-
genomic-intelligence: reconcile the skill against the live /v1 contract (1.1) (#228)
frostbyte_neo 发布于
2026-09-11 17:12:06 +00:00 - Correct the genomic-intelligence expression contract (tss_index, 9,198-500,000 bp)
Genomic Intelligence shipped a new expression contract to production on
2026-08-18 (gpu_service 2026.08.18.1). Expression now has its own
published OpenAPI operation (POST /v1/tasks/expression/predict, schema
ExpressionPredictRequest) instead of the generic templated one, so the
skill's description of it was wrong in four ways:- the sequence bound is 9,198-500,000 bp, not "exactly 9,198 bp";
- a new required field tss_index (0-based, into the whitespace-stripped
sequence, 4599 <= tss_index <= len-4599) selects the window the server
slices, and is mandatory unless the sequence is exactly 9,198 bp; - options is now a closed object whose only, required, key is
description; - violations are 422 validation_failed, never a padded/truncated 200.
Also documents the response's new tss_index / scored_window /
submitted_sequence_length provenance fields, and the gotcha that an
in-range but wrong tss_index returns a confident 200 for the wrong
window. The five other tasks and the composite workflow are unchanged.Co-Authored-By: Claude Opus 5 noreply@anthropic.com
- Correct the genomic-intelligence /v1 contract (per-task floors, typed options)
Correct the skill against the settled /v1 contract (DEV 2026.08.19.4):
- Replace "all six tasks share one shape / one PredictRequest". Six literal
predict operations are published, one per task, each with its own request
schema, minLength and closed options object. The URLs are unchanged. - Replace the "1-500,000 bp" length bound with the real per-task floors:
promoter 300, splice 100, enhancer 50, chromatin 200, annotation 1,000,
expression 9,198, composite 1,000; 500,000 cap throughout. - Add the floor-is-not-regime rule: a request above the floor but below the
model's bio_spec.context_window_bp is accepted and scored against a padded
window. Enhancer's 50 bp bound vs its 249 bp context window is the sharp case. - Correct "413 sequence too long": over-length is 422 validation_failed. 413
means the 16 MiB raw-body cap or the composite's sync_too_large. - Document typed, closed per-task options (an unknown key is a hard 422
extra_forbidden), the closed 21-value error code enum, the defensive-details
rule, the Prefer header on all six operations, and the published composite
REST workflow. - Note that tss_index errors report at loc ["body"], never body.tss_index, so
clients must match on error.code. - Document the new bio_spec fields (request_max_bp, context_window_bp,
trained_window_bp), that max_seq_length_bp is legacy/ambiguous, that there is
no strand_sensitive flag, and that GET /v1/tasks/{task}/models returns a flat
object rather than the {data, meta} envelope. - Add an unknown task -> 404 not_found note and a schema-version caveat, since
production may still serve 2026.08.18.1 until this build is promoted.
Verified against the live DEV schema (info.version 2026.08.19.4 (a5b1f88),
11 operations, no PredictRequest component).- Name the field the expression window actually comes from
Expression reports
context_window_bp: null; 9,198 bp is
trained_window_bp. The SKILL.md and references/tasks.md tables listed
9,198 under a "Model context window" column, conflating the two.- docs(genomic-intelligence): mode is a per-request choice, not a task property
Every predict operation declares the Prefer header and both 200 and 202.
