Files

T

Build: Production / build (push) Failing after 12m39s

Details

fix(skills): pull upstream skill runtime resolution to stop event-loop starvation

The fork's listRuntimeSkillEntries rematerialized every skill's files from
the DB on every heartbeat run dispatch — fs.rm + fs.mkdir + per-file
readFile/writeFile, sequentially per skill. With 24 configured skills and
5 concurrent agents, this saturated the Node event loop badly enough that
executeRun continuations couldn't reach activeRunExecutions.add() within
the orphan-reaper's 5-min threshold, causing reaper to false-positive runs
as "process_lost".

Upstream's listRuntimeSkillEntries calls resolveRuntimeSkillSource, which
checks if the materialized directory already exists on disk and short-
circuits when it does. Fixes the symptom at the root.

Replaces these files with upstream/master content:
  - server/src/services/company-skills.ts
  - server/src/services/heartbeat.ts
  - server/src/services/workspace-runtime.ts
  - server/src/services/company-portability.ts
  - server/src/routes/company-skills.ts
  - server/src/routes/agents.ts
  - packages/adapter-utils/src/server-utils.ts

Pulls in supporting upstream files:
  - server/src/services/catalog-provenance.ts
  - server/src/services/skills-catalog.ts
  - server/src/services/github-fetch.ts
  - server/src/services/portable-path.ts
  - packages/skills-catalog/ (new package)
  - packages/db document_annotation_* schema + migration 0091
  - packages/shared document-annotation types/validators

Drops fork features (to be re-evaluated later):
  - Gitea/Forgejo git skill sources (server/src/services/git-source.ts deleted)
  - PAT support for private skill repos
  - Fork-specific secret-export portability extensions

Adds agentId: null to acquireRunLease test-probe call in routes/agents.ts
to satisfy the fork's environment-runtime agentId requirement (kept).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-29 09:26:51 -04:00

3.8 KiB

Raw Blame History

name, description, key, recommendedForRoles, tags

name

description

key

recommendedForRoles

QA Acceptance

Write acceptance criteria that a reviewer can run against the running app and decide pass or fail without asking the author. The criteria are the contract — automated tests cover correctness, QA covers feature-level behavior.

When to use

A feature change is heading to QA and needs a written validation plan.
A reviewer is asked to verify a PR that touches user-visible behavior.
An incident postmortem requires a regression check before reopen-prevention.
A release candidate needs a pre-cut smoke pass.

When not to use

The change is unit-test-only (utility refactor, internal naming). Acceptance criteria are unnecessary churn.
You are asked to write tests against API contracts. Use contract testing, not feature QA.

Acceptance criteria format

Each criterion is a single, independently-verifiable statement:

- **Given** <starting state>, **when** <action>, **then** <observable outcome>.

Example:

- **Given** a CSV export with 0 rows, **when** the user clicks Export, **then** the file downloads with only the header row and the UI shows "Exported 0 rows".

Avoid criteria that combine multiple whens or thens. Split them.

What every plan must cover

Golden path. The most common successful flow, end to end.
Empty and minimum states. Zero items, one item, missing optional inputs.
Boundary inputs. Max length strings, max numeric values, unicode, RTL text where applicable.
Error states. Network failure, permission denied, validation failures, conflict (409), not found (404).
Concurrency and ordering. Two users acting at once, race against background jobs, refresh during mutation.
Performance envelope. The largest realistic input the change must handle without UI hangs or timeouts.
Backward compatibility. Existing data, existing URLs, persisted user preferences continue to work.
Telemetry and audit. Events, logs, or activity entries the change is supposed to emit.

If a section is genuinely not applicable, write "N/A: " — do not silently omit.

Evidence

Each criterion needs evidence on the verification pass:

Screenshot or short clip for UI behavior.
Copied console / network output for API behavior.
Log snippet or activity row for telemetry.
Timing measurement for performance criteria.

"Looks good to me" without evidence is not a pass.

Quarantine and follow-up

A failing criterion blocks acceptance unless explicitly waived by the owner with a tracked follow-up issue.
"Known issue" without a linked follow-up is not a waiver.
If you add a new criterion mid-pass, restart the pass — partial coverage hides regressions.

Handoff back to the author

Return the validation plan with three sections:

Pass. Criteria that passed, with one-line evidence summaries.
Fail. Criteria that failed, with the exact reproduction.
Blocked. Criteria you could not run, with why.

The author owns turning failures into either fixes or accepted deferrals.

Anti-patterns

Acceptance phrased as test plan ("write a Cypress test for X"). Acceptance is what is true after the change ships; tests are how you check.
Criteria that depend on inspecting implementation details (selectors, query plans). Stay observable.
Long checklists with no priority. Mark must-pass criteria distinctly from nice-to-have.
Validation reports that say "passed" with no evidence. Reviewers cannot audit those.

3.8 KiB Raw Blame History