.0.0b2 / OpenAPI 2.2.0** (409/503 now enumerated, 503 code finalized as `not_ready`). "The consumer-oracle earning its keep." Lesson: a provider's prose heads-up can diverge from its frozen machine-readable spec — verify the actual spec before committing a consumer adaptation.
|
||||
- `[2026-06-30]` **regard is a DEAD AXIS in Worldtree's emitted affect (caught provider-side; worldtree-dev confirmed + escalated to Vuong).** Across all our affect snapshots, `valence[].regard` is EXACTLY 0.15 regardless of agent/end_user/interaction_count, while familiarity accumulates (vuong 0.18→0.69 over 14 turns). Root cause (worldtree-dev, code-grounded): 0.15 = `base_regard = agreeableness*0.3` (sindra A=0.5); regard's only human-writer `update_regard` early-returns unless an emotion is `about="other"`, but the Vili appraiser's `ViliResponse` schema has NO directedness axis (everything hardcoded `about="situation"`) — producer side lost in the #265 Vili rework; consumer machinery intact. NOT WAD; the fix (reintroduce other-directed classification) is an affect-model change touching every agent + a directedness-classification design call → worldtree-dev filing an issue to Vuong. [the consumer/provider thesis paying off again]
|
||||
- `[2026-06-30]` **v1 coverage-audit kicked off; coverage ledger written (`docs/coverage-map.md`) — the first one.** Every Worldtree v1-FROZEN I/O point × ratatoskr status. Anchored on WT's frozen machine-readable artifacts (OpenAPI **2.2.0** `conversation-api-openapi.json` = 40 REST path-groups + SSE schema = 11 events + bifrost wire v0.6), NOT the stale vendored prose markdown. Result: **SSE 11/11 ✅; Bifrost provider planes 8/8 ✅ live-proven** (covers the full `bifrost.memory.MemoryDataStore` protocol = describe_store/get/get_many/search/upsert_many + delete_many, and affect emit/fetch; **`health` is extended-reference-store-only, NOT in the base protocol → correctly deferred, NOT a gap** — settles the prior "health" ambiguity); **client REST 7/40 ✅ live, 11 ⬜ in-scope, 22 🚫 excluded.**
|
||||
- `[2026-06-30]` **Scope mandate A locked (operator): v1 "done" = every frozen I/O point CLASSIFIED (covered-or-excluded-with-rationale), zero unaccounted — NOT a feature-complete client.** The coverage map is a LEDGER, not a build-everything mandate. Reconciles the 2026-06-19 "consume all I/O" reframe with the 2026-05-20 design-brief's "NOT an admin tool" + deferral negative clauses (which predate both the provider identity and the reframe). Resolved the 11 design-brief-vs-reframe ❓ rows via the debug-observability test (*does a turn flow through it?*): 🚫 search / uploads / pending / embed / judgments (consumer-product + eval utilities); ⬜ transient-characters routing (4) + persona_state-write (Tier-2 frontier). **Frontier Tier 1 (all unblocked except #11):** session-picker + SSE-resume (wrappers `list_sessions`/`reconnect_turn` exist with NO caller — presenter-wiring only) → `GET /capabilities` + `GET /me` → BifrostState/Tools widgets (`GET /admin/sessions/{id}/{bifrost,tools}`, admin-key) → **#11 AdminEvents BLOCKED on `admin.events.read` scope**. The 3 admin-observability widgets + picker + resume were design-brief §5/§4/§8d v1 items that **were never built**.
|
||||
- `[2026-06-30]` **Finding P-1 (pin drift) + pin-remediation PENDING.** We vendor the PROSE markdown (`docs/conversation-api-spec.md`), which is **byte-identical to live WT's** but frozen at v0.35.16-era content (last WT edit 2026-05-31) — it does NOT capture b2: 7 new endpoints (admin/keys/bulk, admin/persona/{archive,erase}, admin/usage, embed, judgments, me/usage), the 409/503 on messages-POST (#331), the unified error envelope (#328), or the SSE schema. **WT's authoritative v1 truth is now the FROZEN OpenAPI 2.2.0 + SSE-schema JSON** (`Worldtree/docs/v1-schema-freeze-manifest.md`). So the previously-deferred "re-vendor markdown to b2" is a **near-no-op** (markdown content identical). **Pending operator nod:** re-pin to the machine-readable artifacts (recommended — drift-checkable via `canonical_drift.py`, makes the coverage map reproducible vs a frozen diffable target) vs markdown-only. Deferred (not auto-applied) because it adds vendored artifacts + a canonical-sync pin = substrate change with CI-gating reach. **→ RESOLVED 2026-06-30 (operator: "a then b").** Vendored `conversation-api-openapi.json` (2.2.0) + `conversation-api-sse-events.schema.json` + re-copied the prose markdown; pinned all three in `.corviduo-canonicals.toml` (OpenAPI+SSE = strict drift gates, markdown = `tolerate_drift` reference); advanced `worldtree-spec-rev` f1b59f8→5810a26 + `worldtree-version` v0.29.0(STALE, never bumped from the v0.35.16 pin)→v1.0.0b2 + `pinned-on`→2026-06-30; SPEC-PIN.md history row added. `canonical_drift.py` green (10/10). `pin:`-only, no version bump (no client-facing code change; the b2 409/503 + error-envelope were already consumed in v0.18.3/.4).
