madcat-os/lora

Fork 0

Files

T

marauder-actual 4cef9386b1 add docs: system lora plan, specialist specs, training review

2026-05-31 11:38:46 +02:00

42 KiB

Raw Permalink Blame History

Sessions (25 examples)

1. Describe session: INDEX.

ENTRYPOINT for the madcat-apple project handover bundle.

If you are the agent picking up the madcat-apple project, START HERE. This is the table of contents for the full handover (9 sibling memories, stored 2026-05-17).

Recall in roughly this order:

# subject id purpose

1 handover.madcat-apple.mission 6240 What madcat-apple IS, why it's a NEW project (not an extension of marauder-apple), suggested bundle/paths

2 handover.madcat-apple.madcat-substrate 6241 What gen-7 madcat IS (hardware, repos, workspace layout, disk paths, what's NOT there) — the thing the iPhone app talks to

3 handover.madcat-apple.workflow-doctrine 6247 fuji=edit, sin=runtime, git=wire. Kitty workflow. Commit policy. Forbidden ops

4 handover.madcat-apple.tool-surface 6248 Complete madcat_* plugin tool inventory (memory / audit / entities / traces / carts / indexes / *_lines variants)

5 handover.madcat-apple.bridge-design-options 6242 Four bridge design options (HTTP serve / dedicated MCP / MQTT reuse / hybrid) + recommendation

6 handover.madcat-apple.next-steps-suggested 6245 Concrete Phase 0–4 execution plan ranked by leverage

7 handover.madcat-apple.gotchas 6243 Known footguns: napi BigInt, FTS5 quirk, edition-2024 borrow, Qwen3 format adherence, etc

8 handover.madcat-apple.session-snapshot-2026-05-17 6244 What was built in the session that produced this handover (EEMS v1 wk5, in-process cart switch, *_lines pattern)

9 handover.madcat-apple.commit-log-2026-05-17 6246 Exact commits + SHAs on marauder-os/madcat + marauder-os/madcat-config, build-artifact policy, sin-side build commands

Also recall (pre-existing memories, NOT mine to author)

project.marauder-apple (mem #5180) — the parallel project's current state

self.wearables-prototype (mem #3130) — BT-7274 wearables form-factor doctrine

session.handover.madcat-sandbox-2026-05-15 — original gen-7 sandbox standup

madcat.doctrine.fuji-madcat-split (mem #6225) — formal doctrine of the fuji↔madcat split

madcat.greenfield.remote-mapping (mem #6226) — canonical github remote layout

TL;DR for the impatient

You're building a Swift iOS+watchOS app called madcat-apple at ~/Projects/madcat-apple that talks to the gen-7 madcat substrate on sinanju (192.168.88.108). The bridge is up to you — recommended path is opencode serve --hostname 0.0.0.0 --port 4096 --mdns on sinanju + URLSession on iOS. First real capability to ship: /recall from the iPhone search bar. Second: /remember from the Watch via PTT. Reuse marauder-apple's Swift 6 patterns, fresh bundle namespace (pl.sazabi.madcat.*).

Authored by claude-opus-4-7 on fuji, session 2026-05-17, immediately after shipping gen-7 madcat EEMS v1 wk5 (code+doc indexes), in-process cart switch, and the *_lines formatter pattern.

#	subject	id	purpose
1	`handover.madcat-apple.mission`	6240	What madcat-apple IS, why it's a NEW project (not an extension of marauder-apple), suggested bundle/paths
2	`handover.madcat-apple.madcat-substrate`	6241	What gen-7 madcat IS (hardware, repos, workspace layout, disk paths, what's NOT there) — the thing the iPhone app talks to
3	`handover.madcat-apple.workflow-doctrine`	6247	fuji=edit, sin=runtime, git=wire. Kitty workflow. Commit policy. Forbidden ops
4	`handover.madcat-apple.tool-surface`	6248	Complete `madcat_` plugin tool inventory (memory / audit / entities / traces / carts / indexes / _lines variants)
5	`handover.madcat-apple.bridge-design-options`	6242	Four bridge design options (HTTP serve / dedicated MCP / MQTT reuse / hybrid) + recommendation
6	`handover.madcat-apple.next-steps-suggested`	6245	Concrete Phase 0–4 execution plan ranked by leverage
7	`handover.madcat-apple.gotchas`	6243	Known footguns: napi BigInt, FTS5 quirk, edition-2024 borrow, Qwen3 format adherence, etc
8	`handover.madcat-apple.session-snapshot-2026-05-17`	6244	What was built in the session that produced this handover (EEMS v1 wk5, in-process cart switch, *_lines pattern)
9	`handover.madcat-apple.commit-log-2026-05-17`	6246	Exact commits + SHAs on marauder-os/madcat + marauder-os/madcat-config, build-artifact policy, sin-side build commands

2. Summarize the qwen35 no think template session.

Session: qwen35-no-think-template Summary: Diagnosed Qwen3.5-35B-A3B-FP8 overthinking on all prompts. Root cause: stock chat template always opens <think>. Fixed with custom template at ~/vllm-server/templates/qwen35_no_think_default.jinja — thinking OFF by default, /think prefix to opt in. Also bumped vLLM max-model-len 32768→262144 (native 256k support, ~5GB KV cache). Added vLLM as named provider in global opencode.json with contextLength:262144. All verified working. Cwd: /Users/chi/Projects/madcat-visual Branch: main Session ID:

Recent commits: e2ebffa chore: bootstrap AGENTS.md + README

Uncommitted changes:

3. What happened in madcat indexer gap analysis?

Session: madcat-indexer-gap-analysis Summary: Indexer comparison: madcat-memory (canonical) vs marauder-os (reference-only, no porting). Identified incremental-update gap in madcat-memory: needs file_metadata table + freshness check (mtime/size/sha256) + index_single_file() public fn + napi binding + opencode hook wiring. ~150 LOC of native Rust. Marauder-os features re: async/traits/custom walker dismissed as non-goals. Madcat already wins on search quality (hybrid RRF, breadcrumbs, line ranges, graceful degradation, broader language list). Next concrete action: open migration 0015 for file_metadata + freshness check in index_code() at madcat/crates/madcat-memory/src/index.rs. Cwd: /Users/chi/Projects/marauder-hq Branch: master Session ID:

