The telemetry field count is taken from inspect.signature, not from
memory, because that is the one the release checklist keeps catching.
llm-calls.md said 22 and was two rounds stale; fixing the title alone
would have left the table contradicting it, so tenant_id and meta are
documented too.
The production template needed no new column — it derives them with
LIKE. What it gained is an assertion that it must keep deriving them
and must not inline a column name, which is the drift that could
actually happen.
The changelog leads with the three breaking items. A patch number
carries no warning by design, so the entry has to.
The design traces the incident to four stacked defects rather than one bad
default: the pool is the only resource in the library that pre-allocates,
the kill switch keys off which step failed instead of what failed, the
degraded state can neither recover nor be observed, and the ownership rules
make the sanctioned sharing path unusable.
The plan sequences the tracker ahead of the pool and failure work so every
commit stays green, and records two facts the implementer needs up front:
the pool-construction path has zero test coverage today, and the commit
gate runs the full suite plus a complexity ceiling.
Records what the two Codex review rounds found, which findings held up
under verification, and how each was resolved -- including the one that
changed docs rather than code. Also lists the evidence behind the
completion claim: suite counts, coverage, the 19-minute real-wait Redis
run, and the import contract.
The breaker conflates "this source is unhealthy" with "kill this call
now". Limiter rejections already choose between wait and fail_fast;
breaker rejections had no such choice, so a single-source scope loses
its whole retry budget the moment the gate opens.
Design adds {SCOPE}__CIRCUIT_OPEN (default fail_fast, so existing
deployments keep their control flow) and pins retry_after_s to "time
until a *certain* retry moment" across all six gate exits. The latter
also fixes a separate bug the issue missed: a half-open rejection fed
the probe lease (up to 2x timeout) into the source cooldown memo, whose
set_until only moves forward -- so a recovered source stayed blacklisted
in-process long after the gate closed. That one bites multi-source
deployments too, it is just hidden when other sources absorb the load.
Human-approved 2026-08-19; both documents revised after Codex review.
Twelve tasks across the two plans, each with the files it touches, the
evidence it has to produce, and the command that proves it. #13 goes
first: both branches edit config.py and client.py, and #12's
partitioning template leans on the schema SQL helper and the untargeted
conflict clause that #13 introduces.
Writing the cap plan surfaced a trap worth its own guard. digest_messages
appends the very same dict when a message's content is not a list, so
the telemetry copy, the caller's messages and the cache key all share
one object -- capping in place would poison the caller's request and the
cache key at once, silently. Two red-line tests now pin that down, and
the plan asks for an in-place version to be written and run first, to
prove the tests actually catch it.
Both open issues ask the same question from opposite sides: how much
power the library holds over a downstream database. #13 wants the
structural writes back, #12 wants the data retention back. The two
designs share one boundary -- the library does SELECT and INSERT plus
an optional CREATE, and everything that alters structure or deletes
rows belongs to the downstream, with the library obliged to print the
exact SQL they need to run.
Two findings shape #13 beyond what the issue argues. The precedents it
cites (Hangfire's lock queue, Prefect's multi-instance race, Alembic's
audit trail) all live on a shared production Postgres, while the SQLite
side is a local file with no DBA and no migration tool, so the defaults
split by backend rather than uniformly. And turning ALTER off only
works together with trimming the INSERT to the columns that exist:
without it a stale table drops every row instead of two columns, which
breaks the telemetry rule harder than the automatic ALTER ever did.
For #12 only the body cap touches library code; retention and access
control land in the README, because the sdist carries src and the
README alone -- a template that lives in the wiki is one a downstream
pip install cannot reach.
Eight tasks against the approved design, ordered so the port and both
telemetry backends land before the three call paths that feed them.
Writing the plan turned up a third telemetry path the design missed:
OcrClient emits through the same helper and builds its ChatRequest on
the spot, just as embedding does. OCR rows share the table with chat
rows, so leaving them out would put a hole in a multi-tenant caller's
audit trail, and the same irreversibility argument applies. Listed as
Task 6 and flagged as beyond the approved scope -- it may be dropped,
but only by stating the limitation in the CHANGELOG, not silently.
The integration task pins the issue's own argument as a test: build a
22-column table, open it with the current recorder, and assert the old
rows read back as the empty string rather than NULL -- NULL under an
RLS policy is invisible to everyone, not merely unassigned.
Codex review: the code blocks reference httpx and PolyGatewayError, but
neither module imports them today. A zero-context implementer copying
them verbatim would stall on F821.
Registration pages carry the chosen approach, why the split is by "which
budget the time consumes", the five rejected alternatives with reasons,
and the 3.6 correction found during independent verification.
Five tasks, with the ARCHITECTURE section 6.1 revision first so the code
never contradicts the single source of truth, and the reparenting kept
atomic because scope is a required keyword argument and any split would
leave an unrunnable tree.
The Codex review caught that the planned test evidence pointed at the
wrong stubs: the ones at test_backpressure.py:176-186 cover accounting-side
degradation, not the three gate paths that actually leak to callers, and
try_acquire and try_enter have no stub at all.
Pins the ARCHITECTURE section 6.1 revision to land before or with the
implementation, since the new scope reason contradicts the current single
source of truth. Documents why SourceNotConfiguredError may sit outside
the four-way classification: that rule governs transport-translated call
failures, and the GatewayUnavailableError family already lives outside it.
Also collapses the ten per-field response ternaries in emit_attempt into
an _AttemptUsage view. They all expressed the same decision and pushed the
method to cyclomatic complexity C, which blocked the commit gate.
Ten tasks in a fixed order: land reasoning_tokens first so it can serve
as the acceptance instrument for the thinking-switch fix, then reshape
the provider profile, add the model-level capability table, wire the
assembly guard, fold enable_thinking into the cache fingerprint, and
verify the whole thing against the live API.
Incorporates a read-only Codex review: resolve_thinking now takes the
model name so its errors can name it, and the warning assertion uses a
loguru sink because caplog cannot see loguru output.
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.
The ordering is the load-bearing part. All three changes interlock and
every wrong interleaving fails silently: flipping the usage fallback to
(0, 0) before the settlement points read the derived value refunds the
whole pre-deduction on success, and flipping the embedding transport
before _merge goes three-state mislabels unavailable batches as
measured. So the plan adds the capability first, moves all five call
sites onto it while it is still equivalent, only then lets the third
state take effect, and unbinds the constraint last.
Registers both wiki entries and links the plan to its design.
Records the approved option, the four rejected alternatives with their
reasons, the intentionally dropped CHS migration item, and the two
defects the independent review caught. Links the entry to m1-core-design
as a refinement, since that milestone is where est_tokens froze with
both jobs attached.
The independent verifier found 15 more checks still living only in from_env:
six enum domains, seven conditional-required pairs and two scalar ranges.
More severe than round one because client.py has five asserts that claim
config already validated the redis_url and telemetry paths, which is false on
the from_settings path.
Also records a normalisation gap the verifier missed: _load_pg_dsn strips the
SQLAlchemy +asyncpg suffix, so a hand-built DSN reaches asyncpg unstripped.
Guards for the three cross-field invariants (source timeout vs lease TTL,
stall window vs max TTFT, probe TTL vs slowest timeout) only ran inside
from_env, so the from_settings path could build a GatewaySettings that
violates the class's own documented invariants. Design moves all of them
plus a non-empty sources check into __post_init__ as _validate_* methods,
matching the existing frozen dataclasses in types.py.
Covers two defects left by PR#1: probe_ttl_s was never moved, and an empty
sources tuple leaked a bare 'max() arg is an empty sequence'.
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