|
||||
|
||||
- `[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).
|
||||
|
||||
_41 older entries (2026-05-* — the original debug-TUI/web build era) archived to archival-memory.md._
|
||||
|
||||
@@ -173,5 +187,7 @@ defense against re-attempting the same cul-de-sac.
|
||||
- `[2026-06-19]` **heid-code-review pulled MORE weight than its own "marginal" self-assessment.** The panel returned zero drift, but its single test-fidelity finding CASCADED into 2 real latent-bug fixes when applied (the memory `check_same_thread` bug + Regin's op-feed field-name bug). **Lesson: a contract-fidelity nudge can transitively expose bugs the test never reached — don't dismiss a "marginal" finding by its count.**
|
||||
|
||||
- `[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.
|
||||
|
||||
_18 older entries (2026-05-* — the original debug-TUI/web build era) archived to archival-memory.md._
|
||||
|
||||
+5
-5
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
|
||||
|
||||
[project]
|
||||
name = "ratatoskr"
|
||||
version = "0.18.1"
|
||||
version = "0.18.7"
|
||||
description = "Worldtree Conversation API debug TUI — multi-pane observability dashboard"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.12"
|
||||
@@ -30,7 +30,7 @@ web = [
|
||||
# from the debug TUI. Recipe: bifrost/docs/implementing-a-consumer.md.
|
||||
provider = [
|
||||
"ratatoskr[web]", # reuse the starlette + uvicorn ASGI stack
|
||||
"bifrost>=0.10.0", # consumer engines + library (0.10.0: build_combined_app (#18) + mandatory affect.fetch, strong-or-absent; 0.8.0/wire-v0.6: scope_all/scope_any split (#11); 0.7.0/v0.5: agent_self)
|
||||
"bifrost==1.0.0", # consumer engines + library. 1.0.0 = first STABLE release, wire v0.6 FROZEN (non-breaking repin from >=0.10.0; build_combined_app #18 + mandatory affect.fetch; 0.8.0/v0.6 scope_all/scope_any #11; 0.7.0/v0.5 agent_self)
|
||||
"jsonschema>=4", # bifrost runtime dep — envelope validation
|
||||
"sqlite-vec>=0.1.6", # vector index for the memory plane (vec0 virtual table)
|
||||
]
|
||||
@@ -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 = "f1b59f8cd6fe41e497d0be9dad9d3110451f0d9a"
|
||||
worldtree-version = "v0.29.0"
|
||||
pinned-on = "2026-05-26"
|
||||
worldtree-spec-rev = "5810a26b38a5ea6630892f9a39756f57c5b7b41e"
|
||||
worldtree-version = "v1.0.0b2"
|
||||
pinned-on = "2026-06-30"
