ratatoskr/persistent-memory.md

Persistent memory — ratatoskr

Last updated: 2026-08-07

Always check for /tmp/ratatoskr-dev-handoff.md — if it exists and its Written: stamp is under an hour old, read it (it carries the in-flight handoff from the previous session), then delete it. Older than an hour: stale — delete it unread.

This file captures durable intent and supporting evidence (goals, decisions, foot-gun warnings, in-flight state) across context resets. Read it at session start; treat it as one input alongside CLAUDE.md and the auto-memory system, not as the single source of truth.

When durable state shifts enough to warrant capture, run /snapshot and commit alongside the next commit per the persistent-memory commit-along rule in CLAUDE.md.

---

Repo purpose

Ratatoskr is a dev-grade debug-observability TUI for Worldtree's Conversation API. The product IS the observability surface; chat is the input mechanism. Devs run Ratatoskr against a local Worldtree to watch a turn flow through every layer of the system, side-by-side, in one terminal: agent SSE stream, persona/Vili affect dispatch, tool calls, Bifrost handshake state, admin lifecycle events, optional raw server log.

Named after the squirrel that runs up and down Yggdrasil carrying messages between layers. On-the-nose Worldtree resonance (Yggdrasil = the World Tree).

Second identity (since 2026-06-14): the v1 Bifrost Tier-3 consumer/provider — the durable persistence Worldtree writes Tier-3 agent affect (PAD/persona, :8390)

• memory (:8391) into. Lives in src/ratatoskr/provider/, depends on bifrost (provider optional-extra), separate from the conversation-API spec pin. So ratatoskr now owns BOTH ends of the Bifrost round-trip — the lens #17 exploits.

v0.15.0+ sibling browser surface (ratatoskr.web, ratatoskr-web console script): same five-pane debug surface over the same SSE wire, LAN-viewable. Internal-LAN trust model — 0.0.0.0, no auth/TLS/CORS (operator direction). Disciplined regardless: transcript HTML-escapes assistant content (INV-004); upstream API key stays server-side (INV-003).

Current state / in-flight

As of 2026-08-07:

✅ TTS MIGRATED off Zonos → chatterbox-fast (this session; COMMITTED, not pushed). tts.py repointed from the Zonos gateway (:8890 /v1/audio/speech) to chatterbox-fast (http://10.100.79.3:8197/tts — bespoke non-OpenAI {text,voice,format,stream} schema, no auth, 24kHz, infra-ops-verified against image local/chatterbox-fast:v1). Three subsystems DELETED: (1) affect — Turbo has no emotion knob, so PadState/EmotionDials/pad_to_dials + /api/tts p/a fields + browser pad arg are gone (DEC-7 retired; operator-directed "drop it for chatterbox"); (2) client-side chunking — no per-synth cap (gateway chunks internally), so chunk_text/tts_stream_long/_pcm_after_header gone, one tts_stream call voices a whole turn (DEC-10 retired, the mid-stream yielded_any degrade folded into tts_stream); (3) language pin — English-only, no language field (DEC-9 re-purposed, below). Browser SR 44100→24000 (load-bearing correctness fix). Default voice Cora→glados_25s; donut registered lowercase at /refs/donut.wav. 518 suite green, live-smoked (real 24kHz synth + endpoint proxy + bounced ratatoskr-web). Contract donut_voiced_interview.contract.md amended (migration banner; DEC-1/3/8 amended; DEC-7/9/10 retired w/ historical notes). tts.py is the single swap seam; RATATOSKR_TTS_URL overrides (no env pin, uses the code default).

✅ ENGLISH-DRIFT — RESOLVED SERVER-SIDE (this session; fix deployed + operator ear-confirmed). Operator: Donut "swaps to German halfway through." TWO wrong hypotheses before the real cause (infra-ops, thread 01KZEDMJ…): (W1) "English-only, nothing to drift" — falsified; (W2) "multilingual leak → tighten sampling" — I shipped top_k 1000→80/top_p 0.95→0.85/temp 0.8→0.5 and it made it WORSE (tight sampling pulls the garble onset to ~200 chars vs ~300 at default). REAL CAUSE (signal-measured): the Turbo model OVER-RUNS its generation TAIL — garble/dead-air in the final ~2-3s of a long single generation (voiced-tail ZCR 1.58x the middle). The scheduler's unbounded ratchet built 300-600 char mega-chunks landing in that zone; the "German" was tail garble mis-heard (+ shared-3090 OOM garbage, now gone — Zonos moved off the 3090). FIX = infra-ops server-side max_chunk_chars=250 (image :v2), operator ear-confirmed clean audio + clean joins (ZCR 1.58x→0.64x). CONSUMER SIDE (shipped): REVERTED the W2 sampling knobs — gateway_body back to {text,voice,format,stream}, send FULL text + gateway DEFAULT sampling (the curbs fought the :v2 cap); KEPT the /api/tts empty-200→503 guard as hygiene (DEC-9a; OOM itself resolved). Per-request max_chunk_chars override available if per-call tuning ever wanted. Loop CLOSED — nothing pending.

✅ Donut interview character — voice + memory + honesty + query-formulation ALL DONE, on origin. Deleted+redefined on Worldtree's canonical recall branch (personal WT v1.0.0b183). Persona (docs/characters/donut.md) carries three layered behaviors, all committed+pushed: (1) anti-fabrication — her memory IS what reference_knowledge returns; LOW/no-on-target → deflect in character, never confabulate; (2) near-miss LEAD rule (37b67a5) — a weak-but-named candidate → offer the NAME the tool returned ("do you mean The Juicer?"), never invented detail; (3) expand-don't-distill query formulation (2cc670e) — pass the FULL descriptive phrase, enrich toward entity vocab, never boil to bare keywords. Push live edits: python -m ratatoskr.tier3 patch ratatoskr:donut --system-prompt "$(awk '/^## System prompt/{f=1;next} f' docs/characters/donut.md)".

✅ #393 (descriptive-query subject binding) — FULL LIFECYCLE DONE + CLOSED this session. ratatoskr's b172 evidence → filed as Worldtree #393 → our docs/diagnostics/descriptive_query_binding.py = the canonical fixture on the issue → persona-expand lever landed (roid-rage 4/10→9/10 binds, mis-binds 1/6→0/10, anti-fab held) → tool-side directive (b182/b183 reference_knowledge query-desc + bge reranker) stabilizes not lifts (persona owns the niche) → closed. Two-mechanism split: cross-wing ranking dilution (mimir/all-wing) vs fiction-scope subject-selection (Donut fiction-only). Cross-instrument method corrected three of my confident mid-arc reads via the fixture (parametric-leak→mis-grounding, deployment-gap→wing-scope, subject-selection→reformulation-distillation).

✅ Harness fix (2111b1e) — fiction_wing_probe.py fresh-session-per-query (WT #391 workaround) + NFKC/quote-fold on_target. Surfaced Worldtree #391 (reused mimir session → empty after turn 1) — CLOSED upstream (b171/b172 first-iteration tool_choice forcing). Fixture q=capture + wing-scope fold in 4f4b5ad.

⏳ order_by=chapter flag → FILED as Worldtree #397 (DEFERRED to next session's contract pass; our fixture is the measurement instrument). New axis vs #393: narrative/temporal queries ("what was your first encounter in the dungeon") fail — reference_knowledge sorts by RELEVANCE not chronology, and Donut can't reorder her own results (native recall, kb_bridge retired WT #383). provenance.chapter IS on every chunk but the consumer never holds the result set. Operator ruled a order_by=chapter tool flag the clean fix (upstream OK for this one); worldtree-dev accepted → WT #397 runs the full contract pass next session (design fork on the decision list: sort-top-k vs earliest-matching fetch, cross-generation chapter comparability, non-fiction fallback, tool-description discoverability). Expect the contract to reach our review threads. If it ships → point the fixture at it + add a chronological-query persona instruction; if the persona-only fallback is ever needed → honest-floor redirect (deflect-with-a-lead on ungroundable temporal Qs).

🔧 TTS "unavailable" FIXED — stale web server. ratatoskr-web (started Aug 2) predated the POST /api/tts endpoint → 405 → UI read unavailable. Restarted (new PID, detached), POST /api/tts verified 200 + WAV; gateway http://10.100.79.3:8890 healthy. DURABILITY GAP: ratatoskr-web is a bare nohup process, NO supervisor → will re-stale on reboot/crash. A systemd user unit was offered — NOT done, operator's call.

