v0.2.1 - Project id canonicalization for reliable agent task submission

Summary

Patch release for the worker-first MCP architecture shipped in v0.2.0.

This release fixes project reference canonicalization so agents can reliably use
the projectId returned by codex_list_projects when calling preflight, chat,
workflow, and durable task submission tools.

Fixed

• Cached non-registry projects now return the same canonical path-derived
  projectId across codex_list_projects, codex_preflight_project_run,
  chat tools, workflows, and codex_submit_task.
• Stale cached project ids are retained as aliases, so older local cache records
  do not block agents after catalog refresh.
• Windows catalog regression tests no longer depend on temporary path
  canonicalization after cleanup.

Validation

• python -m pytest -q
• python -m compileall -q openclaw_codex_mcp codex_control_plane_mcp tests scripts
• git diff --check
• python .\scripts\mcp_live_smoke.py --scenario protocol --timeout-seconds 30
• python -m build
• python -m twine check dist/*
• clean virtualenv wheel install and console script smoke

v0.2.0 - Worker-first MCP architecture for long-running parallel Codex tasks

v0.2.0 - Worker-first MCP architecture for long-running parallel Codex tasks

This release is a major architecture update for Codex Control Plane MCP. It
focuses on reliability, stability, and predictable agent behavior when several
long-running Codex turns are running in parallel across different projects.

Highlights

• Added a central worker architecture with client, worker, observe, and
  inline execution modes.
• Added durable scheduling for long-running tasks with queue state, worker
  heartbeats, resource locks, per-thread locks, and concurrency limits.
• Made status/read endpoints passive and bounded by default so polling does not
  create new live app-server work.
• Added a self-describing MCP contract through codexMcpGuide,
  codex_get_agent_contract, tool annotations, startup flows, and guide hashes.
• Improved agent guidance, diagnostics, recovery loop guards, and structured
  error next steps so agents know whether to poll, wait, diagnose, repair, or
  stop.
• Strengthened terminal reconciliation, queue/slot/lock release, and worker
  command behavior for long-running and interrupted turns.
• Added consistent agent-safe redaction for public status, diagnostics, search,
  runtime, lifecycle, and worker command responses.
• Added external MCP client tooling for live testing without restarting Codex
  Desktop sessions.

Why it matters

OpenClaw, Hermes, and other MCP clients can now treat the server as a durable
control plane: submit work, poll status, follow agentGuidance, and avoid
duplicate retries while the central worker owns Codex app-server execution. The
new architecture is designed for multi-project workloads where several heavy
turns may run for minutes or hours.

Compatibility

The public API remains backward compatible. Existing tools are still available,
while new fields are additive. Agents should prefer codex_submit_task for new
work, codex_health_summary on startup, and codex_get_agent_contract or the
tools/list guide for discovery.

Validation

• python -m pytest -q
• python -m compileall -q openclaw_codex_mcp codex_control_plane_mcp tests scripts
• git diff --check
• python .\scripts\mcp_live_smoke.py --scenario protocol --timeout-seconds 30
• external MCP client baseline and diagnostics scenarios
• python -m build
• python -m twine check dist/*
• clean virtualenv wheel install and console script smoke

Codex Control Plane MCP v0.1.4

Release v0.1.4 adds agent guidance for status, diagnostics, preflight, and structured errors, plus persistent recovery loop guards for repair, restart, and interrupt actions.\n\nVerification:\n- CI green on Windows and Ubuntu for Python 3.11, 3.12, and 3.13\n- Local pytest: 144 passed\n- Local wheel/sdist build and twine check passed

Codex Control Plane MCP v0.1.3

Roadmap release for the completed durable control-plane work. This release adds the richer progress journal, runtime inventory, durable thread fork, structured final reports, thread lifecycle tools, workflow goal sync, code review workflows, image inputs, and redacted account, usage, and rate-limit status. It also restores the thin-wrapper comparison guide from the PR #9 contribution by nightcityblade.

Codex Control Plane MCP v0.1.2

Patch release for MCP Registry discovery.\n\n- Adds official MCP Registry metadata in server.json.\n- Adds README ownership proof for io.github.aresyn/codex-control-plane-mcp.\n- Aligns package, runtime server version, and app-server client info at 0.1.2.

Codex Control Plane MCP v0.1.1

Patch release for PyPI-first public onboarding. Adds a PyPI badge, publishes the updated README as the PyPI long description, and creates a fresh PyPI deployment from the current clean public snapshot.

Codex Control Plane MCP v0.1.0

First public release of Codex Control Plane MCP. Includes durable operation polling, Plan Mode workflows, hook-backed SQLite history, diagnostics, public packaging, and trusted publishing setup for PyPI.