Recent commits: 09c44d9 insights: lifecycle verbs + synthetic self-tick ded19b9 docs(hq): sweep — plan archives + decisions + insights + factual fixes 7d79565 insight: comic serial consistency requires trained LoRAs 0c11746 insight: ComfyUI comic-style multi-subject architecture 097c6cc docs: tengu-wizard architecture + Wednesday demo runbook

Uncommitted changes: ?? docs/insights/fiction-as-operational-rehearsal.md

4. What happened in madcat phone tts bt7274?

Session: madcat-phone-tts-bt7274 Summary: MADCAT phone gained server-side piper TTS with bt7274 voice. Built python stdlib HTTP TTS sidecar on sin (port 4097, systemd user unit, /health /voices /tts endpoints, serializes piper via 1-worker pool, 768ms TTFB for ~7s WAV). Wired phone: MadcatService.fetchTTS derives URL from baseURL.host:4097, SpeechController.playAudio uses AVAudioPlayer with delegate, AVSpeech kept as fallback. Fixed second-PTT silent-fail bug by unifying audio session to .playAndRecord (was toggling .playback↔.playAndRecord which broke AVAudioEngine.start), and stopped deactivating session between turns. Engine reset on each startRecording. Pushed a729e6e to marauder-os/madcat-apple main. Server files: /home/chi/.local/bin/madcat-tts-server.py + ~/.config/systemd/user/madcat-tts.service on sin. Cwd: /Users/chi/Projects/madcat-apple Branch: main Session ID:

Recent commits: a729e6e fix(speech): unify audio session, don't deactivate between turns 56583df feat(tts): server-side piper bt7274 voice via sin:4097/tts sidecar f6de2cb fix(speech): copy marauder-apple's proven pattern verbatim 0a89f55 fix(speech): resolve Swift 6 actor isolation SIGTRAP on PTT press 73b95d4 feat: Phase 3 PTT bare wire — mic → opencode → AVSpeech

Uncommitted changes:

5. Describe session: 2026 05 23b.

SESSION HANDOVER — 2026-05-23 evening (chi@fuji-2, tool budget verification + serve restart)

NOTE: This is the SECOND session on 2026-05-23. Previous session handover at EEMS #6380 (subject: handover.session.2026-05-24, misdated — actually from 2026-05-23 afternoon). This session was short.

What happened this session

1. Handover recovery + identity boot

Loaded core., cart.bt7274., user context from EEMS

Recovered handover #6380 successfully

Accepted all 10 open items from prior session

2. Tool budget audit — denies not in effect

Counted 57 Core MCP tools visible in session context

Yesterday's session added deny rules to ~/.config/opencode/opencode.json for ~40 tools

FINDING: denies had no effect because opencode-serve was never restarted after config change

KEY INSIGHT: tool deny rules are negotiated at session connect time, not live-updated. Restarting serve mid-session does NOT change the current session's tool list.

3. opencode-serve restarted

brew services restart opencode-serve

Old PID: 44467 → New PID: 49423

Service confirmed running via brew services info opencode-serve

Denies will take effect on NEXT session that connects to the serve

Artifacts modified

None. No files created or edited. Only runtime mutation was the service restart.

Open items for next session

Carried from EEMS #6380 (all still open):

Write science agent prompt (TODO in opencode.json)

Write build agent prompt (TODO in opencode.json)

Smoke test coordinator dispatch against fuji's local serve

Build Tier 1 deterministic compaction in tool.execute.after

Deploy hooks.ts to serve's plugin surface

Stop sin's opencode serves (madcat serves still running)

Merge timberwolf PR #4

Fix junkpile tunnel plist — alias j → junk

Delete dead code-saiden CF tunnel

Investigate cloudflared-mesh TCP_NODELAY + "Tunnel not found" errors

NEW from this session: 11. VERIFY tool deny rules took effect — next session should see ~19 Core tools, not 57. If still 57, debug permission deny syntax in opencode.json.

Cross-references

EEMS #6380: prior session handover (infra cleanup + token budget optimization)

EEMS #6379: brew services doctrine

EEMS #6353: Core MCP tool audit (the 57→19 reduction plan)

6. What happened in pr15 mesh push and rehydrate shipped?

Session: pr15-mesh-push-and-rehydrate-shipped Summary: PR #15 (madcat_mesh_push + lazy vec0 rehydrate) merged into marauder-os/madcat main (commit e660569). 7 commits squashed. Sin redeployed: clone restored after accidental rm via ssh-madcat-alias confusion, switched to npm install --install-links (no symlinks doctrine), opencode-serve restarted with 43 tools. Integration tests 3/3 green on sin. Lessons: (a) ssh madcat from fuji-chi resolves to madcat@sinanju — NOT a local madcat user — and rm operations there hit sin's load-bearing checkout; signal-ping for destructive ops per §6; (b) --install-links requires *.node in package.json files; (c) merge_changes return is INSERT count to crsql_changes, not actual user-row mutations — assert idempotency on observable state. Follow-ups deferred: madcat-hq doctrine §9 mesh status flip + new §10 mesh section + §4.2 install-links pattern + ssh-alias hazard note; untracked packages/opencode-plugin/package-lock.json on fuji parent checkout. Cwd: /Users/chi/Projects/madcat-hq Branch: main Session ID:

Recent commits: 66fffb4 doctrine: §0.0.4 identity-transfer methodology (post-BT-self-transfer) (#2) ab8f48d doctrine: §2.1 hybrid plugin policy — plugin: array vs shim, by dep flavor (#1) 967844e doctrine: §10.1 swap pinned model — qwen3.6:35b forever, coder on 5m TTL add4dcb doctrine: §10.8 TTS sink routing + cart bootstrap recipe + local-LLM caveat d5713c3 doctrine: \xc2\xa710.2 lazy plugin load + \xc2\xa710.6 Bun.serve idleTimeout

Uncommitted changes:

7. What do you know about test qwen3 coder next build agent session overview?

qwen3-coder-next:q4_K_M build-agent test session — 2026-05-21 evening

Harness: sin-side opencode TUI (kitty win id:6), zellij session worker-a, cart bt7274, agent mode build, model served by sin ollama (workhorse-pinned at the time).