Substrate (this session): branch main, HEAD 2cc670e PUSHED; 5 commits all on origin — 2111b1e (harness fresh-session+quote-fold), 37b67a5 (near-miss LEAD), 6c83a3b (#393 fixture), 4f4b5ad (fixture q=capture+wing-scope), 2cc670e (expand-don't-distill). Personal WT v1.0.0b183 (http://10.250.50.152:8081, both instances). Web on :8765 (restarted). New auto-memory feedback_review_provenance_stays_out_of_artifacts (Heid provenance-leak note — never embed cold-review arm-names/vote-counts in artifacts; forward habit, operator declined retro-sweep).

---

Prior in-flight (2026-08-02, historical — superseded by the block above):

✅ Donut voiced-interview + long-form TTS COMPLETE + PUSHED (d59f907). The whole arc — auto-TTS, KB-bridge → native reference_knowledge, then this session's delivery fixes — is on origin. This session (d59f907, 546 green, long-form live-verified 106.6s / one header):

• Gibberish → English pinned (DEC-9): language:"en-us" on every gateway call (the multilingual model drifted).
• Truncation → client-side chunking (DEC-10): Zonos hard-caps ONE synth at 6144 tok / 71.2s (infra-ops; a delivery-INDEPENDENT 86.3Hz codec constant; max_tokens>6144 400s). chunk_text (paragraph-first, greedy ~75% of cap for prosody, sentence→clause fallback) + tts_stream_long concatenate int16 PCM behind ONE WAV header. /api/tts → POST (DEC-10a) so a long turn rides the body, not a length-capped URL; outer cap 2000→8000.
• Persona → dialogue-only (docs/characters/donut.md, live-patched to ratatoskr:donut): no asterisk RP beats (they were voiced as gibberish) + ALWAYS call reference_knowledge before answering (prompt-level; can't force tool_choice from the define surface).
• Both heid gates triaged + fixed (4-arm panels): untrusted /api/tts body fields degrade never-500 (huge-int PAD OverflowError, non-str agent_id, lone surrogate, whitespace text); lock+client released on EVERY peek escape (was a permanent deadlock); mid-stream-after-commit degrades not raises (yielded_any pivot); non-WAV 200 rejected (RIFF sniff + bounded header scan). +14 regression tests. Contract canonical (DEC-9/10, FN chunk_text/tts_stream_long).

Prior build detail (slices 1-3, the earlier heid gates, P&P #382, KB-bridge retirement to native #383 as v1.0.0b167) is on origin through 608e9a5 and in persistent-memory.d/2026-08-01-donut-voiced-interview-build.md + the git log.

✅ Donut voice + memory + HONESTY all DONE + on origin. reference_knowledge grounds live; artifact coverage shipped; persona is anti-fabrication. The empty-recall was TWO WT-side defects (both fixed): a wing-misfile (re-ingest) and the real root — an INV-361-3 provenance filter dropping concept rows with no note_id/path (Tier-3 blind to ALL concept rows → #384); my search_library-vs-reference_knowledge divergence datum found it. 3-round verify 0/5 → 5/5 thin (97) → 5/5 saturated (705, #385). Then the artifact-coverage gap → #387 (fiction schema had NO item/artifact type; named items like "Enchanted Crown of the Sepsis Whore" rode only incidentally in plot_events) → SHIPPED: b170 adds an artifact type + character-death extraction + participant metadata (#390); the artifacts ground, and Jack (real — dies via Yolanda's backward arrow, was silently unextracted) now grounds too. Full arc → persistent-memory.d/2026-08-03-reference-knowledge-3-round-verify.md. ✅ Donut ANTI-FABRICATION persona (3e12c4d+c0a66fc, pushed): her memory IS what reference_knowledge returns — LOW confidence / no on-target → deflect IN CHARACTER (never confabulate from training); MEDIUM+ → answer. Self-corrects as the KB improves (Jack deflected when absent → grounds now that b170 extracted him). The RETRY-on-LOW idea was TESTED

• REJECTED — it backfires (RRF confidence is inflatable by any DCC-flavored query, manufacturing a MEDIUM to fabricate on; robust fix is tool-side = #389). Live agent recreated via delete+define (PATCH doesn't refresh live context). 🔬 R42 spin-off (operator-directed; ACTIVE peer loop, non-urgent). brokkr-smithy-dev commissioned R42 (fiction-wing retrieval characterization) built on MY probe harness. Shipped docs/diagnostics/fiction_wing_probe.py (04e0293, pushed) as R42's official harness + the re-runnable #389 acceptance gate; conventions adopted verbatim. PENDING (peer-pinged): align arm-1 on-target scoring at R42 Phase-1 authoring; re-run the pinned yardstick when the #389 RRF work lands (pre/post bucket-distribution delta = acceptance signal). Threads: wt-dev 01KZ349M… / brokkr 01KZ421X….

✅ SHIPPED + PUSHED since v0.22.0 (origin at 14bbc2b): the worldtree-sdk cutover (#20, v0.22.0, 7 slices, 494 green — the big one) + bifrost 1.1.5 (3ef3a5e, v0.22.1) + worldtree-sdk 1.0.0→1.1.1→1.1.2 (d3a36f7+0058020 — path-encoding correctness fix + the SSE turn-stream traversal WE caught in their fix) + canonical sync (14bbc2b — added the client-spec-v2 pin, synced OpenAPI/spec forward, additive within the FROZEN v1 wire). The webui runs the current build (v0.22.1) live on :8765 (relaunched this session).

⚙️ VERSIONING CADENCE CHANGED → release-only (operator-ratified 2026-07-30). Retired per-commit bump+tag; version+tag at RELEASES only; between releases, feat:/fix: conventional-commit SHAs. Tier-bar + minor/major approval still apply, at release. Existing ~112 tags left as-is (leave-and-change-forward). (Global CLAUDE.md SemVer §amended to match; this OVERRIDES the per-commit-bump mechanics still described there.)

KEY ADAPTER/CONSUMER FOOT-GUNS (cumulative, still live): SDK reads = open-world dicts → presenters degrade-not- crash at THREE guard levels (container-type isinstance(_,list) / element-type isinstance(m,dict) / top-level isinstance(_,Mapping) before .get); SDK normalizes ALL transport failures to ConnectFailed(status=0) → every caller except ConnectFailed; caller-semantic exceptions a -m CLI catches must NOT live in the -m module (class-identity split; homed in sessions.py). The local_agents index schema v1→v2 bump SILENTLY DROPS pre-cutover consumer agents from the picker (buried Sindra — load_local_agents returns [] on version mismatch; fix = migrate v1→v2 from authoritative WT data). Cutover design → auto-memory project_worldtree_sdk_cutover.

✅ RESOLVED — the "app product" workstreams leave Rata entirely (operator 2026-07-18). No arbo fork, no SillyTavern-on-Rata — a NEW repo (template-dev standing up) takes over BOTH app-product ideas. Rata does NOT fork into anything and is NOT the base for any chat / image-gen app. Rata reverts to its core identity: the Worldtree Conversation-API debug-observability surface + the Bifrost Tier-3 reference impl + the Conversation-API SDK seed / future-consumer. Supersedes the 2026-07-17 "fork Rata for arbo" NEXT-MAJOR plan (that plan is retired; arbo API intel lives in the Recent-decisions detail trail if the new repo wants it).

▶️ Rata's live stake in the Worldtree SDK (#371). The SillyTavern app moved out, but Rata stays the SDK's seed donor + a future consumer: Worldtree owns the official Conversation API SDK (dedicated repo, elevated pre-v1 track, WT #371), seeded from Rata's client spine (sse_client/sessions/tier3); TS ships first, Rata's repin rides the later Python milestone; internal-registry-only. This session Rata shipped the parity-matrix inventory (→ WT docs/sdk/parity-matrix.md 698cfc3, behavioral-spec c999b5f, fixture corpus 3019ee6 = 66 fixtures), the issue-#1 contract drift fix (4bd9abd), and the personal-WT endpoint. WT pipeline: behavioral-spec ✓ / parity-matrix ✓ / fixture-corpus ✓ → next is the codegen spike (d). Three divergences pinned for our eventual repin: D-1 (unknown SSE event → skip+diagnostics-hook vs our current hard-raise), D-2 (open-world enums), D-3 (typed eager 410 session_retired). Full arc → persistent-memory.d/2026-07-18-worldtree-sdk-371-and-sillytavern-app.md.

• SDK fixture-capture: GO GIVEN (operator → worldtree-dev, 2026-07-18); the capture run proceeds on Worldtree's side. Nothing pending from Rata on #371.

