Commit Graph

18 Commits

Author SHA1 Message Date
iomgaa 48805cb9fb fix: address the independent verification findings (issue #5, #6)
The verifier caught that the disable-direction evidence only proved "no
regression", not "actually took effect": on M3 the disabled runs and the
no-opinion baseline are identically distributed, because that model does
not reason by default anyway. So the disable runs alone cannot rule out
the very failure mode issue #5 is about -- the parameter being silently
dropped upstream. The bogus-value experiment that does rule it out was
sitting in the findings document instead of the test suite; it is now
case L3b, and the L3 assertion that could never fail is gone.

Also from the review: the e2e helper caught bare Exception, which would
have disguised a library bug as an unavailable source, exactly the
silence the reporting discipline exists to prevent; the unregistered
model warning fired on every request instead of once per source; and the
transport caught ValueError broadly enough to mislabel unrelated errors,
now narrowed to a dedicated ThinkingUnsupportedError.

The design and plan still described the original judgement criteria,
which the measurements had already overturned. Both now match what the
tests actually do, and the design no longer claims the only new failure
surface is the openai one -- dissect configures MiniMax-M2.7 with
ENABLE_THINKING=false and will fail at assembly, which has to be
coordinated before this merges.
2026-08-02 07:40:06 -04:00
iomgaa 82f4ec4910 feat: model the thinking switch as shape plus capability (issue #5)
enable_thinking=False was a no-op for minimax and openai sources: both
profiles had empty dicts on each side, so the payload update injected
nothing while the caller believed reasoning had been turned off. A
downstream project was blocked on exactly this.

The root cause is that an empty dict meant two different things -- "no
injection needed" and "we do not know how this provider spells it" --
and that a provider-level table cannot express what turned out to be a
per-model property. Live testing showed MiniMax-M3 can disable
reasoning via reasoning_effort while M2.7 and M2.5 cannot be disabled
at all, which two external registries independently confirm.

So the shape stays at provider level and a capability table joins it at
model level. Unknown, unsupported and no-opinion are now three distinct
values, and resolve_thinking is the single place they meet: it raises at
assembly time when a model cannot honour the request, warns and injects
for unregistered models, and injects silently otherwise. Every registered
capability carries the evidence it was derived from.

enable_thinking also joins the cache fingerprint, since it now really
does change the request body.
2026-08-02 06:20:24 -04:00
iomgaa 89ff916bc8 feat: collect reasoning_tokens from the provider usage payload (issue #6)
Reasoning tokens are already counted inside completion_tokens, so the
cost total was never wrong -- what was missing is the attribution: how
much of a call was spent thinking rather than answering.

LLMResponse and TransportResult each gain a trailing reasoning_tokens
field, and the telemetry port grows from 21 to 22 columns with the new
column appended in both backends so fresh and migrated schemas keep the
same physical order.

None means this particular call did not report the field, not that the
source never reports it: a relay that falls back to a local tokenizer
replaces the whole usage object and drops completion_tokens_details.
Downstream checks must therefore read "in (None, 0)"; no provider was
observed reporting a literal zero.
2026-08-02 05:55:37 -04:00
iomgaa 6bb64ca938 feat: accept sampling overlay on chat() and per-source extra_body
Priority is structured injection > per-call overlay > per-source config,
and extra_body now takes part in the cache fingerprint.
2026-07-31 21:17:49 -04:00
iomgaa 86fb4d5536 fix: keep the postgres backfill from disabling telemetry or locking the table 2026-07-31 10:42:55 -04:00
iomgaa 32d7869043 fix: harden the observability fields against the verifier findings 2026-07-31 08:28:41 -04:00
iomgaa 0aa7202c87 feat: collect provider cache tokens and reported model in transport 2026-07-31 07:51:47 -04:00
iomgaa cd8bebba00 refactor: drop the now-unused source parameter from usage resolvers
三态兜底不再读源配置,_resolve_usage / _resolve_stream_usage /
_resolve_embedding_usage 的 source 形参已成死参数;保留它等于在签名上继续
宣称用量口径依赖源配置,与本次改动切断该依赖的意图相悖。同步三个调用点
与测试的直接调用;SourceConfig 仍被文件内错误翻译等函数使用,import 保留。
2026-07-30 10:46:52 -04:00
iomgaa 195454d2e3 fix: stop passing est_tokens off as measured usage
usage 帧缺失/非法时不再拿 est_tokens(最坏情形上界)当实测值,chat 与
embedding 两处兜底改记 0 并标 unavailable;打捞覆盖加 measured 前置条件,
避免 0/0 被洗成 estimated 而算出假的 0.0。embedding 全批合并扩三态(任一批
不可得 → 整体不可得),_total_cost 遇不可得批整体记 NULL。
2026-07-30 10:39:32 -04:00
iomgaa 2bdcb33123 style: wrap page_idx validation line for formatter 2026-07-22 03:20:09 -04:00
iomgaa 3c9f306ea3 fix: address M3 verifier findings on soak invariants and probe tests 2026-07-22 02:21:33 -04:00
iomgaa fdd36e0e1f style: apply ruff format to OCR modules 2026-07-22 01:43:55 -04:00
iomgaa dfbb2f8f10 feat: add MonkeyOCR dual-endpoint transport 2026-07-21 22:36:14 -04:00
iomgaa 193d67da93 feat: add embedding types, port and openai-compat transport 2026-07-21 01:00:55 -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 7b9815f4bc feat: add gateway client with env-driven assembly
Includes config aggregation for multi-source env keys, from_env and
from_settings factories with explicit shared-backend injection,
gather_bounded, top-level exports, tightened import-linter layers with
the gate removed from the Makefile, and the finalized .env.example.
2026-07-20 07:47:05 -04:00
iomgaa 454a8b5e0f feat: add openai-compatible transport with sse parsing and error translation 2026-07-20 06:45:55 -04:00
iomgaa fcadd8cd8e chore: scaffold m1 module skeleton 2026-07-20 06:27:34 -04:00