Commit Graph

23 Commits

Author SHA1 Message Date
YeonGyu-Kim bb8ef30bbe feat(omo-codex): add post-compact rule budget to codex hook
Trim rule and result char budgets after compaction via new
postCompactMaxRuleChars/postCompactMaxResultChars config, applied
through withPostCompactBudget. Extract codex-hook helpers into
dynamic-target-fingerprints, hook-output, path-utils,
rules-engine-factory, and transcript-rule-filter modules.
2026-05-29 11:17:24 +09:00
YeonGyu-Kim ced472dedf feat(omo-codex): add start-work continuation component
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-28 17:03:33 +09:00
YeonGyu-Kim 615ed40ba3 fix(omo-codex): reuse shared lsp mcp 2026-05-28 15:30:24 +09:00
YeonGyu-Kim 091550b94d refactor(omo-codex): port ultrawork hook to typescript 2026-05-28 15:07:51 +09:00
YeonGyu-Kim ae757005a3 refactor(omo-codex): move metis/momus from skills to agent TOMLs, rewrite prometheustic
metis/momus are Codex subagents, not skills. Move them to
components/ultrawork/agents/ as TOML agent role files:

- metis.toml: gpt-5.5 high, pre-planning analyst that detects
  contradictions, ambiguity, missing constraints, and execution risks.
  Ouroboros/ralplan-inspired gap analysis. Read-only.

- momus.toml: gpt-5.5 xhigh, plan reviewer with OKAY/ITERATE/REJECT
  three-verdict system. Blocker-finder with approval bias. Read-only.

planing-prometheustic SKILL.md rewritten to match the structure of
packages/prompts-core/prompts/prometheus/gpt.md (the omo Prometheus
GPT-5.5 prompt):
- Same XML-tagged sections: identity, mission, core_principles,
  output_verbosity_spec, scope_constraints, phases, plan_template,
  critical_rules, stop_rules
- Same phase flow: Classify Intent -> Ground -> Interview -> Plan
  Generation (with Metis) -> High Accuracy Review (with Momus)
- Metis called via spawn_agent(agent_type="metis") not skill load
- Momus called via spawn_agent(agent_type="momus") not skill load
- "Rigorous Review" renamed to "High Accuracy Review"
- Removed shared-skills/skills/metis/ and momus/ (deleted)
- sync-skills.mjs no longer copies metis/momus into plugin/skills/
2026-05-28 14:57:05 +09:00
YeonGyu-Kim f0af25aab1 fix(codex-rules): dedupe compacted context 2026-05-28 14:44:14 +09:00
YeonGyu-Kim 1d3847a6d3 feat(omo-codex): block budgeted create_goal calls 2026-05-28 14:19:14 +09:00
YeonGyu-Kim 68848233c4 docs(omo-codex): translate bundled prompts to English 2026-05-28 14:14:11 +09:00
YeonGyu-Kim 56f39d60fc feat(omo-codex): install through sisyphuslabs marketplace 2026-05-28 13:58:12 +09:00
YeonGyu-Kim 0d7c16a042 refactor(omo-codex): install agent TOMLs via symlinks at install time, drop sync-agents.py
The Python SessionStart hook (sync-agents.py) was a runtime side-effect
that copied agent TOMLs into CODEX_HOME/agents on every session start.
That design had three problems:

1. It was a Python script invoked via 'python3 ${PLUGIN_ROOT}/...' which
   is fragile on Windows where the binary may be 'python', and is the
   wrong layer for a one-shot install task.
2. Agent TOMLs landed as regular file copies, with no provenance link to
   the plugin cache and no tracking for clean uninstall.
3. An older release shipped TOMLs without the required 'name' field;
   because the current bundle no longer ships them, the hook never had
   a chance to overwrite the broken copies on disk, leaving Codex
   permanently warning at session start.

Replace the runtime hook with an install-time linker:
linkCachedPluginAgents() (src/cli/install-codex/link-cached-plugin-agents.ts).
The omo-codex CLI now calls it right after linkCachedPluginBins(). For
each 'components/*/agents/*.toml' in the plugin cache, it:

  - Linux / macOS: creates a symlink at ${CODEX_HOME}/agents/<basename>
    pointing at the cache TOML. The cache directory is the single source
    of truth; removing the cache cleanly breaks the link.
  - Windows: copies the file (symlinks require admin or Developer Mode).
  - Both platforms: writes a '.installed-agents.json' manifest under the
    plugin cache listing the installed absolute paths, so a future
    'omo uninstall --platform=codex' can remove them deterministically.