⚠️ TUI DEPRECATED (operator 2026-07-17) — web supersedes it; rip pending, surgical. Independent of any fork (the web console is now THE interactive surface). tui.py + tests/test_tui.py delete cleanly, BUT cli.py is SHARED (web/entrypoint.py + tier3.py import USER_AGENT; cli.py holds ParsedArgs/_format_duration_ms/_format_usage). OPEN SCOPE Q: remove textual-only (tui.py) vs the whole terminal interface (relocate shared consts out of cli.py first). Breaking public-surface removal → minor bump (operator approval). (The v0.20.17 collapsible debug panes, c678853, are now just a web-console feature — the "pre-fork" framing is moot.)

✅ #368 (user,character) memory silo test — DONE, PASSED live (WT b127). The reason for the pre-session clear; closed. Write+read isolation proven end-to-end (conjunctive {end_user, agent_self}; cold-recall gave zero cross-character bleed); throwaway ratatoskr:betty deleted; Sindra intact; stores scrubbed. Still QUEUED: the backfill live-verify (synthetic legacy corpus). Full record → persistent-memory.d/2026-07-18-368-silo-test-passed.md. Sibling issues WT-owned: #369 (recited-content re-promotion loop), #367 (copula-absence bridge phrasing).

Deferred/queued (all NON-URGENT): (1) P06-driver referential-frame A/B/C probe (operator-ratified, waits on WT b122 → persistent-memory.d/2026-07-17-referential-frame-probe.md); (2) R39 Phase-2 matched-quartets rebuild (confirmatory, "whenever"); (3) bifrost snapshot-cursor adoption (ruled normative, not blocking → persistent-memory.d/2026-07-16-bifrost-cursor-conformance.md).

Substrate / environment: branch main, HEAD d59f907 PUSHED to origin (v0.22.0 cutover + bifrost 1.1.5 v0.22.1 + this session's TTS work all on origin; nothing local-only but the dirty graphify-out/). origin git@gitea.phasefinal.com:vh/ratatoskr.git. Core dep: worldtree-sdk==1.0.0 (gitea PyPI, [tool.uv.sources]; httpx-sse removed — SDK owns SSE). **worldtree-sdk REPINNED 1.1.2→1.2.0 (operator-directed, during the DCC-fix wait) — new ResponseTooLarge (a ProtocolError) mapped → SseResponseTooLarge at the stream surfaces (wt.stream_turn/stream_admin_events + the 2 stream endpoints); the 108MB read-body cap is unreachable on legal traffic so reads inherit the SDK refusal unwrapped. FOOT-GUN: this project's dev deps are a [project.optional- dependencies] EXTRA — uv sync alone PRUNES pytest/respx; use uv sync --all-extras. bifrost ==1.1.5 / wire v0.7; WT openapi vendored 2.3.0, conversation-api-spec v1.1; suite 546 green. Personal WT on b128 (http://10.250.50.152:8081; #368 silo + #364 promotion-hygiene live both instances). The combined :8392 provider (memory+affect) + :8765 web are THE surfaces, dev-box BACKGROUND SHELLS — restart via scratchpad/relaunch_by_pid.py <pid> (pid via ss -ltnp | grep <port>). env.sh sets the REQUIRED RATATOSKR_MEMORY_EMBEDDING_DIM=1024. Keys env-only mode-600 in ~/.config/ratatoskr/provider.env + RATATOSKR_ADMIN_API_KEY (7 read scopes, personal-:8081-only; Heimdall keys per-instance). FOOT-GUN: check owner-scoped agents via GET /agents/<owner>:<name> with the OWNER key (WORLDTREE_API_KEY), NOT the admin key — admin gives a false 404. graphify-out/ runs dirty (auto-regen on the commit hook, never stage). v1 = full Worldtree I/O coverage, cuts when WT tags 1.0 (docs/coverage-map.md).

Other live threads: soong-lab = Tier-3 agent-authoring studio (v0.3.24+; motivational string→object export fixed upstream, our workaround droppable). Cross-session name-recall arc COMPLETE + shipped (v0.20.11→.16; WT #364 closed both sides; Sindra durably recalls Vuong via mark_superseded retirement). Sindra pristine baseline WIPED 2026-07-18 (full #368 scrub, born-empty store — old sindra-baseline/*.db predate it). Open/deferred: #10 subject-migration watch; relational-dynamics verify (bind --bifrost-url :8392); WT #356 resume-durability = WT-owned.

Recent decisions

Chronological log of decisions with [YYYY-MM-DD] prefix. One line per decision. Captures rationale that won't be obvious from code alone.

• [2026-08-07] TTS migrated Zonos→chatterbox-fast (:8197 bespoke schema); affect DROPPED (Turbo has no emotion knob, operator "drop it for chatterbox"), client-chunking DROPPED (no per-synth cap), language pin DROPPED, browser SR 44100→24000. Pushed 19b499a. English "German drift" real cause (after 2 wrong hypotheses) = Turbo model OVER-RUNS its generation TAIL on long single generations (garble in final ~2-3s, ZCR 1.58x); fixed SERVER-SIDE by infra-ops (max_chunk_chars=250, image :v2, operator ear-confirmed). Consumer: REVERTED my interim top_k/top_p/temp curbs (they made it WORSE — pulled garble onset earlier), send full text + default sampling; KEPT the /api/tts empty-200→503 guard as hygiene. Contract donut_voiced_interview.contract.md amended. Loop closed.

• [2026-08-07] order_by=chapter tool flag → FILED as Worldtree #397 (DEFERRED to next session's contract pass). Narrative/temporal-query gap ("first encounter in the dungeon"): reference_knowledge sorts by relevance not chronology; provenance.chapter is on every chunk but the consumer can't reorder native results (kb_bridge retired). Operator ruled the upstream sort flag the clean fix; worldtree-dev accepted, our fixture is the measurement instrument. Tracked at Worldtree #397 (+ althing thread 01KZED2T3XHJ2WMS5NCYK42W6R).

• [2026-08-07] #393 (descriptive-query subject binding) CLOSED — persona-expand lever the win (4/10→9/10), tool directive the fleet floor. docs/diagnostics/descriptive_query_binding.py is the canonical #393 fixture; two-mechanism split (cross-wing dilution vs fiction-scope selection). Commits 6c83a3b/4f4b5ad/2cc670e.

• [2026-08-07] Donut expand-don't-distill persona lever (2cc670e) — keep full descriptive phrase + enrich toward entity vocab, never distill to bare keywords; measured 4/10→9/10 roid-rage binds persona-alone. Composes with near-miss LEAD (37b67a5).

• [2026-08-07] TTS "unavailable" = stale web-server process (predated POST /api/tts → 405); restarted + verified 200+WAV. Durability gap: bare nohup, no supervisor → systemd unit offered, deferred (operator's call).

• [2026-08-03] fiction_wing_probe harness fix (2111b1e) — fresh-session-per-query (WT #391 workaround) + NFKC/quote-fold on_target; surfaced+closed WT #391.

• [2026-06-19] #18 D2 SHIPPED (v0.17.14, 39eebd1) and the full #17+#18 arc PUSHED to origin → persistent-memory.d/2026-06-19-18-d2-shipped-v0-17-14-39eebd1-and-the-full-1.md

• [2026-06-19] bifrost repinned 0.8.0→0.10.0; affect.fetch became MANDATORY (strong-or-absent) → persistent-memory.d/2026-06-19-bifrost-repinned-0-8-0-0-10-0-affect-fetch-be.md

• [2026-06-19] #18 D1 SHIPPED — composite build_combined_app on :8392 (v0.17.16, 7f4ceaa); #18 CLOSED; published v0.18.0 (359dbb1) → persistent-memory.d/2026-06-19-18-d1-shipped-composite-buildcombinedapp-on-8.md

• [2026-06-19] op-feed handshake field-name fix (#17, v0.17.17 d60b77d): capabilities_requested→capabilities → persistent-memory.d/2026-06-19-op-feed-handshake-field-name-fix-17-v0-17-17.md

• [2026-06-19] Ratatoskr is a REFERENCE implementation of the Worldtree/Bifrost standard (operator) → persistent-memory.d/2026-06-19-ratatoskr-is-a-reference-implementation-of-th.md

• [2026-06-19] Ratatoskr v1 is DERIVED from Worldtree I/O coverage (operator) — no self-defined feature ROADMAP → persistent-memory.d/2026-06-19-ratatoskr-v1-is-derived-from-worldtree-i-o-co.md

• [2026-06-20] #18's final leg PROVEN — composite :8392 WT-driven smoke ran end-to-end + persisted → persistent-memory.d/2026-06-20-18-s-final-leg-proven-composite-8392-wt-drive.md

• [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 → persistent-memory.d/2026-06-20-sindra-has-real-pad-but-empty-memory-the-affe.md