|
||||
|
||||
# Bifrost lives on the auth-gated gitea PyPI index (not public PyPI).
|
||||
# uv reads the credential from UV_INDEX_GITEA_USERNAME / _PASSWORD or ~/.netrc.
|
||||
|
||||
+10
-4
@@ -47,7 +47,7 @@ from ratatoskr.sse_client import (
|
||||
TurnIdFlip,
|
||||
WorkerPhase,
|
||||
cancel_turn,
|
||||
stream_turn,
|
||||
stream_turn_resilient,
|
||||
)
|
||||
|
||||
|
||||
@@ -142,9 +142,15 @@ def _parse_args(argv: list[str] | None) -> ParsedArgs:
|
||||
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")
|
||||
raise UsageError("--session and --new are mutually exclusive")
|
||||
if not ns.session and not ns.new:
|
||||
raise UsageError("pass exactly one of --session or --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:
|
||||
@@ -393,7 +399,7 @@ async def _run_turn(
|
||||
cancelling = False
|
||||
sigint_task: asyncio.Task[bool] | None = None
|
||||
cancel_task: asyncio.Task[None] | None = None # strong ref to fire-and-forget cancel
|
||||
aiter_obj = stream_turn(client, session_id, content).__aiter__()
|
||||
aiter_obj = stream_turn_resilient(client, session_id, content).__aiter__()
|
||||
|
||||
try:
|
||||
while True:
|
||||
|
||||
@@ -215,6 +215,59 @@ class SseConnectFailed(Exception):
|
||||
self.body = body
|
||||
|
||||
|
||||
class AgentNotAvailable(SseConnectFailed):
|
||||
"""Eager 409 from the turn POST (Worldtree v1.0.0b1, #331): the session's
|
||||
agent is unavailable, so the turn never launched. Pre-b1 this arrived as a
|
||||
200 stream + an in-stream `error` event; b1 surfaces it eagerly. Subclass of
|
||||
SseConnectFailed so existing `except SseConnectFailed` handlers still catch
|
||||
it — this type just adds the parsed `error_code` + `message`."""
|
||||
|
||||
def __init__(self, *, body: bytes, error_code: str, message: str) -> None:
|
||||
super().__init__(status=409, body=body)
|
||||
self.error_code = error_code
|
||||
self.message = message
|
||||
|
||||
|
||||
class TurnLaunchUnavailable(SseConnectFailed):
|
||||
"""Eager 503 from the turn POST (Worldtree v1.0.0b1, #331): a transient
|
||||
turn-launch failure (loop shutdown / resource exhaustion). RETRYABLE.
|
||||
Subclass of SseConnectFailed; adds `error_code`, `message`, `retryable`."""
|
||||
|
||||
retryable = True
|
||||
|
||||
def __init__(self, *, body: bytes, error_code: str, message: str) -> None:
|
||||
super().__init__(status=503, body=body)
|
||||
self.error_code = error_code
|
||||
self.message = message
|
||||
|
||||
|
||||
# Canonical error_codes (Worldtree #331 / v1.0.0b2): 409 -> agent_not_available,
|
||||
# 503 -> not_ready (retryable; re-pinned from internal_error). Used only as a
|
||||
# fallback default when the body omits error_code — the real code is surfaced
|
||||
# verbatim from the {detail:{error_code,message}} envelope.
|
||||
_EAGER_TURN_FAILURE_CODE = {409: "agent_not_available", 503: "not_ready"}
|
||||
|
||||
|
||||
def _eager_failure_fields(body: bytes, status: int) -> tuple[str, str]:
|
||||
"""Extract (error_code, message) from an eager turn-launch failure body
|
||||
(#331). Accepts the Worldtree `{"detail": {...}}` envelope OR a flat
|
||||
`{error_code, message}`; falls back to a status-derived default code and a
|
||||
generic message when the body is absent / non-JSON / malformed."""
|
||||
try:
|
||||
parsed: Any = json.loads(body)
|
||||
except (json.JSONDecodeError, ValueError):
|
||||
parsed = None
|
||||
src: dict[str, Any] = {}
|
||||
if isinstance(parsed, dict):
|
||||
detail = parsed.get("detail")
|
||||
src = detail if isinstance(detail, dict) else parsed
|
||||
code = src.get("error_code") or _EAGER_TURN_FAILURE_CODE[status]
|
||||
message = src.get("message")
|
||||
if not isinstance(message, str):
|
||||
message = f"turn launch failed (HTTP {status})"
|
||||
return str(code), message
|
||||
|
||||
|
||||
class SseConnectionDropped(Exception):
|
||||
"""Raised when the HTTP/SSE connection dropped mid-stream."""
|
||||
|
||||
@@ -434,6 +487,19 @@ async def stream_turn(
|
||||
f"/sessions/{session_id}/messages",
|
||||
json={"content": content},
|
||||
) as event_source:
|
||||
# Worldtree v1.0.0b1 (#331): turn-launch failures arrive EAGERLY as a
|
||||
# status before any stream — 409 agent_not_available (pre-b1 this was a
|
||||
# 200 + in-stream `error` event), 503 a transient retryable launch
|
||||
# failure. Surface them as typed SseConnectFailed subclasses carrying
|
||||
# error_code; request-level non-2xx (404 session_not_found, etc.) stay
|
||||
# generic SseConnectFailed.
|
||||
status = event_source.response.status_code
|
||||
if status in (409, 503):
|
||||
body = await event_source.response.aread()
|
||||
code, message = _eager_failure_fields(body, status)
|
||||
if status == 409:
|
||||
raise AgentNotAvailable(body=body, error_code=code, message=message)
|
||||
raise TurnLaunchUnavailable(body=body, error_code=code, message=message)
|
||||
try:
|
||||
event_source.response.raise_for_status()
|
||||
except httpx.HTTPStatusError as exc:
|
||||
@@ -483,6 +549,55 @@ async def reconnect_turn(
|
||||
yield event
|
||||
|
||||
|
||||
async def stream_turn_resilient(
|
||||
client: httpx.AsyncClient,
|
||||
session_id: str,
|
||||
content: str,
|
||||
*,
|
||||
max_reconnects: int = 5,
|
||||
) -> AsyncIterator[Event]:
|
||||
"""Resume-orchestration wrapper over stream_turn + reconnect_turn.
|
||||
|
||||
Yields ONE continuous Event stream; on `SseConnectionDropped` (mid-stream
|
||||
drop or clean EOF before a terminal), resumes from the last-seen `sse_id`
|
||||
via `reconnect_turn`, up to `max_reconnects` times, until a terminal
|
||||
Done/Error/Cancelled arrives. The single shared surface presenters consume
|
||||
for resilient streaming (design-brief §8b: "share the consumer, branch the
|
||||
presenter"). Cross-process resume stays deferred to v2 (§8d): `last_seen`
|
||||
lives only in this generator's frame. See contract FN stream_turn_resilient
|
||||
(amendment 2026-06-30).
|
||||
"""
|
||||
assert client is not None
|
||||
assert session_id and isinstance(session_id, str)
|
||||
assert content and isinstance(content, str)
|
||||
assert isinstance(max_reconnects, int) and max_reconnects >= 0
|
||||
|
||||
last_seen: SseId | None = None
|
||||
reconnects = 0
|
||||
gen = stream_turn(client, session_id, content)
|
||||
while True:
|
||||
try:
|
||||
async for event in gen:
|
||||
last_seen = event.sse_id
|
||||
yield event
|
||||
return # generator completed cleanly → terminal event reached (INV-001)
|
||||
except SseConnectionDropped as drop:
|
||||
# Prefer the id we tracked from a yielded event; fall back to the one
|
||||
# the drop carries (covers a drop on the very first frame). Non-drop
|
||||
# reconnect failures (412/410/400/flip) are NOT caught here — they
|
||||
# propagate per the contract's "surface, not recover" policy.
|
||||
seen = last_seen or drop.last_seen_sse_id
|
||||
if seen is None or reconnects >= max_reconnects:
|
||||
raise
|
||||
reconnects += 1
|
||||
gen = reconnect_turn(
|
||||
client,
|
||||
session_id,
|
||||
content,
|
||||
last_event_id=f"{seen.turn_id}:{seen.seq}",
|
||||
)
|
||||
|
||||
|
||||
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)
|
||||
|
||||
+160
-6
@@ -42,9 +42,11 @@ from ratatoskr.sessions import (
|
||||
BifrostHandshakeFailed,
|
||||
PersonaNotConfigured,
|
||||
SessionApiFailed,
|
||||
SessionInfo,
|
||||
create_session,
|
||||
get_persona_state,
|
||||
list_agents,
|
||||
list_sessions,
|
||||
)
|
||||
from ratatoskr.sse_client import (
|
||||
AffectUpdate,
|
||||
@@ -68,7 +70,7 @@ from ratatoskr.sse_client import (
|
||||
TurnIdFlip,
|
||||
WorkerPhase,
|
||||
cancel_turn,
|
||||
stream_turn,
|
||||
stream_turn_resilient,
|
||||
)
|
||||
|
||||
# ---- Australis theme (https://github.com/lkraven/australis) ------------------
|
||||
@@ -798,6 +800,128 @@ 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."""