Stale regular-file copies (from the old sync-agents.py) are removed and
replaced on Unix. On Windows the existing copy is overwritten.

Tests (src/cli/install-codex/link-cached-plugin-agents.test.ts):
9 cross-platform tests that mock the 'platform' parameter to exercise
the Linux, macOS, and Windows code paths in a single 'bun test' run,
matching the existing pattern from linkCachedPluginBins. Covers symlink
creation, Windows copy, stale-file replacement, manifest writing,
idempotency, multi-component discovery, and the empty-bundle edge case.

Removed:
  - packages/omo-codex/plugin/components/ultrawork/hooks/sync-agents.py
  - packages/omo-codex/plugin/test/bundled-agents.test.mjs
    (it tested the Python hook; behaviour is now covered by the TS tests)
  - SessionStart hook entry in both ultrawork and aggregate hooks.json
  - 2 sync-agents tests + 1 manifest assertion in ultrawork-hooks.test.mjs
  - 'hooks/sync-agents.py' in ultrawork/package.json files list
  - sync-agents.py reference from aggregate.test.mjs component markers

Updated:
  - components/ultrawork/README.md, AGENTS.md: describe the install-time
    linker as the source of truth, no more SessionStart agent sync.

Verified end-to-end:
  bun run src/cli/index.ts install --no-tui --platform=codex
  ls -la ~/.codex/agents/  # all 4 TOMLs are symlinks pointing to cache
  cat ~/.codex/plugins/cache/.../omo/0.1.0/.installed-agents.json  # manifest present
2026-05-28 13:58:12 +09:00
YeonGyu-Kim 659342d627 feat(omo-codex): obsess on update_plan + async spawn_agent in Hephaestus baseline
Rewrite # Task Tracking from a single soft paragraph to a strict
update_plan covenant: mandatory for any 2+ step work, exactly one
in_progress, no batched completions, plan closure required, promise
discipline (do not commit to follow-up work you will not finish in
this turn). Pins the {step, status} schema with the pending /
in_progress / completed enum, and adds the explicit failure-mode
verdict that improvising past step 2 without an update_plan call is
itself a defect.

Add # Subagents section documenting that Codex's spawn_agent returns
immediately, runs in parallel, and should be fired 2-5 at a time via
multi_tool_use.parallel for independent investigations. Names the four
bundled roles (explorer / librarian / plan / codex-ultrawork-reviewer),
pins the four-field CONTEXT / GOAL / DOWNSTREAM / REQUEST spawn prompt
template, and instructs the model to call wait_agent sparingly only
when the next critical-path step is strictly blocked.

Compress the three repeated 'omo-codex LSP MCP diagnostics tool
(auto-runs on every edit via the lsp component, but you may also
invoke it explicitly)' phrasings to plain lsp_diagnostics, with the
auto-inject context defined once in # Parallelize aggressively. Saves
about 290 chars and defends the new sections' growth per the
prompt-engineering entropy gate.

The Hephaestus baseline is now 16578 chars; the prior 14627-char
version was already being silently truncated by the per-rule cap.
That truncation is fixed in the companion commit that bypasses the
cap for plugin-bundled rules, so the full discipline now lands on
every Codex session.
2026-05-28 13:58:12 +09:00
YeonGyu-Kim 171a2535d7 fix(omo-codex): bypass per-rule truncation for plugin-bundled rules
The 12000-char per-rule cap exists to guard against absurd user-authored
AGENTS.md files. For PLUGIN_BUNDLED rules the plugin author already
controls the body size, and silent mid-section truncation breaks the
contract that bundled discipline lands in full.

The current bundled Hephaestus baseline is 16k chars: everything from
`# AGENTS.md` onward (Output, Success Criteria, Stop Rules, Task
Tracking) was being dropped from every Codex session without warning.

Skip truncateRule when the source is plugin-bundled; the maxResultChars
budget (40000 default) via truncateBudget still caps total injection.

