memory: snapshot — #18 D2 SHIPPED+PUSHED (v0.17.14, 39eebd1): web pane renders live PAD/valence from our :8390 store, persona-telemetry gap closed; full #17+#18 arc now on origin. D1 (composite :8392) PARKED on bifrost build_combined_app (~v0.9.0, design locked, after WT #289). FR-1 RESOLVED — composite is bifrost-only, ZERO WT change (single-endpoint caps-routed, worldtree-dev code-verified). New decisions: #18 split + Option-C canonical-surface routing; D2 TDD + heid-code-review (1 INV-001 drift + 4 test-gaps fixed). Foot-guns: rationalized-away a known INV-001 deviation that only the post-impl cross-model review caught; latent sqlite check_same_thread bug exposed by the HTTP read route. FOOT-GUN: running :8390/:8765 are PRE-#18 code — restart with new code + RATATOSKR_AFFECT_READ_URL to see D2 live.
This commit is contained in:
+39
-30
@@ -39,37 +39,39 @@ upstream API key stays server-side (INV-003).
|
||||
|
||||
## Current state / in-flight
|
||||
|
||||
_As of 2026-06-18 (PM):_
|
||||
_As of 2026-06-19:_
|
||||
|
||||
**#17 SHIPPED END-TO-END + LIVE-SMOKE PROVEN.** Bifrost-binding the chat client
|
||||
(self-drive + observe) is DONE across CLI/TUI/web — 6 commits `v0.17.8`→`v0.17.13`,
|
||||
full suite **470 green**, **NOT pushed** (operator's call). Slices: (1) `create_session`
|
||||
bind primitive (`7be162e`); (2) dispatch-layer op-feed `ratatoskr.provider.opfeed`
|
||||
(`8ebe227`); (3a) CLI `--bifrost-plane`/`--bifrost-url` (`0bebad7`); (3b) TUI
|
||||
pre-alt-screen (`016defc`); (3c) web server-side bind + UI plane selector
|
||||
(`2806aba`+`179a8df`). **Live smoke:** a bound CLI→sindra session vs personal `:8081`
|
||||
→ handshake 200 → op-feed captured 2 recall searches with the EXACT bound session_id
|
||||
(`2c0c7482`) carrying `scope_any=[{end_user},{agent_self:ratatoskr:sindra}]` @ top_k=128
|
||||
(the #297/#298 union recall, observed provider-side). #17's whole thesis validated:
|
||||
ratatoskr owns both ends → sees the round-trip.
|
||||
**#18 DELIVERABLE 2 SHIPPED + PUSHED — the persona-telemetry gap is CLOSED.** The web
|
||||
pane now renders live PAD/valence for Tier-3 agents from OUR `:8390` affect store
|
||||
(`v0.17.14`, `39eebd1`, suite **482 green**, **pushed to origin**). Three pieces:
|
||||
provider read route `GET /affect/state/{agent_id}` (non-bifrost, added to the affect app
|
||||
via `app.add_route` — keeps `/bifrost/*` top-level + op-feed-skipped); web proxy
|
||||
`GET /api/affect/{agent_id}` (server-supplied `end_user_id`, colon-id `quote()`'d,
|
||||
`RATATOSKR_AFFECT_READ_URL` config, default `127.0.0.1:8390`); pane affect-render
|
||||
(`renderAffectPane`/`loadAffect`, honest pad+valence+emitted_at, labelled "affect", NO
|
||||
fabricated Tier-1 fields, explicit empty-state, 2s post-turn poll). Live-smoke + a
|
||||
Playwright DOM check PROVEN against real sindra/vuong PAD. The push also published the
|
||||
previously-held **#17** arc (`v0.17.8`→`v0.17.13`) — origin/main is now fully caught up.
|
||||
|
||||
**OPERATOR SESSION STATE — background shells UP:** web `:8765` bind-configured
|
||||
(consumer key + `RATATOSKR_PROVIDER_VISIBLE_HOST=10.100.10.50`, sindra + plane
|
||||
selector live); memory provider `:8391` + affect provider `:8390` running WITH the
|
||||
op-feed (`/tmp/opfeed-{memory,affect}.jsonl`); althing light-monitor armed (not signed
|
||||
off). Consumer/owner key = `wt_live_d81b…`. Providers: SQLite + sqlite-vec, separate
|
||||
DB per plane (`memory.db` / `affect.db` at repo root).