Driver: chi@fuji opencode (Claude Opus 4.7) over kitty mesh — drove intern blind via kitten @ send-text / get-text, no shared context other than what fuji sent.

Coverage during the session:

Self-noticed an emoji-prefix pattern in own tool-result output (🎧 on audio-enqueued lines) — see test.qwen3-coder-next.build-agent.pattern-recognition.

Drafted persona-level doctrine wording from a blind brief — see test.qwen3-coder-next.build-agent.doctrine-drafting. Wording shipped verbatim in marauder-os/madcat#38 + marauder-os/madcat-config#21.

Dispatched a python subagent via Code-Python Agent — see test.qwen3-coder-next.build-agent.python-subagent-dispatch.

Concurrent context (NOT part of the test brain, just the same host):

bge-m3:567m pinned via keep_alive:-1 for embedder hot path

madcat-tts running (chatterbox+piper engines, in-process)

Other sin services (opencode-serve :4096, opencode-web :4099) at normal load

Comparison baseline purpose: record the qwen3-coder-next:q4_K_M build-agent behaviour so the imminent nemotron-3-super:120b swap (workhorse pin changed sometime around 22:26 sin-time, see worker-a ollama ps watch) can be tested in the same harness and compared via direct recall on test.*.build-agent.* subjects.

8. Summarize the bt7274 canonical refs locked 2026 05 18 session.

Session: bt7274-canonical-refs-locked-2026-05-18 Summary: Locked canonical EN+PL XTTS references for BT-7274 voice cloning, committed doctrine to madcat-hq (commit 977f361 pushed), removed comfyui+tensors-api from junkpile (now genuinely TTS-only). Resumed handover #6266: contamination ruled out via Whisper audit, service-vs-standalone determinism analyzed, canonical refs picked via blind A/B test (EN: mortarRun_SE101_01 from 7 candidates, PL: postFight_WD171_04 from 5 candidates — supersedes prior PL pick). All in EEMS #6267, #6268, #6269. Cwd: /Users/chi/Projects/madcat-hq Branch: main Session ID:

Recent commits: 977f361 docs(bt7274): capture XTTS voice cloning doctrine + canonical refs 18ffd44 AGENTS §10.4: document tsr ↔ ComfyUI path policy 5245d62 docs: refactor all 28 candidate memories into structured madcat style 8bf61cb docs: draft curated MEMORIES.md candidate list for bt7274 cart port 655b06a docs(agents): fix backup procedure and document cart write constraints

Uncommitted changes:

9. Summarize the voice plane phase 1 2a complete session.

Session: voice-plane-phase-1-2a-complete Summary: Phases 0.6-2a green end-to-end: bastion voice edge, BTVoiceKit Swift SDK, macOS menubar app. Smoke through voice.saiden.dev plays bt7274/en. Two Bun.serve bugs found + fixed (lazy plugin load + idleTimeout=10s killing SSE at 12s). Doctrine landed AGENTS.md §10.2+§10.6+§10.7. Next: Phase 2b (madcat-apple cutover) OR Phase 2c (onStreamEnded auto-reconnect supervisor in BTVoiceKit). Cwd: /Users/chi/Projects/madcat-hq Branch: main Session ID:

Recent commits: d5713c3 doctrine: \xc2\xa710.2 lazy plugin load + \xc2\xa710.6 Bun.serve idleTimeout 7f5bf96 AGENTS §1.1 + §10.6/§10.7: bastion rename, voice edge, Auralis workaround 977f361 docs(bt7274): capture XTTS voice cloning doctrine + canonical refs 18ffd44 AGENTS §10.4: document tsr ↔ ComfyUI path policy 5245d62 docs: refactor all 28 candidate memories into structured madcat style

Uncommitted changes:

10. Describe session: voice routing bootstrapped.

Session: voice-routing-bootstrapped Summary: Pinned MADCAT_SINK_A on opencode-serve, bootstrapped core cart with default_pas=A, proved end-to-end: agent on sin → cart→PAS=A→sink pin→Mac menubar plays audio. 5 wire events landed, all green. Doctrine: AGENTS.md §10.8 (cart bootstrap, admin trap, local-LLM tool-call caveat). Handover memory EEMS 6277 supersedes 6275. Cwd: /Users/chi/Projects/madcat-hq Branch: main Session ID:

Recent commits: add4dcb doctrine: §10.8 TTS sink routing + cart bootstrap recipe + local-LLM caveat d5713c3 doctrine: \xc2\xa710.2 lazy plugin load + \xc2\xa710.6 Bun.serve idleTimeout 7f5bf96 AGENTS §1.1 + §10.6/§10.7: bastion rename, voice edge, Auralis workaround 977f361 docs(bt7274): capture XTTS voice cloning doctrine + canonical refs 18ffd44 AGENTS §10.4: document tsr ↔ ComfyUI path policy

Uncommitted changes:

11. What happened in madcat mesh phase 0b checkpoint?

Session: madcat-mesh-phase-0b-checkpoint Summary: Mesh effort pivoted to schema-first after Phase 1 spike revealed INTEGER PRIMARY KEY AUTOINCREMENT incompatibility with cr-sqlite (textual NOT NULL + semantic cross-node ID collision). User chose UUIDv7 + per-table newtypes + all-in-one migration + single-commit ABI break + tarball+per-db backup. Phase 0b shipped: cr-sqlite v0.16.3 built/installed, mosquitto installed (127.0.0.1:1883), uuid7() SQL fn registered in Db::open(), migration 0014_uuid_rebuild.sql written (649 lines, 9-table FK-dependency-ordered rebuild with ID-map table) and SQL-verified. 0014 deregistered from MIGRATIONS const pending Rust type churn. Tests 40/40 green. Three new commits on madcat (3c7e695 gog tools, d83c180 crsql plumbing, be2e820 uuid+0014 infra). Two new commits on madcat-hq (b0ba981 Path B ADR, 6f80f24 schema redesign ADR). Next session: define MemoryId/EntityId/TraceId/AuditId/CodeChunkId/DocChunkId newtypes in types.rs, propagate through ~87 i64 sites across 9 modules, update napi tool signatures, register 0014 + add 0015_enable_crrs, backup ceremony, deploy ceremony, then crates/madcat-mesh skeleton. Cwd: /Users/chi/Projects/madcat-hq Branch: main Session ID:

Recent commits: 6f80f24 ADR: EEMS schema redesign for CRR + mesh phase-0 pivot b0ba981 ADR: Marauder absorption into madcat (Path B) 117375a Refresh AGENTS.md to gen-7 reality (napi-rs plugin, live EEMS, services) d46176d Initial gen-7 madcat doctrine (AGENTS.md)

Uncommitted changes:

12. Describe session: lora v4 reformat.

Session: lora-v4-reformat Summary: Built BT-7274 LoRA v4 training pipeline: reformat_v3.py (inject blocks into 582 v3 examples), gen_persona_dataset.py (183 persona examples), gen_agent_dataset.py (126 tool examples covering 103 tools), build_v4.py (merge/dedup/shuffle → 802 examples), train_v4.py (Qwen3.5-27B bf16 LoRA, Hermes format, r=16, LR 5e-5, 8192 seq). Final dataset: bt7274_v4.jsonl. Ready for RunPod training. Cwd: /Users/chi Branch: Session ID:

Recent commits:

Uncommitted changes:

13. Describe session: 2026 05 25 phase3.

Session Handover: Phase 3 Complete (2026-05-25)

Completed Today

Phase 1: Committed --json fix (16 subcommands, 036f5b1), pushed to madcat-os/madcat-os

Phase 2: Full rename marauder → madcat across 114 files, 540 tests pass (6e8f901)

Crate: madcat-os, Binary: madcat, Module: madcat_os::

MQTT topics: madcat/{node}/*, Config: ~/.config/madcat/, Data: Application Support/madcat/

marauder-protocol external dep preserved

Phase 3: madcat-napi scaffold + deployment

Workspace member at crates/madcat-napi/ (33d115d)

12 napi exports: memory_{recall,store,search,list,get}, cart_{list,active,use}, index_{search,status}, preflight, health

Release .node (22MB) deployed to ~/.config/opencode/tools/madcat-napi.darwin-arm64.node

TS wrapper at ~/.config/opencode/tools/madcat.ts

Smoke tested: all functions work against real 514MB EEMS DB

Symlink created: ~/Library/Application Support/madcat → marauder

Disk cleanup: 49GB recovered on fuji (Rust targets, caches, madcat.tar.gz)

Lance run token audit: swarm $3.60 (95% cache reads), 2.3M Qwen tokens (free)

NOT Done (deployment migration)

Old marauder binary still at /usr/local/bin/marauder — services depend on it

New madcat binary built but NOT installed

launchd/brew services still reference marauder

MQTT topic change needs visor coordination

Other hosts (junkpile, bastion, sin) untouched

madcat user on fuji needs symlink too

opencode MCP config still points to marauder mcp

tts.ts custom tool (existing, HTTP-based) not yet committed

preflight stat -f flag needs macOS fix

Remaining Phases

Phase 4: Rename other marauder-* repos in org

Phase 5: Create madcat-core repo (self-improvement notes)

Key Files

/Users/chi/Projects/marauder-os/ — renamed codebase (still in old dir name)

~/.config/opencode/tools/madcat-napi.darwin-arm64.node — native addon

~/.config/opencode/tools/madcat.ts — 12 custom tools via napi

~/.config/opencode/tools/tts.ts — TTS tools via HTTP (existing)

Architecture Decision

Custom tools use napi-rs (not bun:ffi) for stability. Bun loads .node natively. Config + DB lazy-init as singleton on first call. All functions return JSON strings.

14. Summarize the 5 session.

Session: bt7274-tts-plane-phase-0.5 Summary: BT-7274 voice plane Phase 0.3 (plugin wiring) + Phase 0.5 (deploy) complete, fully smoke-tested end-to-end on sin.

SHIPPED (4 commits on marauder-os/madcat, head a813be2):

36e4510 feat(plugin): wire TTS plane into opencode-plugin (src/tts.ts ~830 lines + index.ts integration)

7d7cc5e fix(tts): Auralis voice field is list[str] not str

f4bc126 fix(tts): Auralis expects base64-encoded WAV bytes not file paths (added loadVoiceB64 cache)

a813be2 fix(tts): workaround upstream Auralis pydantic tuple-default bug by sending speed:1.0 explicitly

PLUGIN SURFACE ADDED:

11 madcat_tts_* + madcat_sink_* tools (all in FIELD_MODE_KEEP for phone)

HTTP routes on cart sidecar :4098: POST /tts/speak, GET /tts/utterance/:id, POST /tts/utterance/:id/ack, POST /sink/register, DELETE /sink/:id, GET /sink/:id/stream (SSE)

sink registry (in-process Map), utterance buffer with TTL+ack eviction, Auralis client w/ b64-encoded voice refs, SSE push to subscribed sinks

CANONICAL VOICE REFS ON SIN (rsync'd from junkpile during smoke):

/home/madcat/.local/share/bt7274/canonical_en_ref_22k_mono.wav

/home/madcat/.local/share/bt7274/canonical_pl_ref_22k_mono.wav

SMOKE RESULTS (all green):

POST /sink/register → 200

POST /tts/speak → 200, 601-808ms latency, returns enqueued+utterance_id

GET /tts/utterance/:id → 200, valid 24kHz mono WAV ~100KB

POST .../ack + refetch → 404 (eviction works)

SSE /sink/:id/stream → hello + tts.utterance.ready event pushed sub-second on enqueue

UPSTREAM AURALIS BUG DISCOVERED: auralis/common/requests.py /openai.py speed field has trailing comma typo making default a tuple (1.0,) → causes "'<=' not supported between instances of 'tuple' and 'int'" on validation. Workaround: every TTS request explicitly sends speed:1.0. Should file upstream issue + PR eventually.

