Tracking: Agent development support roadmap

[davidruzicka]

Summary

Track the GitHub-native planning structure for agent development support work: project board, roadmap document, and the initial issue set.

Links

• Project: https://github.com/users/davidruzicka/projects/2
• Roadmap doc: docs/roadmaps/agent-development-support.md
• Review/fix loop tracking issue: Tracking: Close PR review/fix loop #184

Tracking issues

• Tracking: Close PR review/fix loop #184 Tracking: Close PR review/fix loop

Current implementation issues

• Add PR review comment resolution loop #178 Add PR review comment resolution loop
• Track review comment resolution state per head SHA #179 Track review comment resolution state per head SHA
• Define merge blocking policy for unresolved review threads #180 Define merge blocking policy for unresolved review threads
• Extend planner output for review-follow-up fix/test plans #181 Extend planner output for review-follow-up fix/test plans
• Add observability for agent pipeline stages #182 Add observability for agent pipeline stages
• Define human escalation rules for agent stages #183 Define human escalation rules for agent stages

Suggested execution order

Phase 1 - close the review loop

1. Add PR review comment resolution loop #178
2. Track review comment resolution state per head SHA #179
3. Define merge blocking policy for unresolved review threads #180
4. Extend planner output for review-follow-up fix/test plans #181

Phase 2 - operational hardening

5. Add observability for agent pipeline stages #182
6. Define human escalation rules for agent stages #183

Usage

Use the project for live prioritization and status updates, and use the roadmap markdown for dependency notes and implementation context that do not fit well in project fields.

Agent note: this issue body was drafted by an agent.

[github-actions]

🤖 Agent note (issuer)

Autonomy gate decision: safe
Reasons:

• issue includes explicit acceptance or validation structure
• issue stays within bounded autonomous risk heuristics

[github-actions]

🤖 Agent plan (planner)

Planner decision: planned
Reasons:

• issue body provides enough structure for a bounded implementation plan
• issue remains inside the low-risk autonomous planning lane

Implementation plan

1. Confirm the narrow goal from issue Tracking: Agent development support roadmap #185 and keep changes bounded to the directly impacted module(s).
2. Add or update targeted success-path and failure-path tests before or alongside production changes.
3. Implement the smallest modular change that satisfies the issue without broad refactors.
4. Update user-facing docs or changelog entries if behavior becomes visible externally.

Validation

• Run targeted unit tests for the touched area.
• Run npm run typecheck.
• Re-run the focused tests after the final refactor pass.

[github-actions]

🤖 Agent implementation note (implementor)

Implementation lease acquired for issue #185.

[github-actions]

🤖 Agent implementation note (implementor)

Implementation result: failed
Summary: Implementor command failed: Command failed: bash -lc node dist/scripts/run-implementor-codex.js
node:internal/errors:984
const err = new Error(message);
^

Error: Command failed: codex exec --full-auto You are the Codex implementor backend for the mcp4openapi autonomous issue pipeline.
Work only inside the current git repository/worktree and keep the change narrowly scoped to the issue below.
Use senior-level code quality: modular design, clean code, explicit boundaries, data-oriented logic where reasonable, no duplication, and safe defaults.
Use strict TDD: add or update tests first, confirm the relevant tests fail, implement the minimal change, then rerun targeted tests and typecheck.
Run targeted tests and typecheck before creating the PR.
Use English for code comments, commit messages, PR title/body, and notes.
Create a dedicated branch if needed, commit with a Conventional Commits message, push it, and open a PR linked to the issue.
The PR description must clearly disclose automation with this exact sentence: "This PR was created by an automated agent."
The PR body should also mention the agent role, source issue number, workflow run ID, testing performed, and any assumptions or limits.
If you cannot complete the task safely, do not open a PR. Return outcome "blocked" for policy/scope blockers or "failed" for implementation/tooling failures.