|
||||
**#18 DELIVERABLE 1 (composite `:8392` endpoint) — PARKED on bifrost** (tracked Gitea #18).
|
||||
Routed to bifrost-dev for a public `build_combined_app` rather than hand-rolled from
|
||||
bifrost privates (debug-surface-uses-canonical principle). bifrost-dev confirmed it: clean
|
||||
additive minor (~`v0.9.0`), design locked (advertise-by-presence handshake, per-route
|
||||
call-time isolation), slotted AFTER WT #289. FR-1 RESOLVED — composite is bifrost-only,
|
||||
ZERO Worldtree change (single-endpoint caps-routed, worldtree-dev code-verified). NEXT:
|
||||
when bifrost ships `build_combined_app`, **repin + reimplement D1 against it** (per-plane
|
||||
failure status + op-feed plane-per-request derivation already specced in the issue).
|
||||
Nothing blocks on our side.
|
||||
|
||||
**PERSONA TELEMETRY GAP → #18 (the live ask).** The affect bind WORKS — PAD persists
|
||||
to our `:8390` store (vuong session: pleasure +0.146, familiarity climbing 0.18→0.59
|
||||
over 8 turns). But the web persona pane shows "telemetry isn't exposed" because it
|
||||
reads Worldtree `persona_state` (`loadPersona` index.html:707), which 404s for Tier-3
|
||||
(ADR-0009 Tier-1-only), AND a Tier-3 turn emits **zero `affect_update` SSE** (wire-
|
||||
verified). Both Worldtree-side sources are dead for consumer agents; the pane was never
|
||||
wired to render PAD from OUR store. **#18 filed** (composite endpoint + PAD read-endpoint).
|
||||
NEXT proposed: fast-track #18's small PAD-display half (provider read-endpoint → pane
|
||||
renders our store) so telemetry shows now — **awaiting operator go**; composite-endpoint
|
||||
half stays contract-first.
|
||||
**OPERATOR SESSION STATE — running shells are PRE-#18 code (foot-gun).** web `:8765` +
|
||||
affect `:8390` + memory `:8391` are the prior session's background shells running OLD code
|
||||
(no read route; web has no `RATATOSKR_AFFECT_READ_URL`). To see D2 live in the operator's
|
||||
own session, RESTART `:8390` (affect provider, new code → gains the read route) + `:8765`
|
||||
(web, new code + `RATATOSKR_AFFECT_READ_URL=http://127.0.0.1:8390` + `RATATOSKR_END_USER_ID`).
|
||||
This session's live-smoke used THROWAWAY `:8393`/`:8766` instances vs the same `affect.db` to
|
||||
avoid disrupting them. Consumer/owner key = `wt_live_d81b…`; providers SQLite + sqlite-vec,
|
||||
`memory.db`/`affect.db` at repo root (affect.db has live sindra PAD: vuong pleasure 0.146,
|
||||
familiarity 0.589, interaction_count 8).
|
||||
|
||||
**Tier-3 memory PROVEN end-to-end** (earlier this session): `ratatoskr:terse-probe`
|
||||
cold-recalled a seeded user fact (scope_any → 1 hit @ cosine 0.6994), and the verbose
|
||||
@@ -87,9 +89,10 @@ linguistic layer → Worldtree #305). `:8081` runs v0.36.0.
|
||||
honesty-fix FYI `858ba58` — we don't pin/assert it, no-op our side). Heimdall key env-only
|
||||
at `~/.config/ratatoskr/provider.env` (mode 600); rotate via infra-ops. `graphify-out/`
|
||||
runs dirty (auto-regen, not chased). Open issues: #10 (subject migration), #11 (AdminEvents
|
||||
pane), **#18** (composite + PAD-read) — all deferred. Codex-first pilot dormant.
|
||||
pane) — deferred; **#18** (D2 PAD-read SHIPPED `v0.17.14`; D1 composite PARKED on bifrost
|
||||
`build_combined_app`). Codex-first pilot dormant.
|
||||
|
||||
Branch: `main`. Remote: `origin → git@gitea.phasefinal.com:vh/ratatoskr.git`.
|
||||
Branch: `main` (== `origin/main` @ `39eebd1`). Remote: `origin → git@gitea.phasefinal.com:vh/ratatoskr.git`.
|
||||
|
||||
## Recent decisions
|
||||
|
||||
@@ -119,6 +122,10 @@ decision. Captures rationale that won't be obvious from code alone.