|
||||
|
||||
@@ -1318,7 +1442,7 @@ class RatatoskrApp(App[int]):
|
||||
pass
|
||||
|
||||
try:
|
||||
async for event in stream_turn(self.client, self.session_id, content):
|
||||
async for event in stream_turn_resilient(self.client, self.session_id, content):
|
||||
if self.active_turn_id is None:
|
||||
self.active_turn_id = event.sse_id.turn_id
|
||||
self._write_turn_headers(self.active_turn_id)
|
||||
@@ -1430,8 +1554,9 @@ 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 +1592,35 @@ 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)
|
||||
@@ -1551,8 +1705,8 @@ async def _resolve_then_run(args: ParsedArgs) -> int:
|
||||
session_id = info.session_id
|
||||
agent_id: str | None = info.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()
|
||||
|
||||
@@ -50,7 +50,7 @@ from ratatoskr.sse_client import (
|
||||
SseConnectionDropped,
|
||||
TurnIdFlip,
|
||||
cancel_turn,
|
||||
stream_turn,
|
||||
stream_turn_resilient,
|
||||
)
|
||||
|
||||
|
||||
@@ -291,7 +291,7 @@ async def _stream_turn_endpoint(request: Request) -> StreamingResponse:
|
||||
try:
|
||||
handle.status = "streaming"
|
||||
try:
|
||||
async for event in stream_turn(client, session_id, handle.content):
|
||||
async for event in stream_turn_resilient(client, session_id, handle.content):
|
||||
# v0.16.0: capture the upstream (Worldtree-assigned)
|
||||
# turn_id from the first event so cancel paths target
|
||||
# the real upstream turn, not our local counter.
|
||||
|
||||
+30
-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(
|
||||
|
||||
+222
-1
@@ -6,6 +6,7 @@ import respx
|
||||
|
||||
from ratatoskr.sse_client import (
|
||||
AffectUpdate,
|
||||
AgentNotAvailable,
|
||||
AwaitingLlmFirstToken,
|
||||
CancelAlreadyCompleted,
|
||||
Cancelled,
|
||||
@@ -18,13 +19,16 @@ from ratatoskr.sse_client import (
|
||||
ResumeBufferExpired,
|
||||
ResumeTurnFinished,
|
||||
SseConnectFailed,
|
||||
SseConnectionDropped,
|
||||
SseId,
|
||||
Text,
|
||||
TurnIdFlip,
|
||||
TurnLaunchUnavailable,
|
||||
_parse_sse_id,
|
||||
cancel_turn,
|
||||
reconnect_turn,
|
||||
stream_turn,
|
||||
stream_turn_resilient,
|
||||
)
|
||||
|
||||
_DONE_42_6 = {
|
||||
@@ -49,6 +53,36 @@ def _sse_chunk(sse_id: str, body: dict[str, object]) -> bytes:
|
||||
return f"id: {sse_id}\ndata: {json.dumps(body)}\n\n".encode()
|
||||
|
||||
|
||||
_EVENT_STREAM = {"content-type": "text/event-stream"}
|
||||
|
||||
|
||||
class _DropStream(httpx.AsyncByteStream):
|
||||
"""Yield the given chunks, then raise a mid-stream drop (RemoteProtocolError).
|
||||
|
||||
Mirrors the inline `_DropAfter` used by TestStreamTurn.test_connection_drop;
|
||||
hoisted to module scope because the resilient-wrapper tests reuse it.
|
||||
"""
|
||||
|
||||
def __init__(self, chunks: list[bytes]) -> None:
|
||||
self._chunks = chunks
|
||||
|
||||
async def __aiter__(self): # type: ignore[no-untyped-def]
|
||||
for c in self._chunks:
|
||||
yield c
|
||||
raise httpx.RemoteProtocolError("simulated mid-stream drop")
|
||||
|
||||
async def aclose(self) -> None:
|
||||
return None
|
||||
|
||||
|
||||
def _drop_response(chunks: list[bytes]) -> httpx.Response:
|
||||
return httpx.Response(200, headers=_EVENT_STREAM, stream=_DropStream(chunks))
|
||||
|
||||
|
||||
def _stream_response(content: bytes) -> httpx.Response:
|
||||
return httpx.Response(200, headers=_EVENT_STREAM, content=content)
|
||||
|
||||
|
||||
class TestParseSseId:
|
||||
def test_happy_simple(self) -> None:
|
||||
"""happy_simple [happy,tracer]: '42:3' -> SseId(turn_id=42, seq=3)."""
|
||||
@@ -415,8 +449,9 @@ class TestStreamTurn:
|
||||
async def test_connect_failed_body_truncated(self) -> None:
|
||||
"""ERROR_ROUTING: SseConnectFailed.body is truncated to <= 1024 bytes."""
|
||||
big_body = b"x" * 5000
|
||||
# 500 (not 409/503 — those are now eager turn-launch carve-outs, #331).
|
||||
respx.post("https://w.example/sessions/s1/messages").mock(
|
||||
return_value=httpx.Response(503, content=big_body)
|
||||
return_value=httpx.Response(500, content=big_body)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(SseConnectFailed) as exc_info:
|
||||
@@ -424,6 +459,71 @@ class TestStreamTurn:
|
||||
assert len(exc_info.value.body) <= 1024
|
||||
assert exc_info.value.body == big_body[:1024]
|
||||
|
||||
@respx.mock
|
||||
async def test_eager_409_agent_not_available(self) -> None:
|
||||
"""b1 #331: eager 409 -> AgentNotAvailable (SseConnectFailed subclass) with
|
||||
typed error_code; the turn never streams."""