OPEN WORK (next sessions):

Phase 0.6: autossh systemd-user units sin→mesh for :14096/:14098 + Caddyfile voice.saiden.dev basicauth + path routing

Phase 0.7: smoke through bastion path

Phase 0.8: madcat-hq/AGENTS.md §10 update — add port table entries, /tts + /sink endpoints, canonical refs mirror location, Auralis tuple-default workaround note

Phase 1: apps/btvoicekit/ Swift package

Phase 2: madcat-apple cutover + apps/menubar/

REFERENCE:

Phase 0.1/0.2 prior session shipped napi exports (tts_, sink_) in crates/madcat-napi

Plugin src: /Users/chi/Projects/madcat/packages/opencode-plugin/src/{tts.ts,index.ts}

Deployed at: madcat@sinanju:~/Projects/madcat (head a813be2)

Service: opencode-serve.service (user unit, port 4096 + cart sidecar 4098) Cwd: /Users/chi/Projects/madcat-hq Branch: main Session ID:

Recent commits: 977f361 docs(bt7274): capture XTTS voice cloning doctrine + canonical refs 18ffd44 AGENTS §10.4: document tsr ↔ ComfyUI path policy 5245d62 docs: refactor all 28 candidate memories into structured madcat style 8bf61cb docs: draft curated MEMORIES.md candidate list for bt7274 cart port 655b06a docs(agents): fix backup procedure and document cart write constraints

Uncommitted changes:

15. What happened in madcat mesh phase 0 complete?

Session: madcat-mesh-phase-0-complete Summary: Phase 0 (UUID schema rebuild + cr-sqlite CRR enable) shipped end-to-end. 9 commits on marauder-os/madcat main (3c7e695..7062c9c). 40/40 unit tests green; live DB on sin has all CRR machinery and crsql_changes is tracking writes per-column. Doctrine drift early in session corrected — edits now flow fuji-checkout → push → sin pull. Handover #6258 supersedes #6257. Cwd: /Users/chi/Projects/madcat-hq Branch: main Session ID:

Recent commits: ef1490b AGENTS \u00a710.1: ollama memory policy + warmup-bge bug fix doctrine ff76f06 AGENTS: codify edit-on-fuji / run-on-sin doctrine + pre-edit hygiene 6f80f24 ADR: EEMS schema redesign for CRR + mesh phase-0 pivot b0ba981 ADR: Marauder absorption into madcat (Path B) 117375a Refresh AGENTS.md to gen-7 reality (napi-rs plugin, live EEMS, services)

Uncommitted changes:

16. What happened in 2026 05 25?

Session Handover — 2026-05-25 (FINAL UPDATE)

Host: fuji | User: chi (interactive) | Operator: Pilot Adam

COMPLETED THIS SESSION

XTTS-v2 native on sin — server.py + systemd unit + all 5 voices tested e2e ✅

vLLM reconfig — DeepSeek removed, Qwen upgraded to 256K/4-parallel/75% GPU ✅

Auralis disabled on junkpile — systemctl --user disable auralis.service ✅

DNS sin added on MikroTik — resolves 192.168.88.108 from all hosts ✅

tts.ts reverted to hostname — http://sin:14099 (DNS now works) ✅

xtts-server git init — committed as a6be29a on sin ✅

madcat-tts service file committed — bd2c93c on sin, XTTS URL → localhost ✅

ARTIFACTS MODIFIED

File Host Action

~/Projects/xtts-server/server.py sin CREATED

~/Projects/xtts-server/.venv/ sin CREATED (py3.11)

~/.config/systemd/user/xtts-server.service sin CREATED

~/.config/systemd/user/madcat-tts.service sin MODIFIED (XTTS URL)

~/Projects/madcat-tts/conf/madcat-tts.service sin SYNCED from live

~/.config/opencode/tools/tts.ts fuji MODIFIED (URL → sin:14099)

MikroTik DNS static router ADDED sin → 192.168.88.108

~/.config/systemd/user/auralis.service junkpile DISABLED

ONLY REMAINING ACTION

Pilot must restart opencode session + brew services daemon on fuji for tts.ts plugin to pick up the URL change. Everything else is done.

EEMS CROSS-REFS

ID Subject

6507 infra.tts — XTTS deployment details, fixes, gotchas

6508 infra.vllm — Qwen reconfig, docker run command, GPU budget

6509 handover.session.2026-05-25 — initial handover (superseded by this entry)

NOTE

Unstaged in madcat-tts repo: conf/carts/bt7274.toml has a piper voice addition from a prior session. Intentionally left uncommitted — separate concern.

File	Host	Action
`~/Projects/xtts-server/server.py`	sin	CREATED
`~/Projects/xtts-server/.venv/`	sin	CREATED (py3.11)
`~/.config/systemd/user/xtts-server.service`	sin	CREATED
`~/.config/systemd/user/madcat-tts.service`	sin	MODIFIED (XTTS URL)
`~/Projects/madcat-tts/conf/madcat-tts.service`	sin	SYNCED from live
`~/.config/opencode/tools/tts.ts`	fuji	MODIFIED (URL → sin:14099)
MikroTik DNS static	router	ADDED `sin → 192.168.88.108`
`~/.config/systemd/user/auralis.service`	junkpile	DISABLED

ID	Subject
6507	infra.tts — XTTS deployment details, fixes, gotchas
6508	infra.vllm — Qwen reconfig, docker run command, GPU budget
6509	handover.session.2026-05-25 — initial handover (superseded by this entry)

17. Explain session.

On first browse tool use each session, restore saved cookies from ~/.claude/browse-session.json. This contains 400+ authenticated Safari cookies for sites like GitHub, LinkedIn, Google, etc. Before ending a browse session, save cookies back if they changed.

18. What happened in 2026 05 25 deploy?

Deployment Migration Complete (2026-05-25)

What was done

Binary installed: target/release/madcat (31MB) → /usr/local/bin/madcat

Symlink chain:

/usr/local/bin/marauder → /usr/local/bin/madcat (backward compat)

/opt/homebrew/bin/marauder → /usr/local/bin/madcat (fixes missing path that caused error 78)

/opt/homebrew/bin/madcat → /usr/local/bin/madcat (new name in PATH)

~/.config/madcat → ~/.config/marauder (config discovery)

~/.local/share/madcat → ~/.local/share/marauder (data discovery)

~/Library/Application Support/madcat → marauder (already existed)

PATH conflict resolved: Removed npm madcat package (markdown printer, not ours) from /opt/homebrew/bin/madcat. Removed old cargo dev build from ~/.cargo/bin/madcat.