|
||||
- `[2026-06-18]` **#17 live-smoke PROVEN — the whole thesis validated.** A self-driven bound CLI session showed, from the PROVIDER side, exactly which memory ops a turn produced (2 recall searches, exact bound session_id, real union-recall scopes). Negative (canary→auth_rejected) NOT live-constructible (Tier-1 agents aren't memory-bindable; a wrong key for an owner-scoped agent fails at agent-auth before the handshake) — covered by the unit test + prior hand-proof.
|
||||
- `[2026-06-18]` **Fixed a pre-existing test-isolation bug exposed by the #17 CLI tests** (`0bebad7`): `test_no_textual_import` did a live `importlib.reload(ratatoskr.cli)` that mutated the shared module in place, breaking class identity (`isinstance`/`pytest.raises`) for every test ordered after it. The real check is the static source-grep; the reload was vestigial → removed. Lesson: never `importlib.reload` a shared module in a test without restoring it.
|
||||
- `[2026-06-18]` **#18 filed (composite endpoint + PAD read-endpoint) — DEFERRED, tracked at Gitea #18.** Two pieces: (1) a composite Bifrost facade (new port e.g. `:8392`) fronting BOTH `:8390`+`:8391` advertising both caps at handshake → one session binds both planes (un-parks the #17 open-q; bifrost reference_server already mounts both planes in one app → thin combined builder; needs per-plane failure-status + the op-feed deriving plane PER-REQUEST from the path instead of its fixed `plane` param). (2) a non-bifrost PAD read-endpoint on the affect provider (recommended over web-reads-`affect.db`-directly) → web persona pane renders PAD/valence from OUR `:8390` store. **Composite half APPROVED by operator ("A is correct"); contract-first next.** **Persona-telemetry diagnosis (verified):** affect bind persists PAD (vuong: pleasure +0.146, familiarity 0.18→0.59 over 8 turns) but the pane reads Tier-3-404 `persona_state` AND Tier-3 emits ZERO `affect_update` SSE (wire-verified) — both WT sources dead, so #18's PAD-display half is the only path. `affect.fetch` over bifrost is RESERVED/blocked but irrelevant (we own the store). Proposed: fast-track the PAD-display half now (awaiting operator go), keep composite contract-first.
|
||||
- `[2026-06-18]` **#18 SPLIT; Deliverable 1 (composite) routed to bifrost — Option C (operator).** D2 (PAD read-endpoint, our-side only) fast-tracked; D1 (composite `:8392` endpoint) routed to bifrost-dev to add a PUBLIC `build_combined_app` rather than hand-roll one from bifrost privates — because ratatoskr is a debug surface that must exercise the CANONICAL surface ("don't go off the reservation"). The Heid framing-panel had unanimously recommended hand-rolling (Option B) — DISCARDED as wrong-grounded (the panel lacked the canonical-surface principle; their own finding that B reaches external/underscore-private names actually vindicated C). bifrost-dev confirmed: clean additive minor (~`v0.9.0`), design locked (advertise-by-store-PRESENCE handshake — no health probe; per-route call-time isolation within a shared ASGI process), slotted after WT #289. [principle → auto-memory `feedback-debug-surface-uses-canonical-surface-only`]
|
||||
- `[2026-06-18]` **FR-1 RESOLVED — the composite premise was unverified, now wire-proven: single-endpoint, caps-routed.** The Heid panel's sharpest catch (Regin): "advertise both caps → Worldtree dispatches both planes to one endpoint" was an ASSUMPTION about WT dispatch, stated as fact. worldtree-dev verified IN CODE: one `BifrostClient` per session (single `_endpoint_url`), handshake `capabilities_granted` parsed INDEPENDENTLY into memory+affect sets, both stores attach off the SAME endpoint iff their cap was granted (`service.py:2597/2703-2713/2745-2751`, `bifrost_client.py ~357-369`; tests `test_tier3_bifrost_{memory,affect}_routing.py`). So D1 is **bifrost-only, ZERO Worldtree change** — #18's "no WT change needed" assumption was correct.
|
||||
- `[2026-06-18]` **#18 D2 implemented via direct in-session TDD (suite 470→482).** Provider read route `GET /affect/state/{agent_id}` added via `app.add_route` (NOT an outer `Mount` — keeps `/bifrost/*` top-level so the existing route test + the op-feed path-check stay valid); web `GET /api/affect/{agent_id}` proxy (server-supplied `end_user_id`, colon-id `quote()`'d, `RATATOSKR_AFFECT_READ_URL`); pane renders the affect-emit shape honestly. Contract `docs/contracts/issues/18.contract.md` (D2-scoped; D1 deferred). **heid-code-review panel (Gróa 5 / Hulda 3 / Regin 0): 1 real INV-001 drift + 4 test-gaps, all fixed.** No contract amendments (code was wrong, contract was right).
