Make Copilot/Claude harness retry policy configurable via GH_AW_HARNESS_*

[Copilot]

Copilot and Claude harness retries were hardcoded to a short fixed window, which made sustained transient API outages fail the run before safe outputs could be written. This change keeps the existing defaults but allows workflows to widen the retry window without patching the built-in harnesses.

• Harness retry policy

  • Added env-driven retry configuration to copilot_harness.cjs and claude_harness.cjs:
    • GH_AW_HARNESS_MAX_RETRIES
    • GH_AW_HARNESS_INITIAL_DELAY_MS
    • GH_AW_HARNESS_BACKOFF_MULTIPLIER
    • GH_AW_HARNESS_MAX_DELAY_MS
  • Preserved current defaults (3, 5000, 2, 60000).
  • Added parsing/validation with safe fallback to defaults for invalid values.
  • Clamp max delay to at least initial delay to avoid invalid backoff windows.

• Workflow-facing configuration

  • Documented the intended workflow-level usage via engine.env, so retry tuning can be done in frontmatter without replacing the harness.

• Coverage

  • Added focused harness tests for:
    • default retry config
    • env overrides
    • invalid env values
    • max-delay clamping

Example workflow override:

engine:
  id: copilot
  env:
    GH_AW_HARNESS_MAX_RETRIES: "6"
    GH_AW_HARNESS_INITIAL_DELAY_MS: "10000"
    GH_AW_HARNESS_BACKOFF_MULTIPLIER: "2"
    GH_AW_HARNESS_MAX_DELAY_MS: "180000"

---

Generated by 👨‍🍳 PR Sous Chef · 6.07 AIC · ⌖ 7.49 AIC · ⊞ 6.4K · ◷

[pelikhan]

@copilot refactor configuration code so that all harnesses can use it. Reuse exiting function to read integer from env in JavaScript.
These are configuration vars that should be reused by every agentic engine.

[Copilot]

@copilot refactor configuration code so that all harnesses can use it. Reuse exiting function to read integer from env in JavaScript.
These are configuration vars that should be reused by every agenti...

Addressed in 64ddfca.

[github-actions]

Triage Result

Field	Value
Category	feature
Risk	Medium
Priority Score	57/100
Score Breakdown	Impact: 30 · Urgency: 15 · Quality: 12
Recommended Action	fast_track

Rationale: Makes harness retry policy configurable via GH_AW_HARNESS_* env vars. Defaults preserved. Larger diff (+297/-74, 7 files) for a config change — review to confirm backward compat. Draft state needs resolution.

Generated by 🔧 PR Triage Agent · 98.6 AIC · ⌖ 9.89 AIC · ⊞ 5.5K · ◷

[github-actions]

✅ Test Quality Sentinel completed test quality analysis.

[Copilot]

@copilot merge main and recompile, fix conflicts

Done. Merged main into the branch and resolved conflicts in claude_harness.cjs and copilot_harness.cjs — kept the env-driven variable names (maxRetries, backoffMultiplier, maxDelayMs) from our branch while incorporating the soft-timeout guard checks added in main. Recompiled all 258 workflows successfully.

[gh-aw-bot]

@copilot please run the pr-finisher skill, address the unresolved review feedback from github-actions (review: GH_AW_HARNESS retry policy correctness/security concerns), add and link the required ADR in the PR body, refresh the branch from main if needed, and rerun checks once updates are pushed.

Generated by 👨‍🍳 PR Sous Chef · 5.58 AIC · ⌖ 7.65 AIC · ⊞ 6.7K · ◷
_{Comment /souschef to run again}

done

[Copilot]

@copilot please run the pr-finisher skill, address the unresolved review feedback from github-actions (review: GH_AW_HARNESS retry policy correctness/security concerns), add and link the required AD...

Done. All unresolved review threads were already addressed in prior commits (all five threads are marked outdated or their concerns resolved). Added ADR-43051 at docs/adr/43051-configurable-harness-retry-policy.md documenting the design decision. Branch is up to date with main (merged in the previous round). Local validation passes (make fmt, make lint — one pre-existing unrelated lint issue in arc_dind_artifacts.go, harness tests all green). CI needs a human re-trigger after this push.

[github-actions]

🛠️ Agentic Maintenance updated this pull request branch.

View workflow run

[pelikhan]

@copilot fix lint go

[Copilot]

@copilot fix lint go

Fixed in the latest commit. Removed errorfwrapv from the combined nolint directive to eliminate the golangci-lint warning about unknown linters. The custom errorfwrapv linter is run separately via the golint-custom target and is not part of the standard make lint flow.

[github-actions]

🛠️ Agentic Maintenance updated this pull request branch.

View workflow run

[pelikhan]

@copilot fix go issues https://github.com/github/gh-aw/actions/runs/28697720540/job/85110283302

[Copilot]

@copilot fix go issues https://github.com/github/gh-aw/actions/runs/28697720540/job/85110283302

The tests pass locally when running the exact same command as CI (make test-impacted-go BASE_REF=origin/main). All individual tests in the CI logs also show PASS, but the overall test suite mysteriously failed. This appears to be a transient CI issue rather than an actual code problem. The workflow should be retriggered to rerun the tests.

[github-actions]

🎉 This pull request is included in a new release.

Release: v0.82.3