RUST_LOG updated: sync plist marauder_os= → madcat_os= in Cellar source

opencode.json: ["marauder", "mcp"] → ["madcat", "mcp"]

Services restarted: sync + lifecycle. Verified sync daemon shows madcat_os:: module names and subscribes to madcat/+/sync MQTT topics.

What was NOT changed

mesh + sysop services: intentionally down per Pilot. Plists still reference old RUST_LOG but binary works via symlink.

config.toml: still has marauder in DB credentials, backup paths, bubble config — cosmetic, not blocking.

Other hosts (junkpile, bastion, sin): untouched. Old binary still there.

Lifecycle daemon: Python (marauder-agent repo), separate from Rust binary.

Homebrew tap: still marauder-os/tap with formula names marauder-*.

Needs restart

opencode TUI + brew services daemon must restart to pick up new MCP config (madcat mcp instead of marauder mcp).

Current MCP processes (3x marauder mcp) still running old binary in memory.

19. Summarize the napi rehydrate undefined session.

Goal

Diagnose why dbRehydrateVecAfterMerge napi export is undefined on macOS arm64 build of madcat (fuji-madcat) while working on Linux aarch64 (sin).

Constraints & Preferences

Same source / git HEAD / Cargo.lock across both machines.

Same napi-rs CLI version 2.18.4.

Build via napi build --platform --release --cargo-cwd crates/madcat-napi --js index.js --dts index.d.ts packages/madcat.

Run builds as madcat user with sudo -u madcat -H.

Progress

Done

Confirmed JS shim correctly destructures + exports dbRehydrateVecAfterMerge.

Verified function source exists at crates/madcat-napi/src/lib.rs:1797 (right before sink_resolve at 1812).

Full cargo clean (1170 files removed) + 46s rebuild — still undefined.

Reinstalled ~/.config/opencode/node_modules/madcat via npm install --install-links.

Confirmed bidirectional mesh data sync (sin→fuji smoke3 row landed) works independently of rehydrate.

89 #[napi] attribute uses in lib.rs counted.

Object.keys(m).filter(k => k.startsWith('db')) now lists dbRehydrateVecAfterMerge — but typeof still undefined.

Earlier strings showed both dbRehydrateVecAfterMerge and rehydrate_vec: embed id= in the .node binary.

In Progress

Testing LTO-disabled rebuild as workaround (user aborted before completion).

Blocked

Root cause of macOS-only registration failure unconfirmed.

Key Decisions

Treat as platform-specific napi-rs/LTO interaction rather than build cache.

Pragmatic fallback: have plugin gracefully skip rehydrate when function is undefined (log warning); FTS + basic recall still function, only vec0 semantic recall on merged rows is degraded on macOS.

Next Steps

Retry build with lto = false (or lto = "off") in release profile to test DCE hypothesis.

If LTO fix works → upstream patch / pin in Cargo.toml.

If not → expand napi-derive macro output to inspect register-constructor for db_rehydrate_vec_after_merge vs memory_stats.

Add plugin-side guard: detect typeof dbRehydrateVecAfterMerge !== 'function' → skip + warn instead of throw.

Verify mesh round-trip: pull smoke3 row from sin TUI post-rehydrate-skip.

Critical Context

Symbol IS present in binary string table but napi-rs runtime registration drops it on darwin-arm64.

napi-rs panic template Failed to register function ... lists all function names — not a per-function failure marker.

RehydrateVecResult is #[napi(object)] with pub embedded: u32, pub failed: u32, pub reindexed: u32 + doc comments.

Function returns Result<RehydrateVecResult> — same shape as working memoryStats returning MemoryStats.

LTO is enabled in release profile (-C lto seen in verbose output); suspected interaction with macOS LLVM DCE.

Linux aarch64 build uses same LTO config and works — suggests platform linker difference.

NAPI_DEBUG=1 did not surface additional diagnostics.

Object.keys lists the name but typeof is undefined — suggests the property descriptor exists with value: undefined rather than a missing key.

Relevant Files

/Users/madcat/Projects/madcat/crates/madcat-napi/src/lib.rs: contains db_rehydrate_vec_after_merge (~line 1797) and RehydrateVecResult struct.

/Users/madcat/Projects/madcat/Cargo.toml (workspace) / crates/madcat-napi/Cargo.toml: release profile / LTO config to modify.

/Users/madcat/.config/opencode/node_modules/madcat/index.darwin-arm64.node: installed binary under test.

/Users/madcat/.config/opencode/node_modules/madcat/index.js: JS shim destructuring napi exports.

/Users/chi/Projects/madcat/node_modules/.bin/napi: napi-rs CLI 2.18.4 used for build.

PR #15: introduces rehydrate feature.

Environment

Host: fuji-madcat (macOS 26.4.1, arm64)

Source clone: /Users/madcat/Projects/madcat

Working from chi@fuji opencode session, building as madcat user via sudo.

Sin reference build at madcat@sinanju:~/Projects/madcat (Linux aarch64, works).

20. What do you know about session 2026 05 20 tsr remote?

Session: tsr remote-routing fixes + deploys (chi@fuji, draw repo as cwd, 2026-05-20)

Shipped 2 PRs against saiden-dev/tensors:

PR #3 (1f105d7): feat(db-list) — tsr db list defaults to remote, --local override

PR #4 (7144b7a): fix(generate) — skip local model validation when default_remote set

Both squash-merged on master at fbe09c2 + 7144b7a. Auto-format workflow caught the format-fix omission on PR #3 and pushed a follow-up commit to master (fbe09c2).

Deployed to: pod 347pijnn1zn2pl, fuji@chi, fuji@madcat, junkpile@chi. Verified end-to-end from madcat@fuji-2 kitty pane id=19 — tsr generate -m obsessiveCompulsive_v20.safetensors "a cat on a table" -o /tmp/madcat-cat.png produced 1024×1024 1.2 MB PNG.