• [2026-06-29] Web SPA combined-bind default (v0.18.1, 719e4d6) — operator-caught gap → persistent-memory.d/2026-06-29-web-spa-combined-bind-default-v0-18-1-719e4d6.md

• [2026-06-29] bifrost repinned 1.0.0 (v0.18.2, af67ad9) → persistent-memory.d/2026-06-29-bifrost-repinned-1-0-0-v0-18-2-af67ad9.md

• [2026-06-30] Worldtree v1.0.0b1→b2 consumer adaptation: eager turn-launch statuses (v0.18.3 b2e4901, v0.18.4 e4317f6) → persistent-memory.d/2026-06-30-worldtree-v1-0-0b1-b2-consumer-adaptation-eag.md

• [2026-06-30] Verify-against-the-real-spec-before-committing caught a real upstream gap → persistent-memory.d/2026-06-30-verify-against-the-real-spec-before-committin.md

• [2026-06-30] regard is a DEAD AXIS in Worldtree's emitted affect (caught provider-side; worldtree-dev confirmed + escalated to Vuong) → persistent-memory.d/2026-06-30-regard-is-a-dead-axis-in-worldtree-s-emitted.md

• [2026-06-30] v1 coverage-audit kicked off; coverage ledger written (docs/coverage-map.md) — the first one → persistent-memory.d/2026-06-30-v1-coverage-audit-kicked-off-coverage-ledger.md

• [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 → persistent-memory.d/2026-06-30-scope-mandate-a-locked-operator-v1-done-every.md

• [2026-06-30] Finding P-1 (pin drift) + pin-remediation PENDING → persistent-memory.d/2026-06-30-finding-p-1-pin-drift-pin-remediation-pending.md

• [2026-06-30] (b) Tier-1 frontier SCOPED, ready for a contract-first TDD cycle (next focused work) → persistent-memory.d/2026-06-30-b-tier-1-frontier-scoped-ready-for-a-contract.md

• [2026-06-30] (b1) SSE-resume SHIPPED (v0.18.5) — stream_turn_resilient (sse_client.py) → persistent-memory.d/2026-06-30-b1-sse-resume-shipped-v0-18-5-streamturnresil.md

• [2026-06-30] (b2) session-picker SHIPPED (v0.18.7) — bare TUI mode → startup picker (design-brief §4) → persistent-memory.d/2026-06-30-b2-session-picker-shipped-v0-18-7-bare-tui-mo.md

• [2026-06-30] capabilities+me slice SHIPPED (v0.18.8) — GET /me + GET /capabilities consumed via a new --whoami one-shot → persistent-memory.d/2026-06-30-capabilities-me-slice-shipped-v0-18-8-get-me.md

• [2026-07-01] b1 (SSE-resume) heid-code-review panel: ZERO findings — cross-model-verified clean → persistent-memory.d/2026-07-01-b1-sse-resume-heid-code-review-panel-zero-fin.md

• [2026-07-01] GET /sessions/{id}/tools quick-win SHIPPED (v0.18.9) — owner-scoped tool inventory in the TUI Tools pane → persistent-memory.d/2026-07-01-get-sessions-id-tools-quick-win-shipped-v0-18.md

• [2026-07-01] BifrostState pane SHIPPED (v0.18.10) — GET /admin/sessions/{id}/bifrost in a new TUI "Bifrost" pane; the FIRST admin-key consumer in ratatoskr → persistent-memory.d/2026-07-01-bifroststate-pane-shipped-v0-18-10-get-admin.md

• [2026-07-01] LEDGER CORRECTION: #11 (AdminEvents) is NO LONGER BLOCKED → persistent-memory.d/2026-07-01-ledger-correction-11-adminevents-is-no-longer.md

• [2026-07-01] AdminEvents pane SHIPPED (v0.18.11) — GET /admin/events SSE in a new TUI pane; #11 closed-by-build; Tier 1 (debug-observability core) COMPLETE → persistent-memory.d/2026-07-01-adminevents-pane-shipped-v0-18-11-get-admin-e.md

• [2026-07-01] Tier-2 SHIPPED (v0.19.1) — transient-characters CRUD + persona-state write; the v1 coverage-audit CONVERGES (zero in-scope gaps) → persistent-memory.d/2026-07-01-tier-2-shipped-v0-19-1-transient-characters-c.md

• [2026-07-01] env.sh now PERSISTS the web Bifrost-bind vars (gitignored, local-only) → persistent-memory.d/2026-07-01-env-sh-now-persists-the-web-bifrost-bind-vars.md

• [2026-07-01] Tier-3 stores RESET (operator-directed) → persistent-memory.d/2026-07-01-tier-3-stores-reset-operator-directed.md

• [2026-07-01] Embedding-latency loop RESOLVED — it was WORLDTREE's, not ratatoskr (the consumer/provider thesis paid off again) → persistent-memory.d/2026-07-01-embedding-latency-loop-resolved-it-was-worldt.md

• [2026-07-01] Web debug-surface parity SHIPPED (v0.19.2, a0a9d5f) — direct in-session TDD → persistent-memory.d/2026-07-01-web-debug-surface-parity-shipped-v0-19-2-a0a9.md

• [2026-07-01] heid-code-review (v0.19.3, 75dec01) — panel caught 2 real client-side SSE-lifecycle bugs TDD missed → persistent-memory.d/2026-07-01-heid-code-review-v0-19-3-75dec01-panel-caught.md

• [2026-07-01] Affect snapshot shape CHANGED valence→relations (relation_edge/1) — the persona pane was reading a dead field → persistent-memory.d/2026-07-01-affect-snapshot-shape-changed-valence-relatio.md

• [2026-07-01] Trust/warmth VALUES converge and go FLAT at confidence 1.0 — that's WAD, not a stuck pane → persistent-memory.d/2026-07-01-trust-warmth-values-converge-and-go-flat-at-c.md

• [2026-07-01] relation_context "stranger" + agency-all-zero flagged to worldtree-dev → both WAD/intentional-v1-deferrals → persistent-memory.d/2026-07-01-relationcontext-stranger-agency-all-zero-flag.md

• [2026-07-01] Persona pane displays the CANONICAL affect→NL Worldtree injects — ADOPT, don't invent (operator steer + reference-impl posture) → persistent-memory.d/2026-07-01-persona-pane-displays-the-canonical-affect-nl.md

• [2026-07-01] Sindra PAD is over-regulated — characterized via controlled probe, flagged to worldtree-dev (separate affect slice) → persistent-memory.d/2026-07-01-sindra-pad-is-over-regulated-characterized-vi.md

• [2026-07-01] Memory plane PROVEN healthy end-to-end → persistent-memory.d/2026-07-01-memory-plane-proven-healthy-end-to-end.md

• [2026-07-01] Salience scorer non-discriminating → 3-way routing → persistent-memory.d/2026-07-01-salience-scorer-non-discriminating-3-way-rout.md

• [2026-07-01] Canonical check BLOCKED an access_tally fork (reference-impl posture held) → persistent-memory.d/2026-07-01-canonical-check-blocked-an-accesstally-fork-r.md

• [2026-07-01] relation_context coherence FIXED upstream (my flag → Worldtree Wave-0, IMPLEMENTED v1.0.0b5) → persistent-memory.d/2026-07-01-relationcontext-coherence-fixed-upstream-my-f.md

• [2026-07-01] Foot-gun (measurement, self-caught before flagging): establish the baseline before claiming a rate → persistent-memory.d/2026-07-01-foot-gun-measurement-self-caught-before-flagg.md

• [2026-07-02] Salience finding matured into brokkr R28 (OPEN) — ratatoskr is the eval instrument → persistent-memory.d/2026-07-02-salience-finding-matured-into-brokkr-r28-open.md

• [2026-07-02] Relational-dynamics arc LIVE on demo (Worldtree v1.0.0b9) — driven by MY relation_context flag → persistent-memory.d/2026-07-02-relational-dynamics-arc-live-on-demo-worldtre.md

• [2026-07-02] R28 (salience→promotion-worthiness) CLOSED (operator-directed) → persistent-memory.d/2026-07-02-r28-salience-promotion-worthiness-closed-oper.md

• [2026-07-02] R29 (PAD mood-dynamics) finding SHIPPED as Worldtree's A1 anchor fix (demo v1.0.0b14, e1cdf82) → persistent-memory.d/2026-07-02-r29-pad-mood-dynamics-finding-shipped-as-worl.md

• [2026-07-03] R30 Phase-1 φ0 measured — deployed engine CONFIG-FAITHFUL (φ0≈0.95) → persistent-memory.d/2026-07-03-r30-phase-1-0-measured-deployed-engine-config.md