Locks the behavior with two regression tests in bundled-rules.test.ts:
bundled body > maxRuleChars lands intact, project body > maxRuleChars
still truncates with the standard notice.
2026-05-28 13:58:12 +09:00
YeonGyu-Kim 94b94f26d6 codex-lsp: add MCP lifecycle logging 2026-05-28 13:58:12 +09:00
YeonGyu-Kim 2b4e094982 fix(omo-codex): bundle explorer/librarian/plan agent TOMLs for spawn_agent
The synced Codex skills (refactor, review-work, remove-ai-slops) emit
`spawn_agent(agent_type="explorer"/"librarian"/"plan", ...)` guidance
that sync-skills.mjs injects into every skill containing OpenCode-only
orchestration calls. Only codex-ultrawork-reviewer.toml was bundled, so
Codex had no matching agent role to dispatch.

An older omo-codex release shipped explorer/librarian/plan TOMLs but
without the required top-level `name` field, leaving Codex to warn:

  Ignoring malformed agent role definition: agent role file at
  ~/.codex/agents/<name>.toml must define a non-empty `name`

This commit bundles three correctly-formed TOMLs into
components/ultrawork/agents/. Each has the full schema Codex parses:
`name`, `description`, `nickname_candidates`, `model`,
`model_reasoning_effort`, `service_tier`, `developer_instructions`.
The existing sync-agents.py SessionStart hook installs them via rglob
into CODEX_HOME/agents/.

Models match the original design: explorer + librarian on gpt-5.4-mini
low effort (fast contextual + external research); plan on gpt-5.5
xhigh effort (deep reasoning + interview-style planning).

Tests:
- test/bundled-agents.test.mjs: locks the sync-hook contract by
  running sync-agents.py against a temp CODEX_HOME and verifying each
  TOML lands with the expected name + schema.
- test/aggregate.test.mjs: locks the schema keys on every bundled
  TOML and the spawn_agent contract (every in-scope agent_type
  referenced by a synced skill has a matching bundle).

Follow-up: the sync-skills.mjs compatibility table also references
`spawn_agent(agent_type="worker", ...)`. No worker.toml is present
in CODEX_HOME and Codex does not warn about its absence, suggesting
worker is a built-in Codex role. Confirm and ship worker.toml if not.
2026-05-28 13:58:12 +09:00
YeonGyu-Kim d4ee7ac58e fix(omo-codex): preserve user priority over bundled rules 2026-05-28 13:58:12 +09:00
YeonGyu-Kim ae9bf5771b fixup! feat(omo-codex): add PLUGIN_BUNDLED rule source to codex-rules engine 2026-05-28 13:58:12 +09:00
YeonGyu-Kim 2200e7dc0b feat(omo-codex): bundle Hephaestus craftsman baseline for every Codex session
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-28 13:58:12 +09:00
YeonGyu-Kim 8d2e6bea62 feat(omo-codex): add PLUGIN_BUNDLED rule source to codex-rules engine
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-28 13:58:12 +09:00
YeonGyu-Kim 73e8988f31 feat(omo-codex): enumerate 4 manual-QA channels + forbid tests-alone verification in ultrawork/ultragoal
Promote the four real-usage QA channels (HTTP call, tmux, Browser use, Computer use) into a dedicated top-level `# Manual-QA channels` section in both the Codex ultrawork directive and the ultragoal skill. Each channel ships with the concrete invocation (`curl -i`, `tmux new-session` + `send-keys` + `capture-pane`, Playwright / puppeteer / Chromium, OS-level GUI automation) and the artifact to capture. The Goal section now declares `TESTS ALONE NEVER PROVE DONE` and requires every criterion to build a fresh real-usage scenario and run it through one of the four channels every time. Auxiliary surfaces (CLI stdout / DB diff / parsed config dump) are explicitly demoted: they only satisfy genuinely CLI- or data-shaped criteria, never user-facing behavior.

Bootstrap criterion item 2 and execution step 4 used to repeat the same surface enumeration; they now collapse onto the new channel table (single source of truth, less drift). EXECUTE-AS-SCENARIO in the ultragoal skill follows the same compression. The previous CLEANUP (paired teardown + receipt) + leftover-state stop rule from the prior commit are preserved.