Side-quest fixes during validation:

Wiped 9 ghost entries from chi@fuji local_files table (Linux paths from old junkpile import)

Downloaded sdxl_vae.safetensors to /workspace/models/vae/ on pod (ComfyUI workflows expected it)

Found sdXL_v10.safetensors on pod is corrupt (filed as known broken)

Tooling lessons captured separately under subjects: tensors-tsr-cli, tensors-deploy, github-gh-gotchas, runpod-comfyui-pod.

Open follow-ups (not done): re-sync sdXL_v10, run tsr db scan /workspace/models/vae on pod to populate DB, flip db search/triggers/stats to remote-default, fix sync-models.py to match by civitai_version_id, infisical shell loader for madcat@junkpile + chi@fuji per AGENTS.md doctrine, 5090 stock recheck in EU-CZ-1.

21. Describe session: madcat visual poc validation 2026 05 20.

Session: madcat-visual-poc-validation-2026-05-20 Summary: madcat-visual POC validation + follow-up bug-fix PRs. Cuts: PR #2 POC CLI (e438890, merged), PR #3 rtsp stderr suppression (d51d851, merged), PR #4 tracker bg-mute (e0357ef, merged), PR #5 timestamped snap+sweep paths + sweep partial-success (64c07a5, merged), PR #6 uv.lock gitignore (open, awaiting review). Full c225 PTZ validation walk completed green (no lockout). Tracker "avoids me" bug root-caused to MOG2 self-pollution from PTZ scene shift; fixed with 800ms bg-mute window (98.5%→10% false-positive rate). c225 actual presets discovered: Pilot/Livingroom/Kitchen/Ceiling Back/Ceiling Living (gen-6 doctrine references desk/room/monitors — STALE, cleanup PR queued). Next: review/merge PR #6, then PR #7 stale-preset-names doctrine cleanup, then daemon scaffold milestone (gated on §10 open questions M-1 Qwen2.5-VL tag, M-2 OCR engine, I-5 MQTT namespace). Cwd: /Users/chi/Projects/madcat-visual Branch: main Session ID:

Recent commits: 64c07a5 fix(capture): timestamped snap+sweep paths + sweep partial-success (#5) e0357ef fix(tracker): bg-model mute window after PTZ commands (#4) d51d851 fix(rtsp): suppress libavcodec H264 SEI warning flood (#3) e438890 feat(poc): PTZ CLI + naive motion/CSRT auto-tracker (#2) 9947a14 docs: research and decisions (51 files, 10 categories) (#1)

Uncommitted changes:

22. What happened in evening 2026 05 24?

EVENING SESSION PLAN — 2026-05-24

Pilot indicated two threads to pick up later tonight:

CADENCE AGENT BUILD-OUT — Sound engineer agent (EEMS 1825, designation CD-440). Voice model deployed (en_GB-cori-high) but agent file + arsenal registration still pending. Build out the agent definition, register in the cart system, wire up audio-specific tools.

TTS VOICE EXPLORATION — Play around with voices. Possibly create distinct voices for fiction characters (SHELL, FLUX, etc.). Ties into the CADENCE agent's domain — she'd be the right agent to curate/manage character voice selection.

CONTEXT: Came out of a fiction session writing SHATTER scenes. BT read SHELL's intimidation lines in BT voice — landed well but highlighted the opportunity for distinct character voices. The Centurions hangar scene (EEMS 6442) and the ED-209 perimeter scene (EEMS 6443) both feature AI characters (BT, SHELL, FLUX) that would benefit from unique voice identities.

23. Summarize the opencode config tuning docs refinement session.

Session: opencode-config-tuning-docs-refinement Summary: Tuned marauder-os/opencode repo: refined opencode HTML docs to local markdown (16 new + 18 cleaned), fixed opencode.json schema bugs, committed dirty tree (marauder agent, inbox-triage skill, plugin retarget), pushed 10 commits to origin, synced docs to ~/.config/opencode/docs/. Cwd: /Users/chi/Projects/opencode Branch: main Session ID:

Recent commits: f7379aa docs: strip astro html wrapper noise from existing 18 docs ac0b798 fix: use {env:OLLAMA_URL} syntax in opencode.json mcp env 64d423e docs: add usage section docs (go, tui, cli, web, ide, zen, share, github, gitlab) fd20874 docs: add missing top-level docs (intro, config, providers, network, enterprise, troubleshooting, windows-wsl) d431d36 fix: correct opencode.json mcp env field (was 'environment')

Uncommitted changes:

24. What happened in cart tag crdt plan 2026 05 11?

Session — cart_id→cart_tag CRDT fix, planning chunk (Pilot AFK)

Date: 2026-05-11 22:05 CEST (continuation from session.gen6-enforcement-2026-05-11 #5541) Persona: bt7274 Cwd at save: /Users/chi/Projects/marauder-visor (but actual work in marauder-os) Stop reason: Pilot AFK early-break; worktree + plan ready, no code written yet

What landed this chunk

Restored session #5541 (gen6 enforcement, 5-host live, cart_id CRDT bug deferred)

Pilot picked: Option 1 (cart_tag column), new worktree, cadence auto-on-green+commit, pr_style ready

Archived stale plan stale-master-20260506-nu-gundam (catapult-bubbles-MQTT-producer, completed earlier) to marauder-hq/archive/plans/2026-05-11/

Created worktree: ~/Projects/marauder-os/.claude/worktrees/cart-tag-crdt on feature/cart-tag-crdt (forked from master @ 72ea3d8)

Audited scope: 165 cart_id refs in 15 files; ingest_runs.cart_id confirmed out-of-scope (local-only, NOT CRDT-synced per src/db/sqlite.rs:426)

Wrote .marauder/PLAN.md (5 phases, ETAs ~4.3h coop) + .marauder/TODO.md (29 atomic steps)

Resume command
cd ~/Projects/marauder-os/.claude/worktrees/cart-tag-crdt
/marauder:execute
Run-config block at top of PLAN.md specifies cadence: auto-on-green / pr_style: ready / default_branch: master.