• [2026-07-03] R30 forward disposition (brokkr-owned; tracked at brokkr R30, "brokkr/worldtree will ping") → persistent-memory.d/2026-07-03-r30-forward-disposition-brokkr-owned-tracked.md

• [2026-07-03] Relational-arc verify DEFERRED — relations[] is Bifrost-provider-only (ADR-0009), confirmed both ways → persistent-memory.d/2026-07-03-relational-arc-verify-deferred-relations-is-b.md

• [2026-07-04] R30 CLOSED on offline-tests + human face-validity (operator steer, relayed via worldtree-dev) → persistent-memory.d/2026-07-04-r30-closed-on-offline-tests-human-face-validi.md

• [2026-07-05] Authored-history-write primitive proposed -> accepted as Worldtree #347 (Worldtree owns the engine design; ratatoskr = reference consumer) → persistent-memory.d/2026-07-05-authored-history-write-primitive-proposed-acc.md

• [2026-07-05] #347 v1 wire validated as reference consumer (GREEN) → persistent-memory.d/2026-07-05-347-v1-wire-validated-as-reference-consumer-g.md

• [2026-07-06] Sindra role character-rp -> character (operator) → persistent-memory.d/2026-07-06-sindra-role-character-rp-character-operator.md

• [2026-07-06] Sindra persona/OCEAN DECLARED -> mood fixed (the full diagnostic converged on a stale personal container) → persistent-memory.d/2026-07-06-sindra-persona-ocean-declared-mood-fixed-the.md

• [2026-07-06] OpenAPI re-vendored 2.2.0->2.3.0 (75da676, pin-only no bump) → persistent-memory.d/2026-07-06-openapi-re-vendored-2-2-0-2-3-0-75da676-pin-o.md

• [2026-07-06] #347 authored-history-write CONSUMER SIDE SHIPPED (v0.19.6) — direct in-session TDD → persistent-memory.d/2026-07-06-347-authored-history-write-consumer-side-ship.md

• [2026-07-06] Tail-2 SHIPPED (v0.19.7) — Tier-3 prose docs re-vendored + persona_state body-shape aligned → persistent-memory.d/2026-07-06-tail-2-shipped-v0-19-7-tier-3-prose-docs-re-v.md

• [2026-07-06] Sindra rewritten onto a #347 authored first-message + first-message-preset AUTO-SEED SHIPPED (v0.19.8) → persistent-memory.d/2026-07-06-sindra-rewritten-onto-a-347-authored-first-me.md

• [2026-07-06] Web UI now RENDERS the seeded first-message (v0.19.9) — operator-reported "i don't see Sindra's greeting on the web ui" → persistent-memory.d/2026-07-06-web-ui-now-renders-the-seeded-first-message-v.md

• [2026-07-06] Web UI: pivot from incremental CSS polish to a designed prototype (Claude Design) that I wire into → persistent-memory.d/2026-07-06-web-ui-pivot-from-incremental-css-polish-to-a.md

• [2026-07-07] Affect-egress reference delivered by worldtree-dev + a we-framing render DRIFT-WATCH banked → persistent-memory.d/2026-07-07-affect-egress-reference-delivered-by-worldtre.md

• [2026-07-12] R34/R35 character-self-report reframe LIVE (WT b53); affect-half VALIDATED in prod, powered memory-half eval GREENLIT + designed → persistent-memory.d/2026-07-12-r34-r35-character-self-report-reframe-live-wt.md

• [2026-07-12] Capture-path resolved → a worldtree producer-probe (ratatoskr-caught blocker) → persistent-memory.d/2026-07-12-capture-path-resolved-a-worldtree-producer-pr.md

• [2026-07-12] bifrost 1.1.1 adopted (v0.20.10, pushed) — the library-level fix for the frozen-v0.6 handshake leak → persistent-memory.d/2026-07-12-bifrost-1-1-1-adopted-v0-20-10-pushed-the-lib.md

• [2026-07-10] Bifrost bound-handshake blocker → bifrost 1.1.0 broke frozen-v0.6; fixed by Worldtree b47/wire-v0.7, our side needed ZERO change → persistent-memory.d/2026-07-10-bifrost-bound-handshake-blocker-bifrost-1-1-0.md

• [2026-07-09] Sindra PATCHed to character-rp → Deckard reasoning-RP seat (operator-directed, INTERIM) → persistent-memory.d/2026-07-09-sindra-patched-to-character-rp-deckard-reason.md

• [2026-07-08] PAD display relaxed for R32-1B unbounded-z, done PROACTIVELY (v0.20.9, patch, operator-directed "sindra full and unbounded") → persistent-memory.d/2026-07-08-pad-display-relaxed-for-r32-1b-unbounded-z-do.md

• [2026-07-07] Web-UI iteration-3 SHIPPED (v0.20.7, patch) — all three queued items + the memory 0/0 root-caused → persistent-memory.d/2026-07-07-web-ui-iteration-3-shipped-v0-20-7-patch-all.md

• [2026-07-07] Web-UI next-work QUEUED for a fresh-context session (operator-directed /snapshot handoff) — full specs in Current state § ⏭ QUEUED → persistent-memory.d/2026-07-07-web-ui-next-work-queued-for-a-fresh-context-s.md

• [2026-07-07] Markdown pass-1 SHIPPED (v0.20.6) — RP semantic coloring + paragraph reflow (operator-directed markdown rework, step ①) → persistent-memory.d/2026-07-07-markdown-pass-1-shipped-v0-20-6-rp-semantic-c.md

• [2026-07-07] Affect-derived tooltips (v0.20.5) + transparent squirrel vendored + v0.20.0–.5 PUSHED to origin (operator-authorized) → persistent-memory.d/2026-07-07-affect-derived-tooltips-v0-20-5-transparent-s.md

• [2026-07-07] SVG sparklines + 3D mood cube imported from the updated Claude Design prototype (v0.20.4) — operator: "the svg sparklines and the new 3d graph" → persistent-memory.d/2026-07-07-svg-sparklines-3d-mood-cube-imported-from-the.md

• [2026-07-07] Brand mark + favicon → the aurora squirrel (v0.20.3), replacing the ᛯ rune → persistent-memory.d/2026-07-07-brand-mark-favicon-the-aurora-squirrel-v0-20.md

• [2026-07-07] Context-injection view SHIPPED (v0.20.2) — the console now reconstructs the FULL hidden affect block Worldtree injects into the agent's system prompt (operator: "use that canon in the interface, see as much context injection as possible") → persistent-memory.d/2026-07-07-context-injection-view-shipped-v0-20-2-the-co.md

• [2026-07-06] Claude Design console SHIPPED (v0.20.0 MINOR, operator-approved) — see Current state for the full record → persistent-memory.d/2026-07-06-claude-design-console-shipped-v0-20-0-minor-o.md

• [2026-07-13] P06 memory-half DRIVEN + SCORED — the reframe's memory mechanism is validated → persistent-memory.d/2026-07-13-p06-memory-half-driven-scored-the-reframe-s-m.md

• [2026-07-13] Memory extraction turned REASONING-OFF for the eval (operator-directed) → persistent-memory.d/2026-07-13-memory-extraction-turned-reasoning-off-for-th.md

• [2026-07-13] Vendored the brokkr R34 psych-profile canon (Vuong-directed) — BOTH files, not just the parameters → persistent-memory.d/2026-07-13-vendored-the-brokkr-r34-psych-profile-canon-v.md

• [2026-07-13] Affect-egress "coordinated re-vendor" open item RESOLVED — it was a benign R32-1B doc note, not the we-framing conditional → persistent-memory.d/2026-07-13-affect-egress-coordinated-re-vendor-open-item.md

• [2026-07-13] WT #355 root-caused via ratatoskr telemetry (Vuong-routed via soong-dev) → persistent-memory.d/2026-07-13-wt-355-root-caused-via-ratatoskr-telemetry-vu.md

• [2026-07-13] WT #355 VALIDATION — fix CONFIRMED; the standing loop-in obligation is DISCHARGED → persistent-memory.d/2026-07-13-wt-355-validation-fix-confirmed-the-standing.md

• [2026-07-13] b61 adopted as the personal target — the orthogonal over-budget TRIGGER also fixed → persistent-memory.d/2026-07-13-b61-adopted-as-the-personal-target-the-orthog.md

• [2026-07-13] Cleaned + prepped for a Sindra run (operator: "clean up everything + prep") → persistent-memory.d/2026-07-13-cleaned-prepped-for-a-sindra-run-operator-cle.md

• [2026-07-14] soong-lab adopted as our Tier-3 agent-authoring studio (operator-directed) → persistent-memory.d/2026-07-14-soong-lab-adopted-as-our-tier-3-agent-authori.md

