Version bump in pyproject and __init__, CHANGELOG dated 2026-09-09,
README install lower bound raised to >=1.3.5, and release-prep evidence
(remote check, gates, real gateway smoke and one bounded live probe)
recorded in the 1.3.5 validation finding.
Field counts come from inspect, not memory: record_llm_call takes 36
parameters, COLUMNS has 36 entries, the physical table has 37.
- README: capability table says 36 fields and names the three row kinds;
new section covers reading call_stats, the five SQL migration items,
the attribution query and the storage-side upgrade
- README/.env.example/ARCHITECTURE: error_body follows the summarize_body
limit and the structured-exhaustion error carries its own bounded
explanation, so neither is inside PGW_TELEMETRY_TEXT_CAP coverage
- ARCHITECTURE 7.8: the ten columns with per-column semantics, the I3/I4
invariants, operation versus exc.operation, and the assembly gate
- CHANGELOG: unreleased section listing the four public changes and what
downstream must do, in particular counting failures by event_kind and
the assembly-time error for custom recorders
- schemas/llm-calls: the ten columns plus a three-row-kind section
- metrics/call-telemetry-coverage: 1.3.5 coverage contract, real live
baselines left unfilled rather than stating a fake percentage
Validation record records the T4 evidence: mechanical migration red then
green, the four PG acceptance cases, the seven-item mutation matrix with
all seven killed and the copy restored to an identical digest, plus the
PYTHONPATH pitfall that made the first mutation round silently test the
original source.
Version numbers and release steps are deliberately untouched.
Grow the telemetry contract from 26 to 36 fields and give every logical
call a failure terminal row, so SQL can finally answer "how many calls
failed" and "why did the whole pool die".
Schema and port move together with the emitter writes in one commit:
splitting them would ship columns that nothing populates.
- schema: append 10 nullable columns (scope, operation, logical_call_id,
event_kind, http_status_code, error_type, cause_type, error_body,
attempts, total_latency_ms) to all five definition sites in one order
- ports: 10 keyword-only parameters without defaults; the protocol
signature is now the single source the assembly gate derives from
- emitter: take domain exception objects instead of pre-flattened text
and pin down the diagnostics in one helper; a relabelled 503 stays
503 and success rows leave all five columns NULL
- emitter: reject recorders whose record_llm_call cannot accept the
current field shape at assembly time, since _record would otherwise
swallow the TypeError and drop every row while calls keep succeeding
- clients: write at most one terminal row per logical call through a
single shared exit, deduplicated by the call context; TelemetryMW
stops writing terminals so the two sites cannot double count
- clients: cancellation stays best effort and propagates, non-domain
exceptions get no terminal row and keep their classification
- transports: give _status_to_error an explicit operation and fix the
historically mislabelled embedding HTTP failures
- structured: promote the bounded error formatter so the reask feedback
and the terminal explanation share one set of limits
Terminal rows carry no cost and no tokens, so cost aggregation is
unchanged; failure counts must now filter on event_kind.
The failing assertion was never testing the script. It compared the row
count of a table three other projects also write to, before and after
the run, and the failure it reported (61 rows became 12) landed while
the script under test was demonstrably confined to its own schema.
A row count cannot carry the property that assertion stood in for. It
goes red when anyone else writes, and green when an outside insert
happens to cancel out a wrong delete. The second half is the one that
was guarding against a dropped audit table.
So the property moves to where the database enforces it: the script
runs as a role that owns its scratch table and holds no grant at all on
the shared one. Falling back to public stops being something a later
assertion might notice and becomes permission denied. Measured, along
with the rest of the Postgres semantics this rests on.
The tool grows --table so the target stops being whatever search_path
resolves to. The table half is pinned to llm_calls: without that, one
typo turns a telemetry cleaner into a general purpose row deleter.
Codex raised six problems and all are folded in. The one place this
still disagrees with it is recorded with the reason.
The four red e2e cases were blamed on MiniMax-M3 no longer reasoning.
Raw gateway probes show the opposite: M3 reasons fine (124 chars of
reasoning_content, prompt 194 to 216, completion 3 to 60). What changed
is that the MiniMax route stopped returning completion_tokens_details,
while qwen and deepseek still do on the same gateway and key. The
library already holds 185 chars of proof in LLMResponse.thinking and
never feeds it into any verdict.
The design turns that verdict into a first-class return value judged
from multiple signals, says UNKNOWN when a single response cannot tell,
and reconciles it against the capability table so a stale declaration
becomes a warning instead of a silent illusion.
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.
A sixteen-row matrix over 127 real calls: disable and enable on
MiniMax-M3 in both streaming and non-streaming mode, extra_body winning
over the profile slot, qwen and deepseek still disabling correctly, a
drift sentinel that re-derives every registered capability from live
behaviour, and the assembly guard refusing the models that cannot
comply.
Two judgement criteria had to be corrected by the data they were meant
to judge. Output length cannot separate the two regimes at all -- the
disabled runs reach 46 tokens when the model narrates its working in
the visible answer, and the enabled runs drop to 13 when medium effort
barely thinks. reasoning_tokens separates them cleanly in both
directions, which is precisely what issue #6 was collected for. A
second anchor compares prompt_tokens between the two regimes: the
vendor injects a reasoning instruction when thinking is on, so the
input side grows, and comparing the two runs relatively avoids
hardcoding any vendor number.
Provider names are mapped explicitly rather than guessed from the model
string; guessing had silently skipped the qwen row behind a "source
unavailable" reason that was not true.
Findings: live-API measurements across MiniMax M3/M2.7/M2.5, qwen and
deepseek, plus a survey of how nine unified gateways model per-model
parameter divergence. Key facts: reasoning_effort is MiniMax's real
switch, M2.x reasoning is mandatory and cannot be disabled, and the
relay's local token-count fallback silently drops reasoning_tokens.
Design: keep the parameter shape at provider level, push capability
down to model level, split "unknown" / "unsupported" / "no opinion"
into three distinct values, and fail at assembly time when a model
cannot honour enable_thinking=False.
AIMD ceiling now respects per-source max_concurrency and the pacer is
assembled explicitly in the client; MIN_CALLS parses as strict int;
acceptance doc corrects source-5 attempt count to 549; design and
migration notes aligned with implemented 429/stall/suppression
semantics and AIMD constants documented.
Records the human decision to test against the real gateway with real
data instead of building a mock gateway, six execution scenarios with
fault-source mixing, hard invariants scored from our own telemetry,
and the corpus inventory pulled from the lab server.
iomgaa