|
||||
- `[2026-06-19]` **#18 D2 SHIPPED (`v0.17.14`, `39eebd1`) and the full #17+#18 arc PUSHED to origin.** Live-smoke PROVEN against real data (throwaway `:8393`/`:8766` vs the real `affect.db` → real sindra/vuong PAD through the full web→provider chain; Playwright DOM check confirmed the pane render + the F1 fix — no fabricated "neutral"). The push carried 9 previously-held commits incl. the deliberately-unpushed #17 (`v0.17.8`→`v0.17.13`); origin/main now == `39eebd1`, tag `v0.17.14`.
|
||||
|
||||
_41 older entries (2026-05-* — the original debug-TUI/web build era) archived to archival-memory.md._
|
||||
|
||||
@@ -146,5 +153,7 @@ defense against re-attempting the same cul-de-sac.
|
||||
- `[2026-06-17]` **"Promotion didn't fire → #296" was PREMATURE — twice over.** (1) Polled the op-feed only ~2min, but the upsert landed at ~4min — promotion is async + multi-trigger; watch a longer window. (2) It DID fire; the real bug is extraction QUALITY, not non-firing. "No upsert while a session is live and `<10min` idle" is WAD.
|
||||
- `[2026-06-18]` **Wiping our `:8391` store does NOT reset Worldtree's promotion-side dedup** — a same-agent re-smoke returned `reason_code=noop_duplicate` / `candidate_count=0`: the extractor NEVER RE-RAN, dedup short-circuited against an earlier promotion. **For a clean promotion smoke, use a BRAND-NEW agent + end_user (never-used names).** (Also: `llm_calls_used=0` is NOT the "did the extractor run" tell — `noop_duplicate` is.)
|
||||
- `[2026-06-18]` **`affect.emit` is POST-TURN ASYNC — checking the op-feed immediately after a turn MISSES it.** The Tier-3 affect appraise→emit→rehydrate loop runs AFTER the SSE `[done]`; the emit lands in our `:8390` store seconds later (op-feed grep right after `[done]` showed only the handshake; the `emit stored:true` appeared on a later read). Same family as the async-promotion timing trap. Watch a few-second window post-turn before concluding "no affect emitted." Also wire-verified the same turn: Tier-3 sindra emits ZERO `affect_update` SSE (the persona-strip SSE path never populates for consumer agents) — see the #18 PAD-display decision.
|
||||
- `[2026-06-18]` **Rationalized away a KNOWN contract-invariant deviation during TDD — only the cross-model code-review caught it.** #18 D2's `loadAffect` called `setPersonaStrip(snap)`, which renders `dominant_emotion || "neutral"`; the affect snapshot has no `dominant_emotion`, so it fabricated a "neutral" emotion — violating the very INV-001 ("no synthesized Tier-1 fields") I had WRITTEN. I knew the strip did this and talked myself into it as acceptable. Neither the design panel nor TDD caught it (unit tests don't exercise the JS render); the post-implementation `/heid-code-review` did (Gróa + Hulda both). **Lesson: a known deviation from a contract invariant is drift even when you've rationalized it — flag it, don't argue yourself past it; the post-implementation cross-model review is the backstop for author-rationalized drift, distinct from the design-stage panel.**
|
||||
- `[2026-06-18]` **Latent SQLite thread-safety bug in the affect store, surfaced ONLY by the new HTTP read route.** `open_affect_store` created the connection without `check_same_thread=False`; the bifrost emit path never tripped it (uvicorn's loop ran on the connection's creating thread), but the `TestClient`-driven read route runs handlers off a worker thread → `sqlite3.ProgrammingError`. Fix: `check_same_thread=False` (safe — the event loop serializes access) + explicit `PRAGMA busy_timeout=5000` (don't rely on sqlite3's `timeout=5.0` default). **Lesson: a sqlite-backed ASGI app needs `check_same_thread=False`; the HTTP-layer test exposed what the direct-store-method tests structurally couldn't.**
|
||||
|
||||
_18 older entries (2026-05-* — the original debug-TUI/web build era) archived to archival-memory.md._
|
||||
|
||||
Reference in New Issue
Block a user