Repository: davidruzicka/mcp4openapi
Agent ID: implementor
Workflow run ID: github-actions-23287699335
Timestamp: 2026-03-19T09:10:51.117Z
Issue #185: Tracking: Agent development support roadmap
Issue URL: #185
Issue labels: agent:safe, agent-support, tracking, agent:planned

Issue body:

Summary

Track the GitHub-native planning structure for agent development support work: project board, roadmap document, and the initial issue set.

Links

• Project: https://github.com/users/davidruzicka/projects/2
• Roadmap doc: docs/roadmaps/agent-development-support.md
• Review/fix loop tracking issue: Tracking: Close PR review/fix loop #184

Tracking issues

• Tracking: Close PR review/fix loop #184 Tracking: Close PR review/fix loop

Current implementation issues

• Add PR review comment resolution loop #178 Add PR review comment resolution loop
• Track review comment resolution state per head SHA #179 Track review comment resolution state per head SHA
• Define merge blocking policy for unresolved review threads #180 Define merge blocking policy for unresolved review threads
• Extend planner output for review-follow-up fix/test plans #181 Extend planner output for review-follow-up fix/test plans
• Add observability for agent pipeline stages #182 Add observability for agent pipeline stages
• Define human escalation rules for agent stages #183 Define human escalation rules for agent stages

Suggested execution order

Phase 1 - close the review loop

1. Add PR review comment resolution loop #178
2. Track review comment resolution state per head SHA #179
3. Define merge blocking policy for unresolved review threads #180
4. Extend planner output for review-follow-up fix/test plans #181

Phase 2 - operational hardening

5. Add observability for agent pipeline stages #182
6. Define human escalation rules for agent stages #183

Usage

Use the project for live prioritization and status updates, and use the roadmap markdown for dependency notes and implementation context that do not fit well in project fields.

Agent note: this issue body was drafted by an agent.

Required final output:

• Write exactly one JSON object to /tmp/mcp4openapi-implementor-codex-cpoeoF/result.json
• The JSON must match this schema:
  {
  "outcome": "pr-created" | "failed" | "blocked",
  "summary": "short human-readable summary",
  "pullRequest": { "number": 123, "url": "https://github.com/owner/repo/pull/123" }
  }
• Include pullRequest only when outcome is "pr-created".
• Do not wrap the JSON in markdown.
• Ensure the file contents are valid JSON before exiting.
  OpenAI Codex v0.115.0 (research preview)

---

workdir: /home/runner/work/mcp4openapi/mcp4openapi
model: gpt-5.3-codex
provider: openai
approval: never
sandbox: workspace-write [workdir, /tmp, $TMPDIR, /home/runner/.codex/memories]
reasoning effort: none
reasoning summaries: none
session id: 019d055c-b328-7fd3-bcbb-c87a7b6ccbaf

user
You are the Codex implementor backend for the mcp4openapi autonomous issue pipeline.
Work only inside the current git repository/worktree and keep the change narrowly scoped to the issue below.
Use senior-level code quality: modular design, clean code, explicit boundaries, data-oriented logic where reasonable, no duplication, and safe defaults.
Use strict TDD: add or update tests first, confirm the relevant tests fail, implement the minimal change, then rerun targeted tests and typecheck.
Run targeted tests and typecheck before creating the PR.
Use English for code comments, commit messages, PR title/body, and notes.
Create a dedicated branch if needed, commit with a Conventional Commits message, push it, and open a PR linked to the issue.
The PR description must clearly disclose automation with this exact sentence: "This PR was created by an automated agent."
The PR body should also mention the agent role, source issue number, workflow run ID, testing performed, and any assumptions or limits.
If you cannot complete the task safely, do not open a PR. Return outcome "blocked" for policy/scope blockers or "failed" for implementation/tooling failures.

Repository: davidruzicka/mcp4openapi
Agent ID: implementor
Workflow run ID: github-actions-23287699335
Timestamp: 2026-03-19T09:10:51.117Z
Issue #185: Tracking: Agent development support roadmap
Issue URL: #185
Issue labels: agent:safe, agent-support, tracking, agent:planned

Issue body:

Summary

Track the GitHub-native planning structure for agent development support work: project board, roadmap document, and the initial issue set.