Verified live against 2026.08.19.4: promoter submitted with
Prefer: respond-async returns 202 and polls to a normal payload; annotation
with no Prefer header returns 200 synchronously.Relabels the task table's "Mode" column "Recommended mode" and states the rule
under the table, so the latency guidance stays without asserting a constraint
the API never had.Co-Authored-By: Claude Opus 5 (1M context) noreply@anthropic.com
Signed-off-by: Alexander Boldakov alexboldakov@gmail.com- docs(genomic-intelligence): correct the request_id availability claim
error.request_id is not always populated — 413 sync_too_large omits it from
the body. The X-Request-Id header is set on every response, so read the
header as a fallback.Co-Authored-By: Claude Opus 5 (1M context) noreply@anthropic.com
Signed-off-by: Alexander Boldakov alexboldakov@gmail.com- docs(genomic-intelligence): reconcile against the live contract, bump to 1.1
Folds in corrections that existed only in our downstream staging copy, and
re-verifies every claim against the live 2026.08.19.4 schema and API.- Splice: state that the wrong strand fails silently. It does not return
zeros or an empty result -- measured live, a reverse-complemented sequence
returns plausible sites at different positions, often at high confidence,
so neither score nor count reveals the mistake. Any "empty means wrong
strand" heuristic is unsafe. - Delivery mode: no usable templated /v1/tasks/{task}/predict fallback (any
other task segment is 404, never 422); Prefer is declared on all six
predict operations plus the composite; async is JSON-only. - max_seq_length_bp: legacy, ambiguous and being withdrawn. It reads 9,198
for g0-expression -- the trained window, not a request cap -- so gating on
it wrongly rejects the 9,198-500,000 bp range expression accepts. - Errors: treat error.details as display-only and accept either declared
shape; prefer the X-Request-Id header for correlation, since the body
field is absent on some error paths. - Drop a stale schema-version note claiming production might still serve
2026.08.18.1, and note that a generated client must be regenerated. - Document the by-hand equivalent of the composite workflow.
Validated: skills-ref validate passes; repo spec rules clean; tests/_meta
10 passed / 1213 subtests. SKILL.md 362 lines, under the 500 limit.Signed-off-by: Alexander Boldakov alexboldakov@gmail.com
- docs(genomic-intelligence): refresh contract prose against PROD 2026.08.19.5
Today's GI ship landed after this text was written, so several claims went
stale within hours:- 422 details is the declared {"errors": [...]} object, not a bare array.
Defensive handling of either shape is kept; only the prose was wrong. - error.request_id is populated on every error path, including both 413
variants; success envelopes carry meta.request_id. - bio_spec.max_seq_length_bp is retired and absent from the live response;
request_max_bp is the cap. - Version notes hedging that PROD may still serve an older build are moot.
- Sync/async is a per-request delivery choice, never a task property; the
composite's 50,000 bp sync limit is the only forced case.
Also renames the client's synthesized non_json error code to http_error,
which is in the published 21-value enum; client-origin errors remain
distinguishable by carrying no request_id.Co-Authored-By: Claude Opus 5 (1M context) noreply@anthropic.com
Signed-off-by: Alexander Boldakov alexboldakov@gmail.com- docs(genomic-intelligence): drop API-codebase references, normalize comments
Audited against AUTHORING.md. Removes every pointer at the private service
codebase (retiredgpu_service/*paths, internal constants and symbols) and
the internal release stamps that went with them, restating each as what the
Genomic Intelligence API serves, with the published OpenAPI document as the
authority. Also normalizes the research-use wording, removes pinned model IDs
and prediction values from prose, and makes comment voice consistent.No contract facts changed; every bound, field and status code re-verified
against the live schema.Co-Authored-By: Claude Opus 5 (1M context) noreply@anthropic.com
- docs(genomic-intelligence): stamp the verified contract version, mark loc tuples illustrative
Addresses: https://github.com/K-Dense-AI/scientific-agent-skills/pull/228#pullrequestreview-4976574250
The footer previously named an internal service build (2026.08.19.4), which a
reader cannot resolve from the published contract. The last push removed it
entirely, which was worse: the stamp is the only handle a reader has on which
claims to re-verify, and nothing in that repo's CI can check our numbers. It is
back, as the OpenAPI info.version this file was verified against.The loc tuples now say they are illustrative of the error shape and not part of
the contract, rather than sitting two lines from the instruction not to branch
on them.Co-Authored-By: Claude Opus 5 (1M context) noreply@anthropic.com
- genomic-intelligence: the submitted length is meta.sequence_length
data.input.sequence_length was removed from the API at contract revision 13;
the docs described it as the scored 9,198 bp.Co-Authored-By: Claude Fable 5.1 noreply@anthropic.com
Claude-Session: https://claude.ai/code/session_01LA7HntiXoc7ZpQz8boGk6b
Signed-off-by: Alexander Boldakov alexboldakov@gmail.com
Co-authored-by: Claude Opus 5 noreply@anthropic.com下载附件