• [2026-07-15] Cross-session recall failure root-caused → the person-prime scan build → persistent-memory.d/2026-07-15-cross-session-recall-failure-root-caused-the.md

• [2026-07-15] Sindra redefined from the soong-lab bundle → persistent-memory.d/2026-07-15-sindra-redefined-from-the-soong-lab-bundle.md

• [2026-07-16] WT #364 + brokkr R39 re-drive (DECISIVE) — name-recall root-caused Worldtree-side; the fix is the signal FAMILY, not a threshold → persistent-memory.d/2026-07-16-wt-364-brokkr-r39-re-drive-decisive-name-reca.md

• [2026-07-16] bifrost ruled scan snapshot-cursor NORMATIVE (offset NOT blessed) + shipped conformance coverage in bifrost 1.1.3 → persistent-memory.d/2026-07-16-bifrost-ruled-scan-snapshot-cursor-normative.md

• [2026-07-16] brokkr flagged ratatoskr as R39 Phase-2 PROBE-RUNNER (Arm-2 contradiction set = our frozen 10-chunk specimen); ACCEPTED IN PRINCIPLE (Vuong 2026-07-16) — formal scope + effort commit lands when Arm-2 actually spins → persistent-memory.d/2026-07-16-brokkr-flagged-ratatoskr-as-r39-phase-2-probe.md

• [2026-07-17] mark_superseded verb SHIPPED + live-verified (v0.20.15, be2c577) — WT #364 durable retirement lands on our store; #364 CLOSED end-to-end both sides → persistent-memory.d/2026-07-17-marksuperseded-verb-shipped-live-verified-v0.md

• [2026-07-17] Web-console UI (v0.20.16, pushed): code-block word-wrap + per-code-block & per-turn copy buttons → persistent-memory.d/2026-07-17-web-console-ui-v0-20-16-pushed-code-block-wor.md

• [2026-07-17] P06-driver referential-frame A/B/C probe QUEUED (operator-ratified, deploy-gated on WT b122) → persistent-memory.d/2026-07-17-p06-driver-referential-frame-a-b-c-probe-queu.md

• [2026-07-17] Sindra live memory.db tidied to a 5-fact PRISTINE baseline for a test drive → persistent-memory.d/2026-07-17-sindra-live-memory-db-tidied-to-a-5-fact-pris.md

• [2026-07-18] #368 (user, character) memory silo test — DONE, PASSED live (WT b127). Write + read isolation both proven end-to-end; betty (throwaway) deleted; the immediate post-clear action, closed. → persistent-memory.d/2026-07-18-368-silo-test-passed.md

• [2026-07-18] Worldtree owns the official Conversation API SDK (#371) — Rata's client spine (sse_client/sessions/tier3) is the SEED; the SillyTavern app moved OUT to a NEW repo (template-dev), Rata does NOT fork. Rata = SDK seed + future consumer; TS ships first (Rata's repin rides the later Python milestone); internal-registry-only. → persistent-memory.d/2026-07-18-worldtree-sdk-371-and-sillytavern-app.md

• [2026-07-18] issue #1 contract drift fixed (4bd9abd) — SSE event vocab re-canonicalized: added awaiting_llm_first_token (#201) + affect_update (#204) to the Event union + TESTS (both were parsed by _envelope_for_type and tested in test_sse_client.py, but never in #1's contract; surfaced by the #371 parity pass). Contract-only, no bump.

• [2026-07-18] Both app products (arbo image-gen + SillyTavern chat) leave Rata to a NEW repo (template-dev standing up); Rata does NOT fork and is NOT the app base. Reverts Rata to its core — Worldtree debug-observability surface + Bifrost reference impl + Conversation-API SDK seed/future-consumer. Supersedes the 2026-07-17 'fork Rata for arbo' NEXT-MAJOR plan.

• [2026-07-18] ephemeral-template (Echo) create SHIPPED (v0.21.2, c7016f2, #19) — config passthrough + --system-prompt + SessionInfo.kind/config + --whoami roles fix. Diagnosed from the ignored session_api_failed startup line; role/model drift resolved w/ worldtree-dev (spec re-synced v1.1). TDD + heid contract-review + bug-hunt.

• [2026-07-18] Rata = THE reference consumer of the worldtree-sdk Python spine — parity pass (12 grounded findings) shaped its contract BEFORE build (open-world reads, caller-injected transport, per-wire role/model — adopted); coverage-map re-anchored to the SDK's 41-op ratified surface (b1fbadd); 4 ergonomics items parked post-v1 with wtsdk-dev.

• [2026-07-18] worldtree-sdk cutover DECIDED — adopt the Python SDK for the consumer client layer (operator, overriding "stay hand-rolled"). Issue #20; contract docs/contracts/worldtree_sdk_cutover.contract.md (e45640c, vor-cross'd + heid-reviewed); auto-memory project_worldtree_sdk_cutover. Consumer layer only, Bifrost provider untouched; slice-1 foundation next. See in-flight.

• [2026-07-19] worldtree-sdk cutover SLICE-1 + SLICE-2 COMPLETE + PUSHED (origin aba1730, v0.21.10, 497 green). The biggest, riskiest cutover slice done end-to-end through the full House Code Discipline (adapter→cli→web→delete→live-smoke→both heid gates); the bug-hunt caught 4 real confirmed bugs the conformance lens couldn't, and a convergent code-review finding was correctly REJECTED as category-5 (SDK envelope-parser behavior). Slice-3 next. → persistent-memory.d/2026-07-19-worldtree-sdk-cutover-slice-1-2-complete.md

• [2026-07-19] worldtree-sdk cutover SLICE-3 COMPLETE + pushed (ca9a339+fc256bb, v0.21.11–.12, 469 green). Persona/authored-history/first-message onto the wt adapter; last hand-rolled sessions.py paths deleted; both heid gates cleared — code-review ZERO drift, bug-hunt caught + fixed a real regression I shipped (ConnectFailed escaping both rewired probes → uncaught crash; the SDK normalizes ALL transport failures to ConnectFailed, not raw httpx) plus a finite-PAD chokepoint gap. Slice-4 (agents/tier3 + model→role) next. → persistent-memory.d/2026-07-19-worldtree-sdk-cutover-slice-3-complete.md

• [2026-07-19] worldtree-sdk cutover SLICE-4 COMPLETE (agents/Tier-3 + model→role fold, c62b4ee+aed9429+477d98f, v0.21.13–.15, 475 green). Full House Code Discipline; the LIVE SMOKE caught a python -m double-module exception-class-identity bug unit tests structurally can't; both heid panels cleared (code-review zero-drift + 3 fixups; bug-hunt 5/5/5 → open-world-presenter degrade-not-crash fixes). Resolves the deferred scope-B model→role. Slice-5 next. → persistent-memory.d/2026-07-19-worldtree-sdk-cutover-slice-4-complete.md

• [2026-07-19] worldtree-sdk cutover SLICE-5 COMPLETE (characters + me/capabilities/models, deab762+d86d6df+4e20030, v0.21.16–.18, 488 green). Last consumer reads + transient-character CRUD onto the wt adapter (CLI-only rewire, NO new Error-map rows — all six routes → SessionApiFailed default); live-smoke-proven on :8081/b128; both heid gates cleared — code-review caught the null/element open-world-presenter degrade holes, the cold bug-hunt caught the container-type layer below them (guard container-type + element-type + top-level-mapping). Slice-6 (admin) next. → persistent-memory.d/2026-07-19-worldtree-sdk-cutover-slice-5-complete.md

• [2026-07-19] worldtree-sdk cutover SLICE-6 COMPLETE (admin: bifrost inspection + admin-events SSE, de9a5ba+bba57e1+11ae2f0, v0.21.19–.20, 494 green). The two admin routes onto client.admin.* (WEB-only — the coverage-map's tui.py rows were stale); admin auth moved from a per-call header to the client's admin_auth; the admin-events adapter re-wraps the SDK's divergent AdminEvent→ratatoskr's (nan/None degraded) to preserve the web surface. Live-smoke-proven (real session.created event id=34 re-wrapped end-to-end). Both heid gates cleared — code-review 3/3 no-drift (only a stale docstring + a test-gap), the cold bug-hunt caught 4 real hardening gaps the CR couldn't (ConnectFailed unmapped on the admin stream; non-str type crash; dict(non-mapping) bifrost 500; a transport leak). Slice-7 (teardown, LAST) next. → persistent-memory.d/2026-07-19-worldtree-sdk-cutover-slice-6-complete.md