Links

• Project: https://github.com/users/davidruzicka/projects/2
• Roadmap doc: docs/roadmaps/agent-development-support.md
• Review/fix loop tracking issue: Tracking: Close PR review/fix loop #184

Tracking issues

• Tracking: Close PR review/fix loop #184 Tracking: Close PR review/fix loop

Current implementation issues

• Add PR review comment resolution loop #178 Add PR review comment resolution loop
• Track review comment resolution state per head SHA #179 Track review comment resolution state per head SHA
• Define merge blocking policy for unresolved review threads #180 Define merge blocking policy for unresolved review threads
• Extend planner output for review-follow-up fix/test plans #181 Extend planner output for review-follow-up fix/test plans
• Add observability for agent pipeline stages #182 Add observability for agent pipeline stages
• Define human escalation rules for agent stages #183 Define human escalation rules for agent stages

Suggested execution order

Phase 1 - close the review loop

1. Add PR review comment resolution loop #178
2. Track review comment resolution state per head SHA #179
3. Define merge blocking policy for unresolved review threads #180
4. Extend planner output for review-follow-up fix/test plans #181

Phase 2 - operational hardening

5. Add observability for agent pipeline stages #182
6. Define human escalation rules for agent stages #183

Usage

Use the project for live prioritization and status updates, and use the roadmap markdown for dependency notes and implementation context that do not fit well in project fields.

Agent note: this issue body was drafted by an agent.

Required final output:

• Write exactly one JSON object to /tmp/mcp4openapi-implementor-codex-cpoeoF/result.json

• The JSON must match this schema:
  {
  "outcome": "pr-created" | "failed" | "blocked",
  "summary": "short human-readable summary",
  "pullRequest": { "number": 123, "url": "https://github.com/owner/repo/pull/123" }
  }

• Include pullRequest only when outcome is "pr-created".

• Do not wrap the JSON in markdown.

• Ensure the file contents are valid JSON before exiting.
  mcp startup: no servers
  Reconnecting... 1/5 (unexpected status 401 Unauthorized: Missing bearer or basic authentication in header, url: https://api.openai.com/v1/responses, cf-ray: 9deb58bf9ca869f9-DFW, request id: req_5a0ae07f4e56440f82e448462ac9dc5e)
  Reconnecting... 2/5 (unexpected status 401 Unauthorized: Missing bearer or basic authentication in header, url: https://api.openai.com/v1/responses, cf-ray: 9deb58c199494641-DFW, request id: req_a55c4228bd514d7caea8886f98095179)
  Reconnecting... 3/5 (unexpected status 401 Unauthorized: Missing bearer or basic authentication in header, url: https://api.openai.com/v1/responses, cf-ray: 9deb58c5080d8fc2-ORD, request id: req_8bb0f02e98314fd19bca7cc19bd1c1ab)
  Reconnecting... 4/5 (unexpected status 401 Unauthorized: Missing bearer or basic authentication in header, url: https://api.openai.com/v1/responses, cf-ray: 9deb58cafc16110a-ORD, request id: req_27c6283617e5448bae67f2b9c8cca242)
  Reconnecting... 5/5 (unexpected status 401 Unauthorized: Missing bearer or basic authentication in header, url: https://api.openai.com/v1/responses, cf-ray: 9deb58d56815f606-ORD, request id: req_d6f42c85782e430fa0615d710d86f7b6)
  ERROR: unexpected status 401 Unauthorized: Missing bearer or basic authentication in header, url: https://api.openai.com/v1/responses, cf-ray: 9deb58e8fdc610ea-ORD, request id: req_0c7c02a5dcf74e4897837f170cdd4a35