Regression tests in `components/ultrawork/hooks/ultrawork-hooks.test.mjs` pin: the `# Manual-QA channels` heading, all four channel labels (`HTTP call`, `tmux`, `Browser use`, `Computer use`), `TESTS ALONE NEVER PROVE DONE`, `every criterion needs its own real-usage scenario`, and `every time`. README + CHANGELOGs document the restructure and the new size (11,005 chars / 232 lines). All 11 ultrawork hook tests + 7 aggregate tests pass. Installed locally via `runCodexInstaller` into `~/.codex/plugins/cache/code-yeongyu-codex-plugins/omo/0.1.0/`; cache hooks emit the new directive end-to-end and the identifier-like `ulw_helper.ts` keyword-boundary check still suppresses.
2026-05-28 13:58:12 +09:00
YeonGyu-Kim e746dcf0d8 feat(omo-codex): mandate manual-QA-as-scenario + paired cleanup in ultrawork/ultragoal
Both the Codex ultrawork directive and the ultragoal skill now force the agent to actually invoke the real user-facing surface (HTTP via `curl -i`, terminal/TUI via `tmux new-session` + `send-keys` + `capture-pane`, GUI via computer-use / Playwright, CLI stdout, DB diff) instead of treating evidence as a free-form artifact list. A paired CLEANUP step requires teardown of every QA-spawned process, tmux session, browser context, container, bound port, temp file/dir, and QA-only env var, with a one-line cleanup receipt recorded next to the artifact path (ultrawork) or embedded in the `--evidence` string (ultragoal). Missing receipt keeps the criterion in_progress / records BLOCKED. New Stop rule: leftover state from QA means NOT done.

Regression tests in `components/ultrawork/hooks/ultrawork-hooks.test.mjs` pin SURFACE-AS-SCENARIO, the concrete `curl -i` / `tmux new-session` / `computer-use / Playwright` invocations, the paired CLEANUP block with cleanup receipt + `tmux kill-session`, and the leftover-state Stop rule so the mandates cannot be silently regressed. README and CHANGELOGs refreshed; stale 5,821-char claim replaced with measured 10,037 chars / 213 lines. All 9 ultrawork hook tests + 7 aggregate tests pass.
2026-05-28 13:58:12 +09:00
YeonGyu-Kim f77338b4a2 refactor(omo-codex): sync telemetry component sources 2026-05-28 13:58:11 +09:00
YeonGyu-Kim bd867019f9 feat(omo-codex): wire Codex SessionStart telemetry for DAU/WAU/MAU
Adds a new Codex plugin component `telemetry` that emits a single
omo_codex_daily_active event (reason: session_start) from every Codex
SessionStart hook, with the same UTC-day deduplication, hashed
installation identifier, and four-flag opt-out as the install-time
event. Previously omo-codex telemetry only fired on install_completed,
so DAU/WAU/MAU under-reported real Codex usage.

- New plugin component packages/omo-codex/plugin/components/telemetry/
  mirrors the rules/comment-checker/lsp pattern: own src/, tsc build,
  vitest tests, package.json (posthog-node dep), hooks/hooks.json.
- src/codex-hook.ts wraps createPluginPostHog().trackActive(..., "session_start")
  with safeShutdown so Codex session startup never blocks on telemetry.
- Plugin root hooks.json + workspaces register the new component
  alongside rules and ultrawork on SessionStart.
- Aggregate test expectations updated to include the telemetry directory.
- cross-package-equivalence.test.ts pins product-identity constants and
  shouldDisablePostHog behavior to stay byte-equivalent between the CLI
  installer (src/telemetry/) and the plugin runtime
  (plugin/components/telemetry/src/), so the two PostHog sources never
  drift on event name, distinct_id base, dedup file path, or opt-out
  flags.
- PostHogActivityReason union in the CLI-side posthog.ts gains
  "session_start" so future CLI paths can emit the same reason without
  a type break.
2026-05-28 13:58:11 +09:00
YeonGyu-Kim 2415f37bc0 vendor: import codex-plugins as packages/omo-codex/{plugin,scripts,marketplace.json,MARKETPLACE.md} 2026-05-28 13:58:11 +09:00