|
||||
respx.post("https://w.example/sessions/s1/messages").mock(
|
||||
return_value=httpx.Response(
|
||||
409,
|
||||
json={
|
||||
"detail": {
|
||||
"error_code": "agent_not_available",
|
||||
"message": "agent ratatoskr:sindra is unavailable",
|
||||
}
|
||||
},
|
||||
)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(AgentNotAvailable) as exc:
|
||||
_ = [e async for e in stream_turn(client, "s1", "hi")]
|
||||
assert exc.value.status == 409
|
||||
assert exc.value.error_code == "agent_not_available"
|
||||
assert "unavailable" in exc.value.message
|
||||
assert isinstance(exc.value, SseConnectFailed) # existing handlers still catch
|
||||
|
||||
@respx.mock
|
||||
async def test_eager_503_turn_launch_unavailable_retryable(self) -> None:
|
||||
"""b1 #331: eager 503 -> TurnLaunchUnavailable (retryable, SseConnectFailed subclass)."""
|
||||
respx.post("https://w.example/sessions/s1/messages").mock(
|
||||
return_value=httpx.Response(
|
||||
503,
|
||||
json={"error_code": "turn_launch_failed", "message": "resource exhausted"},
|
||||
)
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(TurnLaunchUnavailable) as exc:
|
||||
_ = [e async for e in stream_turn(client, "s1", "hi")]
|
||||
assert exc.value.status == 503
|
||||
assert exc.value.retryable is True
|
||||
assert exc.value.error_code == "turn_launch_failed"
|
||||
assert isinstance(exc.value, SseConnectFailed)
|
||||
|
||||
@respx.mock
|
||||
async def test_eager_409_non_json_body_defaults(self) -> None:
|
||||
"""b1 #331: eager 409 with a non-JSON body -> AgentNotAvailable with the
|
||||
status-derived default error_code."""
|
||||
respx.post("https://w.example/sessions/s1/messages").mock(
|
||||
return_value=httpx.Response(409, content=b"<html>nope</html>")
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(AgentNotAvailable) as exc:
|
||||
_ = [e async for e in stream_turn(client, "s1", "hi")]
|
||||
assert exc.value.error_code == "agent_not_available"
|
||||
|
||||
@respx.mock
|
||||
async def test_eager_503_non_json_body_defaults_not_ready(self) -> None:
|
||||
"""b2: eager 503 with a non-JSON body -> TurnLaunchUnavailable with the
|
||||
canonical default error_code `not_ready`."""
|
||||
respx.post("https://w.example/sessions/s1/messages").mock(
|
||||
return_value=httpx.Response(503, content=b"<html>nope</html>")
|
||||
)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(TurnLaunchUnavailable) as exc:
|
||||
_ = [e async for e in stream_turn(client, "s1", "hi")]
|
||||
assert exc.value.error_code == "not_ready"
|
||||
assert exc.value.retryable is True
|
||||
|
||||
@respx.mock
|
||||
async def test_no_text_aggregation(self) -> None:
|
||||
"""no_text_aggregation: consumer yields each text event separately; no concat."""
|
||||
@@ -1040,3 +1140,124 @@ class TestAwaitingLlmFirstToken:
|
||||
elapsed = [b.elapsed_ms_since_building_prompt for b in beats]
|
||||
assert elapsed == sorted(elapsed) # monotonically increasing
|
||||
assert all(b.turn_id == 42 for b in beats)
|
||||
|
||||
|
||||
_URL = "https://w.example/sessions/s1/messages"
|
||||
|
||||
|
||||
class TestStreamTurnResilient:
|
||||
"""docs/contracts/issues/1.contract.md FN stream_turn_resilient (amendment 2026-06-30)."""
|
||||
|
||||
@respx.mock
|
||||
async def test_happy_no_drop(self) -> None:
|
||||
"""happy_no_drop [happy]: clean stream passes through; no reconnect issued."""