  at genericNodeError (node:internal/errors:984:15)
  at wrappedFn (node:internal/errors:538:14)
  at ChildProcess.exithandler (node:child_process:422:12)
  at ChildProcess.emit (node:events:524:28)
  at maybeClose (node:internal/child_process:1104:16)
  at ChildProcess._handle.onexit (node:internal/child_process:304:5) {
  code: 1,
  killed: false,
  signal: null,
  cmd: 'codex exec --full-auto You are the Codex implementor backend for the mcp4openapi autonomous issue pipeline.\n' +
  'Work only inside the current git repository/worktree and keep the change narrowly scoped to the issue below.\n' +
  'Use senior-level code quality: modular design, clean code, explicit boundaries, data-oriented logic where reasonable, no duplication, and safe defaults.\n' +
  'Use strict TDD: add or update tests first, confirm the relevant tests fail, implement the minimal change, then rerun targeted tests and typecheck.\n' +
  'Run targeted tests and typecheck before creating the PR.\n' +
  'Use English for code comments, commit messages, PR title/body, and notes.\n' +
  'Create a dedicated branch if needed, commit with a Conventional Commits message, push it, and open a PR linked to the issue.\n' +
  'The PR description must clearly disclose automation with this exact sentence: "This PR was created by an automated agent."\n' +
  'The PR body should also mention the agent role, source issue number, workflow run ID, testing performed, and any assumptions or limits.\n' +
  'If you cannot complete the task safely, do not open a PR. Return outcome "blocked" for policy/scope blockers or "failed" for implementation/tooling failures.\n' +
  '\n' +
  'Repository: davidruzicka/mcp4openapi\n' +
  'Agent ID: implementor\n' +
  'Workflow run ID: github-actions-23287699335\n' +
  'Timestamp: 2026-03-19T09:10:51.117Z\n' +
  'Issue Tracking: Agent development support roadmap #185: Tracking: Agent development support roadmap\n' +
  'Issue URL: https://github.com/davidruzicka/mcp4openapi/issues/185\n' +
  'Issue labels: agent:safe, agent-support, tracking, agent:planned\n' +
  '\n' +
  'Issue body:\n' +
  '## Summary\n' +
  'Track the GitHub-native planning structure for agent development support work: project board, roadmap document, and the initial issue set.\n' +
  '\n' +
  '## Links\n' +
  '- Project: https://github.com/users/davidruzicka/projects/2\n' +
  '- Roadmap doc: docs/roadmaps/agent-development-support.md\n' +
  '- Review/fix loop tracking issue: Tracking: Close PR review/fix loop #184\n' +
  '\n' +
  '## Tracking issues\n' +
  '- [ ] Tracking: Close PR review/fix loop #184 Tracking: Close PR review/fix loop\n' +
  '\n' +
  '## Current implementation issues\n' +
  '- [ ] Add PR review comment resolution loop #178 Add PR review comment resolution loop\n' +
  '- [ ] Track review comment resolution state per head SHA #179 Track review comment resolution state per head SHA\n' +
  '- [ ] Define merge blocking policy for unresolved review threads #180 Define merge blocking policy for unresolved review threads\n' +
  '- [ ] Extend planner output for review-follow-up fix/test plans #181 Extend planner output for review-follow-up fix/test plans\n' +
  '- [ ] Add observability for agent pipeline stages #182 Add observability for agent pipeline stages\n' +
  '- [ ] Define human escalation rules for agent stages #183 Define human escalation rules for agent stages\n' +
  '\n' +
  '## Suggested execution order\n' +
  '### Phase 1 - close the review loop\n' +
  '1. Add PR review comment resolution loop #178\n' +
  '2. Track review comment resolution state per head SHA #179\n' +
  '3. Define merge blocking policy for unresolved review threads #180\n' +
  '4. Extend planner output for review-follow-up fix/test plans #181\n' +
  '\n' +
  '### Phase 2 - operational hardening\n' +
  '5. Add observability for agent pipeline stages #182\n' +