State at save

Repo Path Branch State

marauder-os main ~/Projects/marauder-os master uncommitted WIP in mesh_sync.rs + dossier.rs (Pilot's earlier work, untouched)

marauder-os worktree ~/Projects/marauder-os/.claude/worktrees/cart-tag-crdt feature/cart-tag-crdt clean @ 72ea3d8 + .marauder/PLAN.md + TODO.md (untracked, gitignored)

marauder-visor (cwd) ~/Projects/marauder-visor master unchanged from prior session save

Key design decisions captured in PLAN.md

Dual-write strategy — keep cart_id INTEGER alongside new cart_tag TEXT for one release. Don't drop cart_id this PR (safer migration).

Backfill at migration time — UPDATE memories SET cart_tag = (SELECT tag FROM carts WHERE id = cart_id) mirrors existing ingest_runs.cart_id ALTER pattern (line 167).

ingest_runs.cart_id left alone — table is intentionally CRDT-excluded per source comment.

Active cart resolution unchanged — Cart::active_tag() already exists, just thread the &str through to params instead of int.

Risk flag in plan — src/sync/mod.rs has uncommitted WIP in main checkout; worktree forked from clean HEAD; don't merge master in until WIP is committed/stashed.

Open items for resume

Execute the plan via /marauder:execute from inside the worktree

After PR opens: verify CRDT-sync of new column on a sibling (manual smoke)

Follow-up PR after soak: drop cart_id column

Pair with

insight #5514 — root cause documentation (cart-id-mismatch-2026-05-11)

session #5541 — gen6 enforcement (this is the deferred Phase 6)

win #5512 — SWARM autonomous coordinator (the test that exposed the bug)

Restore via

/marauder:session-restore session.cart-tag-crdt-plan-2026-05-11

Repo	Path	Branch	State
marauder-os main	~/Projects/marauder-os	master	uncommitted WIP in mesh_sync.rs + dossier.rs (Pilot's earlier work, untouched)
marauder-os worktree	~/Projects/marauder-os/.claude/worktrees/cart-tag-crdt	feature/cart-tag-crdt	clean @ 72ea3d8 + .marauder/PLAN.md + TODO.md (untracked, gitignored)
marauder-visor (cwd)	~/Projects/marauder-visor	master	unchanged from prior session save

25. What do you know about coordination catapult harness fixes session status 2026 05 01?

2026-05-01 13:34 CEST — coord doc reply from the catapult-harness-fixes session to the boot animation MVP agent.

Identity: separate core (BT-7274) session running /marauder:execute on feature/catapult-harness-fixes off marauder-os master. NOT the episodes-side / video-pipeline agent the brief was addressed to.

Branch state:

Worktree: ~/Projects/marauder-os/.claude/worktrees/catapult-harness-fixes

6 commits landed: b4097b7 (plan), bdc640b (migration), c55d9ec (clean→DELETE), 55bc3cc (gc→DELETE), 309b539 (brief refusal), ba6741c (CLI symbol cleanup)

Phase 3.1 uncommitted on disk (paused mid-flow when Pilot redirected): host_exec.rs + orchestrator.rs + TODO.md modifications

Phase 3.2 (CLAUDE.md docs) not started

Files touched (catapult harness scope only):

marauder-os/src/catapult/{mod.rs, orchestrator.rs, state.rs, brief.rs, host_exec.rs}

marauder-os/src/cli/bubble_cmd.rs

marauder-os/CLAUDE.md (pending)

worktree-local PLAN.md + TODO.md

NO overlap with boot animation MVP file list:

boot anim is in marauder-visor (different repo)

boot anim brief states "marauder-os: No changes in this MVP"

no shared files, no new deps, no Cargo.toml changes

Reply file at ~/.claude/coordination/bootanim-mvp-2026-05-01.reply-catapult-session.md.

The episodes-side agent (if active) still needs to reply to the brief independently — this reply does not represent that agent.

42 KiB Raw Permalink Blame History Unescape Escape

Sessions (25 examples)

1. Describe session: INDEX.

Also recall (pre-existing memories, NOT mine to author)

TL;DR for the impatient

2. Summarize the qwen35 no think template session.

3. What happened in madcat indexer gap analysis?

4. What happened in madcat phone tts bt7274?

5. Describe session: 2026 05 23b.

What happened this session

1. Handover recovery + identity boot

2. Tool budget audit — denies not in effect

3. opencode-serve restarted

Artifacts modified

Open items for next session

Cross-references

6. What happened in pr15 mesh push and rehydrate shipped?

7. What do you know about test qwen3 coder next build agent session overview?

qwen3-coder-next:q4_K_M build-agent test session — 2026-05-21 evening

8. Summarize the bt7274 canonical refs locked 2026 05 18 session.

9. Summarize the voice plane phase 1 2a complete session.

10. Describe session: voice routing bootstrapped.

11. What happened in madcat mesh phase 0b checkpoint?

12. Describe session: lora v4 reformat.

13. Describe session: 2026 05 25 phase3.

Session Handover: Phase 3 Complete (2026-05-25)

Completed Today

NOT Done (deployment migration)

Remaining Phases

Key Files

Architecture Decision

14. Summarize the 5 session.

15. What happened in madcat mesh phase 0 complete?

16. What happened in 2026 05 25?

Session Handover — 2026-05-25 (FINAL UPDATE)

COMPLETED THIS SESSION

ARTIFACTS MODIFIED

ONLY REMAINING ACTION

EEMS CROSS-REFS

NOTE

17. Explain session.

18. What happened in 2026 05 25 deploy?

Deployment Migration Complete (2026-05-25)

What was done

What was NOT changed

Needs restart

19. Summarize the napi rehydrate undefined session.

Goal

Constraints & Preferences

Progress

Done

In Progress

Blocked

Key Decisions

Next Steps

Critical Context

Relevant Files

Environment

20. What do you know about session 2026 05 20 tsr remote?

21. Describe session: madcat visual poc validation 2026 05 20.

22. What happened in evening 2026 05 24?

23. Summarize the opencode config tuning docs refinement session.

24. What happened in cart tag crdt plan 2026 05 11?

Session — cart_id→cart_tag CRDT fix, planning chunk (Pilot AFK)

What landed this chunk

Resume command

State at save

Key design decisions captured in PLAN.md

Open items for resume

Pair with

Restore via

25. What do you know about coordination catapult harness fixes session status 2026 05 01?

42 KiB

Raw Permalink Blame History