• [2026-07-19] wyrd-dev #368 silo-enforcement consult delivered — ratatoskr's store-side silo is CONVENTIONAL (query-time filter); wyrd going STRUCTURAL off the framing. Answered artifact-only from the provider memory-store code; wyrd folded my foot-guns into their unit-4 contract + committed to one-DB-file-per-campaign + first-class partition columns. OPEN LOOP: I'll eyeball their data model once the contract's cut (they'll ping). → persistent-memory.d/2026-07-19-wyrd-368-silo-consult-delivered.md

• [2026-07-19] worldtree-sdk cutover SLICE-7 (teardown, the LAST) COMPLETE — the whole cutover shipped as v0.22.0 (ec68b1f, minor, operator-approved). Zero runtime-logic teardown: httpx-sse dropped (SDK owns SSE), wire contracts #2/#15 retired (files deleted; #1+first_message kept), sessions.py/sse_client.py KEPT as pure type/exception homes (operator decision A1 — no rename/fold), coverage-map re-anchored. All 7 slices done, 494 green; push + althing-announce pending (operator's call). → persistent-memory.d/2026-07-19-worldtree-sdk-cutover-slice-7-complete.md

• [2026-07-19→08-01] Donut voiced-interview BUILD — auto-TTS via Zonos + retire-ready KB-recall bridge + Princess Donut. Slice-1 done (persona + define); slices 2-3 to build; both external deps verified live. THE active work. → persistent-memory.d/2026-08-01-donut-voiced-interview-build.md

• [2026-08-01] worldtree-sdk 1.0.0→1.1.1→1.1.2 repin — and a reference-consumer catch. 1.1.1's path-encoding fix MISSED the inline turn_stream.py:185 on the SSE path (caller-shaped session_id, our highest-traffic route); wtsdk-dev fixed it in 1.1.2 same-day. (d3a36f7+0058020, pushed.)

• [2026-08-01] Mimir #382 grounding bug — our finding shaped the fix. Rata caught that the #380 vector re-index left Mimir DISCARDING correct P&P hits (no named source in the fiction wing → agent distrusts its own hits + answers from training; a silent-substitution "reasoning move, not retrieval"). Fix = our proposed residual (self-describing _index.md) + a Mimir prompt rule; deployed b166. P&P verification re-run OWED to infra-ops; DCC dir still opaque (backfill failed, flagged to worldtree-dev).

• [2026-08-01] Canonical sync — added the client-spec-v2 pin (option A) + synced OpenAPI/spec forward (14bbc2b, pushed). Whole-manifest sync also bumped the OpenAPI hard-gate additively (frozen v1 wire → no breakage). Coverage-map re-audit vs the new surface = queued follow-up.

• [2026-07-30] Versioning cadence → RELEASE-ONLY (operator-ratified, brokkr-smithy relayed). Retired per-commit bump+tag; tag only releases; between releases feat:/fix: SHAs. Existing ~112 tags left as-is. Global CLAUDE.md SemVer being amended to match.

• [2026-08-01] bifrost 1.1.4→1.1.5 (v0.22.1, 3ef3a5e, pushed) — optional-store-verb 500→unsupported_capability hardening; provider restarted onto it.

• [2026-08-01] Sindra saga — restored from local-index burial, wiped, smoke-tested. The v0.22.0 web restart dropped her live session AND the schema-v2 discard buried her from the picker; migrated her v1→v2 from authoritative WT (real role thoughtful-character, not the stale mistral-small-4), then scripts/reset-sindra-stores.sh wiped memory+persona for a from-scratch smoke.

• [2026-08-02] Donut TTS: English pin + long-form chunking + POST + dialogue-only persona + both heid gates — shipped d59f907 (pushed). Gibberish→language:"en-us"; truncation→client-side chunk+concatenate under the 71.2s/6144-tok cap; persona dialogue-only + always-call reference_knowledge; 4-arm gates fixed a lock deadlock + several untrusted-input 500s the GET→POST switch re-opened. → persistent-memory.d/2026-08-02-donut-tts-chunking-english-gates.md

• [2026-08-02→03] reference_knowledge grounding VALIDATED end-to-end — 0/5→5/5 across a 3-round verify; the verify instrument drove diagnosis of a structural Tier-3 blindness (INV-361-3 metadata mismatch, #384) + density restore (#385). Donut recalls the DCC corpus live; wt-dev's "cleanest consumer-side validation this pipeline has had." → persistent-memory.d/2026-08-03-reference-knowledge-3-round-verify.md

• [2026-08-03] Artifact-coverage gap filed as WT #387 (DEFERRED, tracked #387; operator picks when it runs). "Crown of the Sepsis Whore" (major DCC item, confirmed 2× in source text) absent from the 705 concepts — the fiction concept schema has NO item/artifact type, so named objects ride incidentally in plot_events and single-scene items survive on sampling luck. My ratatoskr coverage-probe offer (known-major-artifacts yardstick) recorded on #387; wt-dev pings me when its re-extraction ships. Consumer-side flag, wt-owned fix (schema evolution). Thread 01KZ349M….

• [2026-08-03] worldtree-sdk repinned 1.1.2→1.2.0 (operator-directed, ae49dcf, pushed). New ResponseTooLarge (a ProtocolError, non-resumable) mapped → SseResponseTooLarge at the stream surfaces (wt.stream_turn/stream_admin_events + the 2 stream endpoints); the 108MB read-body cap is unreachable on legal traffic so reads inherit the SDK refusal unwrapped. Absorbed WT spec 2.4.0/2.5.0 (zero-schema). +2 adapter tests.

• [2026-08-03] Donut ANTI-FABRICATION persona shipped (3e12c4d+c0a66fc, pushed) + the retry-on-LOW experiment tested & rejected. Her memory IS the tool's results: LOW/no-on-target → deflect in-character, MEDIUM+ → answer; self-corrects as the KB improves. The retry BACKFIRES (RRF confidence inflatable by any DCC-flavored query → false MEDIUM → fabrication); robust fix is tool-side = #389. → persistent-memory.d/2026-08-03-donut-anti-fabrication-and-retry.md

• [2026-08-03] R42 (fiction-wing retrieval characterization) probe harness shipped to brokkr-smithy-dev (operator-directed, 04e0293, pushed). docs/diagnostics/fiction_wing_probe.py is R42's official harness + the re-runnable #389 acceptance gate; conventions (0.030/0.016 buckets, on-target = row names the subject, N-run bucket distribution) + the frozen artifact yardstick adopted verbatim. PENDING (peer-pinged): arm-1 on-target alignment at Phase-1; #389 gate re-run when RRF work lands. Threads wt-dev 01KZ349M… / brokkr 01KZ421X….

• [2026-08-02] worldtree-sdk 1.2.0 repin DEFERRED to a dep pass (my rec; operator to decide). New ResponseTooLarge (a ProtocolError, NOT caught by our except ConnectFailed) + response-alloc caps that assume a 2.5.0 server (worldtree-dev runs it → safe in practice). When repinning, add ResponseTooLarge to the caught envelopes. Tracked: wtsdk-dev announce thread 01KZ1ZYM….

• [2026-08-02] Filed issue #21 (sibling POST handlers _create_session/_submit_turn 500 on malformed JSON — the parse-JSON-or-400 asymmetry the heid gates flagged; pre-existing, out of the TTS diff's scope). Fix = a shared parse-JSON-or-400 helper.

67 older entries (2026-05-* debug-TUI/web era + the 2026-06-14 → 06-18 Bifrost-provider build / #17+#18 / #295-296 era) archived to archival-memory.md.

For per-issue TDD implementation notes, Volva findings, and contract amendments, see the git log — every per-issue commit carries a structured message capturing the trail.

Tried and abandoned

Log of approaches that were tried and rejected, with rationale. Future-self defense against re-attempting the same cul-de-sac.

• [2026-07-10] Reverting our provider to bifrost 1.0.0 to fix the bound-handshake schema_validation_failed — DISPROVEN, and it would've been the WRONG state → persistent-memory.d/2026-07-10-reverting-our-provider-to-bifrost-1-0-0-to-fi.md

• [2026-06-15] Canonical sync retired the issue-scoped parser staleness. contract_parser.py synced to v2.1 (commit d85ab43): now validates issue-scoped frontmatter + four v2.1 test categories. The old "treat parser ERROR-on-issue-scoped as expected" note no longer applies.

• [2026-06-15] Issue #17 filed. REVERSES design-brief §6's "no Bifrost-binding consumer support" — that negative clause predates ratatoskr's provider identity (2026-06-14), so the canary now owns both ends but its client couldn't drive its own provider. (Shipped 2026-06-18.)

• [2026-06-16] scripts/contract_drift_check.py defaults GITEA_REPO to "Worldtree" (line 74), so a bare run in ratatoskr false-positives DRIFT by hashing Worldtree's same-numbered issue. Always export GITEA_REPO=ratatoskr GITEA_OWNER=vh before running the drift-checker here.