  '6. Define human escalation rules for agent stages #183\n' +
  '\n' +
  '## Usage\n' +
  'Use the project for live prioritization and status updates, and use the roadmap markdown for dependency notes and implementation context that do not fit well in project fields.\n' +
  '\n' +
  'Agent note: this issue body was drafted by an agent.\n' +
  '\n' +
  '\n' +
  'Required final output:\n' +
  '- Write exactly one JSON object to /tmp/mcp4openapi-implementor-codex-cpoeoF/result.json\n' +
  '- The JSON must match this schema:\n' +
  '{\n' +
  ' "outcome": "pr-created" | "failed" | "blocked",\n' +
  ' "summary": "short human-readable summary",\n' +
  ' "pullRequest": { "number": 123, "url": "https://github.com/owner/repo/pull/123" }\n' +
  '}\n' +
  '- Include pullRequest only when outcome is "pr-created".\n' +
  '- Do not wrap the JSON in markdown.\n' +
  '- Ensure the file contents are valid JSON before exiting.',
  stdout: '',
  stderr: 'OpenAI Codex v0.115.0 (research preview)\n' +
  '--------\n' +
  'workdir: /home/runner/work/mcp4openapi/mcp4openapi\n' +
  'model: gpt-5.3-codex\n' +
  'provider: openai\n' +
  'approval: never\n' +
  'sandbox: workspace-write [workdir, /tmp, $TMPDIR, /home/runner/.codex/memories]\n' +
  'reasoning effort: none\n' +
  'reasoning summaries: none\n' +
  'session id: 019d055c-b328-7fd3-bcbb-c87a7b6ccbaf\n' +
  '--------\n' +
  'user\n' +
  'You are the Codex implementor backend for the mcp4openapi autonomous issue pipeline.\n' +
  'Work only inside the current git repository/worktree and keep the change narrowly scoped to the issue below.\n' +
  'Use senior-level code quality: modular design, clean code, explicit boundaries, data-oriented logic where reasonable, no duplication, and safe defaults.\n' +
  'Use strict TDD: add or update tests first, confirm the relevant tests fail, implement the minimal change, then rerun targeted tests and typecheck.\n' +
  'Run targeted tests and typecheck before creating the PR.\n' +
  'Use English for code comments, commit messages, PR title/body, and notes.\n' +
  'Create a dedicated branch if needed, commit with a Conventional Commits message, push it, and open a PR linked to the issue.\n' +
  'The PR description must clearly disclose automation with this exact sentence: "This PR was created by an automated agent."\n' +
  'The PR body should also mention the agent role, source issue number, workflow run ID, testing performed, and any assumptions or limits.\n' +
  'If you cannot complete the task safely, do not open a PR. Return outcome "blocked" for policy/scope blockers or "failed" for implementation/tooling failures.\n' +
  '\n' +
  'Repository: davidruzicka/mcp4openapi\n' +
  'Agent ID: implementor\n' +
  'Workflow run ID: github-actions-23287699335\n' +
  'Timestamp: 2026-03-19T09:10:51.117Z\n' +
  'Issue Tracking: Agent development support roadmap #185: Tracking: Agent development support roadmap\n' +
  'Issue URL: https://github.com/davidruzicka/mcp4openapi/issues/185\n' +
  'Issue labels: agent:safe, agent-support, tracking, agent:planned\n' +
  '\n' +
  'Issue body:\n' +
  '## Summary\n' +
  'Track the GitHub-native planning structure for agent development support work: project board, roadmap document, and the initial issue set.\n' +
  '\n' +
  '## Links\n' +
  '- Project: https://github.com/users/davidruzicka/projects/2\n' +
  '- Roadmap doc: docs/roadmaps/agent-development-support.md\n' +
  '- Review/fix loop tracking issue: Tracking: Close PR review/fix loop #184\n' +
  '\n' +
  '## Tracking issues\n' +
  '- [ ] Tracking: Close PR review/fix loop #184 Tracking: Close PR review/fix loop\n' +
  '\n' +
  '## Current implementation issues\n' +
  '- [ ] Add PR review comment resolution loop #178 Add PR review comment resolution loop\n' +
  '- [ ] Track review comment resolution state per head SHA #179 Track review comment resolution state per head SHA\n' +
