docker logs tatlock has been empty for months and the /app/logs
mount untouched since 2025-12. Not a broken handler: the stdout
StreamHandler was correct all along, but the production default
level was WARNING ("minimal noise") and a healthy service warns
roughly never — startup, backend flavor detection and the wrapper's
balancing/compaction signals were all suppressed, which is exactly
what made the serving cutover unverifiable from logs on 2026-09-12.
Production now defaults to INFO; LOG_LEVEL stays the override for
when noise is ever the real problem; development keeps DEBUG. The
mount was always decorative — no file handler exists, docker logs is
the log. Three tests pin the level table, the WARNING-revert
mutation shown to fail its test.
Also filed T-7: the full suite flaked once and passed on rerun for
the second time — next occurrence keeps the failing run's output.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The provider assigned self._openai_client, an attribute nobody reads
— OllamaProvider.client serves self._client — so the null-content
sanitizer, the wrapper signal reading and the OLLAMA_TIMEOUT cap were
all silently dead in production (sessions unaffected; they ride
ModelSettings). Found via webber's identical bug on 2026-09-13.
Three fixes travel together, because wiring alone would have traded a
silent bypass for a loud crash: the client goes through the official
openai_client constructor parameter; the parent-chat lookup survives
openai's property/cached_property descriptor change (this venv's
2.11.0 is the latter — the old hardcoded .fget would have raised
AttributeError on the first wired completion; ported from webber's
2026-08-11 fix); and the balancing/compaction signals are read from
the response body's model_extra inside create() — the httpx
event-hook approach demonstrably never fires under the openai SDK.
The tests now assert through provider.client, the property
pydantic_ai actually reads. The old ones asserted on the dead
attribute and stayed green for the entire bypass — a check whose
subject is not the real thing cannot fail for the real reason
(workspace D-24's shape). Three mutations shown to fail their tests:
the dead-attribute wiring, the .fget-only lookup, and removing the
signal read from the request path. 683 tests green; a live dev turn
through the wired client answers normally.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The flavor probe gains a third answer: the wrapper names itself on
/health, so behind OLLAMA_HOST tatlock now distinguishes boilerroom,
a bare llama-server, and Ollama. Through the wrapper each pipeline
phase is a named session with the decided eviction ranking —
tatlock-steward/-orchestrate/-synthesize at 40, librarian at 30,
lower parks sooner (webber will sit at 20; Open WebUI stays
session-less and can never evict anyone). Against a bare llama-server
the raw id_slot pins survive unchanged, Ollama gets neither, and an
unprobed flavor sends nothing rather than guessing — the backend
stays swappable by env alone. tool_choice through the wrapper follows
the llama-server rule, since that is who answers.
The wrapper's balancing and compaction-due signals are read
everywhere: an httpx response hook on the provider covers every
PydanticAI call, streams included, and the steward's raw call reads
the body extras. Acting on compaction_due is a future ticket — the
signal just must not pass silently.
Verified end to end against the live wrapper: the dev server probed
flavor=boilerroom, a full pipeline turn answered in 5.7 s, and
GET /sessions showed all three phase sessions resident at rank 40
with engine-reported occupancies. The demonstration also filled the
production slot map — session-less prod delegations would have 503d
— cleared by a wrapper restart and filed as boilerroom T-11 (sessions
need an exit). A latent test flaw surfaced too: the ollama
tool_choice test relied on the dev backend probing as ollama; it now
pins the flavor it claims to test.
27 selector tests (9 new), 677 total green; three mutations shown to
fail their tests (librarian rank, the wrapper branch, the no-nudge
set); the new wrapper contract class runs 10/10 against the live
boundary.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
T-4 carries the decided usage ranking — tatlock 40, librarian 30,
webber 20 (workspace T-137), Open WebUI session-less and deprecating.
T-5: docker logs is empty and the log mount untouched since 2025-12,
which made today's cutover verification blind.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
TTFT equals wall time today: nothing streams until the three-phase
pipeline completes, so desklock's time-to-first-word is the full
pipeline (14.9 s mean, measured 2026-09-11). Workspace D-60 names
streaming synthesis a first-class goal of the serving rework.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Filed separately from the settings work in tatlock-ui because it commits here
and closes separately. Related to workspace T-13, which is scoped to the
Portainer stack alone and would leave this copy behind.
Co-Authored-By: Claude <noreply@anthropic.com>
`make typecheck` reports 95 errors in 31 files and has never once passed, so
gating on it did not enforce a standard — it blocked every push to this repo,
including 57fa6c1, the commit that added the gate. Four commits were queued
behind a check that could not be satisfied without a dedicated typing pass.
This is not lowering a bar. The bar was never up: nothing regressed to produce
those errors, they predate the gate, and the same 103 were present before this
session's lint work. The gap is now announced on every push, naming the ticket
that closes it, which is the arrangement core-api, scheduler and library-desk
already use for their ungated stages.
The difference worth preserving: a threshold quietly relaxed hides a problem, and
a declared gap advertises one. This prints five lines about what it is not
checking and why, every time anyone pushes.
typecheck remains a target and still runs on demand. T-1 in this repo's vault
carries the measured breakdown — 29 missing annotations being the bulk — and
removing these lines is that ticket's definition of done.
Co-Authored-By: Claude <noreply@anthropic.com>
Commits a .claude/settings.json rather than leaving permissions to
per-developer local state, and initialises a pql vault for this repo's
tickets and internal decisions.
Every git deny rule appears in both the `git <verb>` and `git * <verb>`
forms. Only the second catches `git -C <path>`, and without it the whole
deny list is decorative -- it looks like a policy and stops nothing.
The allow list carries pql's absolute path alongside the bare name.
pql is installed to ~/.local/bin, which is on the login PATH but not the
one a non-interactive shell gets, so the bare-name rules match nothing on
their own and every call would prompt anyway.
.gitignore now covers .claude/settings.local.json, which is machine-local
and must never be shared. `pql init` contributed the .pql/* rules with an
exception for the changelog, which is the replication log of record and
has to be committed for tickets to travel with a clone.
Co-Authored-By: Claude <noreply@anthropic.com>
jpmschweitzerandClaude Fable 5