fix(workflows): airouter-impl-ready prompt was producing empty task descriptions

${metadata.automation.test_files} and ${metadata.automation.spec_ids} are
absent from M39 work items (created from dashboard without these fields),
resulting in an empty, useless prompt:
  "Implement the failing test. Test files: . Spec IDs: ."

Switch to ${metadata.task_description} — a sibling metadata key (not under
automation, so write-protected path does not apply) — populated by patching
items with their body text. The _TriggerItemView in dispatch_service.py
correctly exposes item.metadata so this resolves at compile time.

All 16 scaffolded M39 items patched with metadata.task_description via CP API.
This commit is contained in:
Paul O'Reilly
2026-07-31 10:40:34 +12:00
parent d06a526256
commit fc27ffe170

View File

@@ -24,7 +24,18 @@ nodes:
AGENT_REPO_URL: "git@gitea.oreillyit.nz-ai-enablement:skynet/agent-runtimes-agents.git" AGENT_REPO_URL: "git@gitea.oreillyit.nz-ai-enablement:skynet/agent-runtimes-agents.git"
AGENT_BRANCH: "task/${item.uuid}" AGENT_BRANCH: "task/${item.uuid}"
labels: [airouter] labels: [airouter]
prompt: "Implement the failing test. Test files: ${metadata.automation.test_files}. Spec IDs: ${metadata.automation.spec_ids}." prompt: |
You are implementing source code for the following task.
## Task Description
${metadata.task_description}
## Instructions
1. Read the task description carefully — it specifies the file(s) to create/modify and the exact requirements.
2. Find the test file mentioned in the description and run it to see current state: `python -m pytest <test_file> -v --tb=short`
3. Implement the required source code until all tests pass.
4. Do NOT modify any test files — they are read-only.
5. Run the tests one final time to confirm they are green before finishing.
escalation: escalation:
fixture_broken: fix-test-fixture-sonnet fixture_broken: fix-test-fixture-sonnet
contract_ambiguous: review-spec-opus contract_ambiguous: review-spec-opus