  '- [ ] Define merge blocking policy for unresolved review threads #180 Define merge blocking policy for unresolved review threads\n' +
  '- [ ] Extend planner output for review-follow-up fix/test plans #181 Extend planner output for review-follow-up fix/test plans\n' +
  '- [ ] Add observability for agent pipeline stages #182 Add observability for agent pipeline stages\n' +
  '- [ ] Define human escalation rules for agent stages #183 Define human escalation rules for agent stages\n' +
  '\n' +
  '## Suggested execution order\n' +
  '### Phase 1 - close the review loop\n' +
  '1. Add PR review comment resolution loop #178\n' +
  '2. Track review comment resolution state per head SHA #179\n' +
  '3. Define merge blocking policy for unresolved review threads #180\n' +
  '4. Extend planner output for review-follow-up fix/test plans #181\n' +
  '\n' +
  '### Phase 2 - operational hardening\n' +
  '5. Add observability for agent pipeline stages #182\n' +
  '6. Define human escalation rules for agent stages #183\n' +
  '\n' +
  '## Usage\n' +
  'Use the project for live prioritization and status updates, and use the roadmap markdown for dependency notes and implementation context that do not fit well in project fields.\n' +
  '\n' +
  'Agent note: this issue body was drafted by an agent.\n' +
  '\n' +
  '\n' +
  'Required final output:\n' +
  '- Write exactly one JSON object to /tmp/mcp4openapi-implementor-codex-cpoeoF/result.json\n' +
  '- The JSON must match this schema:\n' +
  '{\n' +
  ' "outcome": "pr-created" | "failed" | "blocked",\n' +
  ' "summary": "short human-readable summary",\n' +
  ' "pullRequest": { "number": 123, "url": "https://github.com/owner/repo/pull/123" }\n' +
  '}\n' +
  '- Include pullRequest only when outcome is "pr-created".\n' +
  '- Do not wrap the JSON in markdown.\n' +
  '- Ensure the file contents are valid JSON before exiting.\n' +
  'mcp startup: no servers\n' +
  'Reconnecting... 1/5 (unexpected status 401 Unauthorized: Missing bearer or basic authentication in header, url: https://api.openai.com/v1/responses, cf-ray: 9deb58bf9ca869f9-DFW, request id: req_5a0ae07f4e56440f82e448462ac9dc5e)\n' +
  'Reconnecting... 2/5 (unexpected status 401 Unauthorized: Missing bearer or basic authentication in header, url: https://api.openai.com/v1/responses, cf-ray: 9deb58c199494641-DFW, request id: req_a55c4228bd514d7caea8886f98095179)\n' +
  'Reconnecting... 3/5 (unexpected status 401 Unauthorized: Missing bearer or basic authentication in header, url: https://api.openai.com/v1/responses, cf-ray: 9deb58c5080d8fc2-ORD, request id: req_8bb0f02e98314fd19bca7cc19bd1c1ab)\n' +
  'Reconnecting... 4/5 (unexpected status 401 Unauthorized: Missing bearer or basic authentication in header, url: https://api.openai.com/v1/responses, cf-ray: 9deb58cafc16110a-ORD, request id: req_27c6283617e5448bae67f2b9c8cca242)\n' +
  'Reconnecting... 5/5 (unexpected status 401 Unauthorized: Missing bearer or basic authentication in header, url: https://api.openai.com/v1/responses, cf-ray: 9deb58d56815f606-ORD, request id: req_d6f42c85782e430fa0615d710d86f7b6)\n' +
  'ERROR: unexpected status 401 Unauthorized: Missing bearer or basic authentication in header, url: https://api.openai.com/v1/responses, cf-ray: 9deb58e8fdc610ea-ORD, request id: req_0c7c02a5dcf74e4897837f170cdd4a35\n'
  }

Node.js v20.20.1

[davidruzicka]

Live refresh after merging PR #187: I cleaned up recursive proposal-intake duplicates by closing #186, #188, #189 as duplicates of #181 and closing #190 as a duplicate of #182. I also opened #191 to track the underlying automation bug so the roadmap/project queue stays canonical. Agent note: this comment was prepared by an agent.

[github-actions]

🤖 Agent note (proposal-intake)

Resolution: create-fresh
Reason: no relevant existing issue or pull request matches this proposal
Linked issue: #192 (#192)