17 Commits

Author SHA1 Message Date
iomgaa c634cab35e docs: admit governance backend failures into the scope-level error model
GovernanceBackendError arrived with the M2 distributed backends but never
made it into the section 6.1 table, so it had no place in the taxonomy
callers actually read. That omission is why the README missed it too.

Records the reparenting, the new governance_backend_down reason, and why
SourceNotConfiguredError deliberately stays outside the reparented family:
a misconfigured source name must burn its failure budget and surface,
not retry forever in silence.
2026-08-06 04:22:35 -04:00
iomgaa 2958dc8231 docs: document sampling passthrough and the empty thinking profiles 2026-07-31 21:41:34 -04:00
iomgaa 58cb55b869 chore: release 1.0.4 instead of a minor bump 2026-07-31 11:11:55 -04:00
iomgaa 966d548245 chore: release 1.1.0 with the response observability fields 2026-07-31 08:08:37 -04:00
iomgaa d1520cc0a5 docs: realign authoritative docs with the three-state usage_source
ARCHITECTURE.md 四处: §4.4 预扣量改指 effective_est_tokens(); §5.1 补三态值域表与
cost NULL 口径(含缓存命中行的例外与缺口查询必带 cache_hit 限定); §7.1 打捞路径
由强制 estimated 改为仅在收到 usage 帧时降级; §7.7 est_tokens 降为可选调优覆盖并
写明 tpm//60 派生规则与既有的全局 TPM 闸限制。

migrations/chsanalyzer.md 行 151 由保留改判有意放弃并写入理由; G2 标记已闭。
schemas/llm-calls.md 同步三态与 cost 口径。
2026-07-30 11:11:01 -04:00
iomgaa e09362dcd1 docs: sync M4 outcomes into roadmap, architecture, and migration docs
VT migration abandoned (v1.0 scope becomes two projects), Q1 resolved
to Gitea PyPI, Q6 resolved as judge exemption (unwired zero-consumer
eval scaffolding), migration docs annotated with implementation errata,
and the reference/ read-only rule clarified for the worktree workflow.
2026-07-22 10:57:00 -04:00
iomgaa 0f9ecad2c4 docs: sync OCR architecture wording and close G1 R9 R10 2026-07-21 23:34:33 -04:00
iomgaa 910857fd13 docs: sync env template, migration notes and architecture for M2.5 2026-07-21 10:00:11 -04:00
iomgaa b165c2aae6 docs: finalize M2 design after human approval gate 2026-07-20 23:41:20 -04:00
iomgaa 8aaf8f200b docs: add M2 distributed design and record Q3 embedding decision 2026-07-20 23:01:29 -04:00
iomgaa 0b8460b6d5 fix: address independent verification findings
Classify empty completions as transient per human ruling (fixes flaky
real-gateway smoke and prevents caching empty responses), rename the
factory injection parameter gate to breaker per the frozen design,
rewrite the probe-entry cleanup without except BaseException, declare
python-dotenv explicitly, add a mid-backoff cancellation test, and
record all implementation errata in the design and architecture docs.
2026-07-20 22:01:26 -04:00
iomgaa 2fb968b851 docs: apply seven M1-design feedback amendments to architecture
Correct the section 6.1 reason enum against actual CHS code, make
retry_after_s a non-optional float, add structured_data to LLMResponse
extensions, finalize the structured parameter type, document SSE
missing-done semantics and watchdog thinking-token liveness, add the
StructuredMW layer to the default onion order, and register
middleware/structured.py in the module map.
2026-07-20 06:12:52 -04:00
iomgaa 034605c2b4 docs: move full multi-source behavior into M1 scope
Per 2026-07-20 human decisions: multi-source switching/cooldown ships
with M1 (retry-loop signatures freeze there), both GovDoc and
Video-Tree must pass the M1 onboarding smoke test, and Redis
integration tests use the lab's remote Redis with isolated namespaces.
2026-07-20 05:26:58 -04:00
iomgaa 48f82404ee docs: add D14 structured-output ladder decision
Define the five-step ladder (native-schema prevention, repair, shape
validation, bounded feedback re-ask, ResultInvalidError) as D14;
rewrite section 7.9 accordingly, give the structured parameter its
three-tier semantics in the chat() signature, and scope the bounded
re-ask outside transport retry and breaker counting.
2026-07-20 04:00:07 -04:00
iomgaa 07e772f522 docs: amend architecture per migration reverse constraints
Resolve 13 gaps flagged by the three migration documents: finalize
chat() signature with per-call cache namespace/salt, fix middleware
onion ordering (per-attempt source-scoped admission inside retry
loop), structured AllSourcesExhausted fields, est_tokens in
SourceConfig, per-scope resilience config keys, probe lease TTL,
settle/release idempotency, shared limiter/breaker backend semantics,
multimodal digest in telemetry, OCR trust_env and health check, API
stability rules, and correct the Q3 embedding claim.
2026-07-20 02:57:32 -04:00
iomgaa 4f2c149a9d docs: add D13 retry decision and development roadmap
Record tenacity vs self-built evaluation as D13 in ARCHITECTURE.md
(self-built wins: per-attempt orchestration, cancellation guarantees,
supply-chain discipline). Add research-wiki/ROADMAP.md expanding the
milestone table with ordering rationale and exit criteria.
2026-07-20 01:02:35 -04:00
iomgaa 3058f4c744 chore: bootstrap project scaffolding
Add architecture doc (research-wiki/ARCHITECTURE.md), CLAUDE.md with
tiered SOP for Fable 5, adapted .claude skills/hooks/settings, package
skeleton (src/polygateway), pyproject with import-linter contracts,
Makefile, .env.example and smoke test.
2026-07-20 00:49:10 -04:00