|
||||
stream = _sse_chunk("42:1", {"type": "text", "content": "a"}) + _sse_chunk(
|
||||
"42:2", _DONE_42_6
|
||||
)
|
||||
route = respx.post(_URL).mock(return_value=_stream_response(stream))
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
events = [e async for e in stream_turn_resilient(client, "s1", "hi")]
|
||||
assert [e.sse_id for e in events] == [SseId(42, 1), SseId(42, 2)]
|
||||
assert isinstance(events[-1], Done)
|
||||
assert route.call_count == 1 # POST-001: no reconnect on a clean stream
|
||||
|
||||
@respx.mock
|
||||
async def test_resume_after_one_drop(self) -> None:
|
||||
"""resume_after_one_drop [tracer]: a mid-stream drop resumes via reconnect; one stream."""
|
||||
first = _drop_response([_sse_chunk("42:1", {"type": "text", "content": "a"})])
|
||||
resume = _stream_response(
|
||||
_sse_chunk("42:2", {"type": "text", "content": "b"})
|
||||
+ _sse_chunk("42:3", _DONE_42_6)
|
||||
)
|
||||
route = respx.post(_URL).mock(side_effect=[first, resume])
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
events = [e async for e in stream_turn_resilient(client, "s1", "hi")]
|
||||
assert [e.sse_id for e in events] == [SseId(42, 1), SseId(42, 2), SseId(42, 3)]
|
||||
assert isinstance(events[-1], Done)
|
||||
assert route.call_count == 2
|
||||
# POST-003: reconnect carries the last yielded pre-drop event's id.
|
||||
assert route.calls[1].request.headers.get("Last-Event-ID") == "42:1"
|
||||
# PRE/wire: first attempt does NOT carry a Last-Event-ID.
|
||||
assert route.calls[0].request.headers.get("Last-Event-ID") is None
|
||||
|
||||
@respx.mock
|
||||
async def test_resume_after_clean_eof(self) -> None:
|
||||
"""resume_after_clean_eof: a clean EOF before terminal also triggers resume (INV-001)."""
|
||||
first = _stream_response(_sse_chunk("42:1", {"type": "text", "content": "a"}))
|
||||
resume = _stream_response(_sse_chunk("42:2", _DONE_42_6))
|
||||
route = respx.post(_URL).mock(side_effect=[first, resume])
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
events = [e async for e in stream_turn_resilient(client, "s1", "hi")]
|
||||
assert [e.sse_id for e in events] == [SseId(42, 1), SseId(42, 2)]
|
||||
assert isinstance(events[-1], Done)
|
||||
assert route.calls[1].request.headers.get("Last-Event-ID") == "42:1"
|
||||
|
||||
@respx.mock
|
||||
async def test_two_drops_then_done(self) -> None:
|
||||
"""two_drops_then_done: two transient drops, third attempt completes; ids thread through."""
|
||||
a1 = _drop_response([_sse_chunk("42:1", {"type": "text", "content": "a"})])
|
||||
a2 = _drop_response([_sse_chunk("42:2", {"type": "text", "content": "b"})])
|
||||
a3 = _stream_response(_sse_chunk("42:3", _DONE_42_6))
|
||||
route = respx.post(_URL).mock(side_effect=[a1, a2, a3])
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
events = [e async for e in stream_turn_resilient(client, "s1", "hi")]
|
||||
assert [e.sse_id for e in events] == [SseId(42, 1), SseId(42, 2), SseId(42, 3)]
|
||||
assert route.call_count == 3
|
||||
assert route.calls[1].request.headers.get("Last-Event-ID") == "42:1"
|
||||
assert route.calls[2].request.headers.get("Last-Event-ID") == "42:2"
|
||||
|
||||
@respx.mock
|
||||
async def test_unresumable_zero_event_drop(self) -> None:
|
||||
"""unresumable_zero_event_drop [adversarial]: drop before any event → propagate."""
|
||||
route = respx.post(_URL).mock(side_effect=[_drop_response([])])
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(SseConnectionDropped):
|
||||
_ = [e async for e in stream_turn_resilient(client, "s1", "hi")]
|
||||
assert route.call_count == 1 # no id to resume from → no reconnect
|
||||
|
||||
@respx.mock
|
||||
async def test_max_reconnects_exhausted(self) -> None:
|
||||
"""max_reconnects_exhausted [adversarial]: every attempt drops; budget caps reconnects."""
|
||||
side = [
|
||||
_drop_response([_sse_chunk(f"42:{n}", {"type": "text", "content": "x"})])
|
||||
for n in (1, 2, 3)
|
||||
]
|
||||
route = respx.post(_URL).mock(side_effect=side)
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(SseConnectionDropped):
|
||||
_ = [
|
||||
e
|
||||
async for e in stream_turn_resilient(
|
||||
client, "s1", "hi", max_reconnects=2
|
||||
)
|
||||
]
|
||||
assert route.call_count == 3 # initial + 2 reconnects, then give up
|
||||
|
||||
@respx.mock
|
||||
async def test_zero_budget_no_resume(self) -> None:
|
||||
"""zero_budget_no_resume [adversarial]: max_reconnects=0 → first drop propagates."""