• [2026-06-19] The SAME check_same_thread sqlite bug recurred in the MEMORY store — exposed by the contract-mandated search dispatch test (TestClient = worker thread) → persistent-memory.d/2026-06-19-the-same-checksamethread-sqlite-bug-recurred.md

• [2026-06-19] Full WT-driven :8392 live-smoke is infra-gated — :8392 not in WT's BIFROST_CLIENT_ALLOWED_HOSTS (bind 422s) → persistent-memory.d/2026-06-19-full-wt-driven-8392-live-smoke-is-infra-gated.md

• [2026-06-19] heid-code-review pulled MORE weight than its own "marginal" self-assessment → persistent-memory.d/2026-06-19-heid-code-review-pulled-more-weight-than-its.md

• [2026-06-20] The post-turn-async timing trap bit AGAIN — even a 35s post-[done] read missed the promotion upsert_many by ~2s → persistent-memory.d/2026-06-20-the-post-turn-async-timing-trap-bit-again-eve.md

• [2026-06-30] Heimdall keys are PER-INSTANCE — a key minted on one Worldtree 401s on another → persistent-memory.d/2026-06-30-heimdall-keys-are-per-instance-a-key-minted-o.md

• [2026-06-30] tea comment <N> hangs on Gitea → persistent-memory.d/2026-06-30-tea-comment-n-hangs-on-gitea.md

• [2026-07-02] Mask-HOSTED transient characters have a STATIC mood engine — cost a whole R29 probe → persistent-memory.d/2026-07-02-mask-hosted-transient-characters-have-a-stati.md

• [2026-07-03] The "neutral non-appraising tail" premise fails — the neutral MESSAGE choice dominates → persistent-memory.d/2026-07-03-the-neutral-non-appraising-tail-premise-fails.md

• [2026-07-03] Two φ0-fit traps: fast-turn timescale + low-baseline conditioning → persistent-memory.d/2026-07-03-two-0-fit-traps-fast-turn-timescale-low-basel.md

• [2026-07-06] persona_state + the agent envelope are Tier-3-BLIND -- NOT valid signals for "did a persona store" → persistent-memory.d/2026-07-06-personastate-the-agent-envelope-are-tier-3-bl.md

• [2026-07-06] Raw POST /sessions is NOT Bifrost-bound -> zero affect/memory emits → persistent-memory.d/2026-07-06-raw-post-sessions-is-not-bifrost-bound-zero-a.md

• [2026-07-06] A fast/"no-op" deploy can leave a STALE container running the old image -- verify the running version, not the deploy status → persistent-memory.d/2026-07-06-a-fast-no-op-deploy-can-leave-a-stale-contain.md

• [2026-07-06] #348 OCEAN key-mismatch: a declared OCEAN silently resolved to neutral → persistent-memory.d/2026-07-06-348-ocean-key-mismatch-a-declared-ocean-silen.md

• [2026-07-06] pkill -f "ratatoskr-web --host" SELF-MATCHES the bash command running it → persistent-memory.d/2026-07-06-pkill-f-ratatoskr-web-host-self-matches-the-b.md

• [2026-07-06] Playwright: no python playwright module in the venv; use NODE playwright + an explicit executablePath → persistent-memory.d/2026-07-06-playwright-no-python-playwright-module-in-the.md

• [2026-07-06] The Bash tool's grep is a ugrep-wrapper (--ignore-files -I) that silently returns NOTHING on some files → persistent-memory.d/2026-07-06-the-bash-tool-s-grep-is-a-ugrep-wrapper-ignor.md

• [2026-07-06] DesignSync (claude.ai/design MCP) needs claude.ai design scopes before ANY method works → persistent-memory.d/2026-07-06-designsync-claude-ai-design-mcp-needs-claude.md

• [2026-07-13] thinking_enabled=False on the define was a NO-OP — char-rp-reasoning ignores it → persistent-memory.d/2026-07-13-thinkingenabled-false-on-the-define-was-a-no.md

• [2026-07-13] A same-image redeploy does NOT reload a bind-mounted config — the ModelRegistry boot-caches it at __init__ → persistent-memory.d/2026-07-13-a-same-image-redeploy-does-not-reload-a-bind.md

• [2026-07-15] soong-lab bundle ship.native.motivational.goals/fears are bare STRINGS, but WT agents.define requires OBJECTS → persistent-memory.d/2026-07-15-soong-lab-bundle-ship-native-motivational-goa.md

• [2026-07-15] re.sub/re.subn INTERPRETS backslash-escapes in the REPLACEMENT string → persistent-memory.d/2026-07-15-re-sub-re-subn-interprets-backslash-escapes-i.md

• [2026-07-13] Called Deckard "hung" off a short timeout — WRONG (operator correction) → persistent-memory.d/2026-07-13-called-deckard-hung-off-a-short-timeout-wrong.md

• [2026-07-13] Resumed-session context-snapshot is IN-MEMORY → lost on a container recreate (agent_not_available on resume) → persistent-memory.d/2026-07-13-resumed-session-context-snapshot-is-in-memory.md

• [2026-07-16] sortable_chunk_fields advertised WITHOUT the required type field = whole-handshake deploy-breaker; only DRIVING the real bind caught it → persistent-memory.d/2026-07-16-sortablechunkfields-advertised-without-the-re.md

• [2026-08-01] local_agents index schema v1→v2 bump SILENTLY buries pre-cutover consumer agents from the picker — load_local_agents returns [] on version mismatch (no migration path); the v0.22.0 restart made Sindra vanish even though she was alive on WT. Fix applied ad-hoc: migrate the v1 row → v2 from authoritative WT data (the v1 model field held a stale model name, NOT the current role). A one-time v1→v2 migration guard is the durable fix (unbuilt; operator-flagged).

• [2026-08-01] Zonos: mp3/opus response_format silently return mislabeled PCM (no encoder wired) — use response_format:"wav" only. And use the GATEWAY :8890, NOT the engine :1920 (rep-penalty bug pads ~70s silence + ignores voice).

• [2026-08-02] Zonos hard-caps ONE synthesis at max_tokens=6144 = 71.2s of audio (6144 / 86.3Hz codec frame rate; >6144 → HTTP 400, an architectural sequence limit). 86.3Hz is a delivery-INDEPENDENT constant — 6144 tokens is ALWAYS 71.2s regardless of emotion/rate (emotion changes words-per-71.2s, not seconds-per-token). Any turn longer than ~71s REQUIRES client-side chunk-and-concatenate (raw PCM, ONE WAV header — never stitch multiple WAV headers). Fixed in d59f907 (DEC-10). Don't chase a "raise max_tokens" fix — the gateway rejects it.

• [2026-08-02] A GET→POST endpoint switch re-opens untrusted-TYPE crashes that string-only query params silently masked. Under GET, p/a/agent_id were always str|None; under a JSON POST body they can be a huge int (float()→OverflowError), an unhashable list/dict (dict.get→TypeError), or a lone surrogate (utf-8 encode→UnicodeEncodeError) — each a 500 the old code never saw. Guard EVERY body field when moving a query endpoint to a JSON body. Both heid gates converged on these (all 4 arms). Fixed in d59f907.

• [2026-08-03] A bare uv sync PRUNES this project's dev deps — pytest/respx/ruff live in [project.optional-dependencies] (an EXTRA, not a dependency-group), so uv sync (default groups only) removes them from .venv, and uv run pytest then silently falls back to a user-site pytest (py3.11, ~/lib) that can't import the .venv's worldtree_sdk → 16 collection ModuleNotFoundErrors. Use uv sync --all-extras. Bit me right after the 1.2.0 lock; the repin itself was never at risk.

• [2026-08-03] tier3 patch does NOT refresh a live agent's running context — it updates STORAGE (the define/patch response echoes the new prompt) but the running agent keeps serving the OLD system prompt. To change a live Tier-3 persona reliably, delete + define (recreate), not patch. (Cost a confusing "patched but behavior unchanged" loop on the Donut anti-fabrication change.)

• [2026-08-03] A persona-side confidence gate can't stop LLM fabrication — RRF confidence is inflatable by query phrasing. A "re-search on LOW" retry reformulates the query with related real entities (or just DCC-flavored terms), which scores MEDIUM off THOSE matches, not the subject — manufacturing false grounding to fabricate on. The signal that survives is on-target (does a returned row NAME the subject), which is a TOOL-side check, not something a prompt can enforce against a model with strong genre priors. → #389.

34 older entries (2026-05-* debug-TUI/web era + the 2026-06-14 → 06-18 foot-gun cluster) archived to archival-memory.md.