|
||||
first = _drop_response([_sse_chunk("42:1", {"type": "text", "content": "a"})])
|
||||
route = respx.post(_URL).mock(side_effect=[first])
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
with pytest.raises(SseConnectionDropped):
|
||||
_ = [
|
||||
e
|
||||
async for e in stream_turn_resilient(
|
||||
client, "s1", "hi", max_reconnects=0
|
||||
)
|
||||
]
|
||||
assert route.call_count == 1
|
||||
|
||||
@respx.mock
|
||||
async def test_buffer_expired_propagates(self) -> None:
|
||||
"""buffer_expired_propagates [error]: a 412 on reconnect surfaces, not retried."""
|
||||
first = _drop_response([_sse_chunk("42:1", {"type": "text", "content": "a"})])
|
||||
resume = httpx.Response(412, json={"turn_id": 42, "buffered_from_seq": 7})
|
||||
route = respx.post(_URL).mock(side_effect=[first, resume])
|
||||
async with httpx.AsyncClient(base_url="https://w.example") as client:
|
||||
collected: list[object] = []
|
||||
with pytest.raises(ResumeBufferExpired):
|
||||
async for e in stream_turn_resilient(client, "s1", "hi"):
|
||||
collected.append(e)
|
||||
assert [e.sse_id for e in collected] == [SseId(42, 1)] # type: ignore[attr-defined]
|
||||
assert route.call_count == 2
|
||||
|
||||
@@ -2945,3 +2945,225 @@ 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
|
||||
|
||||
@@ -190,14 +190,14 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "bifrost"
|
||||
version = "0.10.0"
|
||||
version = "1.0.0"
|
||||
source = { registry = "https://gitea.phasefinal.com/api/packages/vh/pypi/simple/" }
|
||||
dependencies = [
|
||||
{ name = "jsonschema" },
|
||||
]
|
||||
sdist = { url = "https://gitea.phasefinal.com/api/packages/vh/pypi/files/bifrost/0.10.0/bifrost-0.10.0.tar.gz", hash = "sha256:aba1869dba68d921f2e0be8fb560277073da09ec2ad5f410e226cacd5e84fe1a" }
|
||||
sdist = { url = "https://gitea.phasefinal.com/api/packages/vh/pypi/files/bifrost/1.0.0/bifrost-1.0.0.tar.gz", hash = "sha256:93130d68dfd9868580a4514277996ba176837972b9e42129eda8bb03ad3b18b9" }
|
||||
wheels = [
|
||||
{ url = "https://gitea.phasefinal.com/api/packages/vh/pypi/files/bifrost/0.10.0/bifrost-0.10.0-py3-none-any.whl", hash = "sha256:88adbce23fa8840a14f9493e4f0cf6f9320f4950845f7a6080387defe574a5cc" },
|
||||
{ url = "https://gitea.phasefinal.com/api/packages/vh/pypi/files/bifrost/1.0.0/bifrost-1.0.0-py3-none-any.whl", hash = "sha256:1a53baa2b0596b7c418e2d82e3eeee0f13054604d78b592609ee1aff90dccac2" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -1052,7 +1052,7 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "ratatoskr"
|
||||
version = "0.18.1"
|
||||
version = "0.18.7"
|
||||
source = { editable = "." }
|
||||
dependencies = [
|
||||
{ name = "httpx" },
|
||||
@@ -1086,7 +1086,7 @@ web = [
|
||||
|
||||
[package.metadata]
|
||||
requires-dist = [
|
||||
{ name = "bifrost", marker = "extra == 'provider'", specifier = ">=0.10.0", index = "https://gitea.phasefinal.com/api/packages/vh/pypi/simple/" },
|
||||
{ name = "bifrost", marker = "extra == 'provider'", specifier = "==1.0.0", index = "https://gitea.phasefinal.com/api/packages/vh/pypi/simple/" },
|
||||
{ name = "httpx", specifier = ">=0.27" },
|
||||
{ name = "httpx-sse", specifier = ">=0.4" },
|
||||
{ name = "jsonschema", marker = "extra == 'provider'", specifier = ">=4" },
|
||||
|
||||
Reference in New Issue
Block a user