web-ci.yml — runs on push/PR to master|dev that touches web/**:
- format:check (prettier --check)
- lint (eslint flat config)
- type-check (tsc --noEmit)
- bun run build (next build, sanity)
- bunx opennextjs-cloudflare build (Cloudflare worker bundle)
web-deploy.yml — runs on push to master that touches web/** OR manual
workflow_dispatch (with optional environment input):
- bun install --frozen-lockfile
- bun run prebuild + bunx opennextjs-cloudflare build
- cloudflare/wrangler-action@v3 deploy with CLOUDFLARE_API_TOKEN +
CLOUDFLARE_ACCOUNT_ID secrets, scoped to working-directory: web
Both gated by paths-filter so plugin-only changes do not trigger them.
Concurrency group cancels in-progress CI runs but NOT in-progress deploys.
A web-production GitHub environment is referenced so deploys can be
gated behind required reviewers / wait timers if desired.
Verified locally end-to-end before push:
- bun install: 678 packages
- format:check: pass after `bun run format` reformatted 21 files
- lint: pass
- type-check: pass
- bun run build: pass (4 locales × pages built)
- bunx opennextjs-cloudflare build: pass (.open-next/worker.js generated)
Imports the public marketing site previously living in
../oh-my-opencode-web. Independent of the npm plugin: own package.json,
bun.lock, tsconfig.json. Not included in the published package — root
files: array still only ships dist/, bin/, postinstall.mjs.
Stack:
- Next.js 15.5 App Router + RSC, deployed to Cloudflare Workers via
@opennextjs/cloudflare (build target .open-next/worker.js).
- Tailwind v4 + shadcn/ui primitives.
- next-intl with 4 locales (en/ja/ko/zh) under app/[locale]/.
- Playwright e2e tests under web/e2e/.
- Custom domains ohmyopenagent.com (primary) and ohmyopencode.org
(legacy alias) declared in web/wrangler.toml.
Source files were re-formatted via `bun run format` to bring them in
line with the existing .prettierrc (singleQuote: false). Functional code
unchanged.
Default `bun test` recurses into every directory and would pick up
`web/e2e/*.spec.ts` once the marketing site lands. Explicitly listing
the existing test roots (matching script/run-ci-tests.ts TEST_ROOTS)
keeps plugin tests isolated from web E2E tests without needing a
`testPathIgnorePatterns` that bunfig.toml does not support yet.
The previous commit (2dfa6336f) used 'git add -A' which swept up files that
prior commits had intentionally deleted but were still present untracked in
the local workspace. This commit re-deletes them to match the upstream intent.
Files removed (each was previously deleted in the cited commit):
- drafts/gpt-5-5/{README,deep,hephaestus,oracle,sisyphus-junior,sisyphus}.md
(deleted in 40ded422c chore(drafts): remove stale gpt-5.5 prompt drafts)
- src/plugin-dispose.{ts,test.ts}
(deleted in e2f5c0d36 refactor(plugin): remove orphaned createPluginDispose)
- src/features/tmux-subagent/{cleanup,session-created-handler,session-deleted-handler}.ts
(deleted in 7a7926f22 chore(tmux-subagent): remove dead event-handler modules)
- src/tools/delegate-task/{model-string-parser,resolve-call-id,resolve-call-id.test}.ts
(model-string-parser deleted in db056346d; resolve-call-id was scratch)
- src/__debug-test.test.ts (debug scratch never intended for git)
Typecheck + model-requirements tests still pass. The legitimate metis +
AGENTS.md edits from the previous commit remain on dev.
Source code change:
- src/shared/model-requirements.ts: prepend claude-sonnet-4-6 to metis fallback
chain so Sonnet becomes the default. Opus 4.7 max remains as the immediate
fallback for callers who want extra reasoning.
- src/shared/model-requirements.test.ts: update assertion to expect Sonnet
primary + Opus secondary.
AGENTS.md accuracy fixes (verified against source):
- Agent modes: Sisyphus/Hephaestus are 'primary' (not 'all'); Sisyphus-Junior
is 'subagent' (not 'all'). Confirmed via 'const MODE: AgentMode = ...' in
each agent file. Also clarified Prometheus has no agentSources factory and
is built via buildPrometheusAgentConfig.
- Sisyphus fallback chain: corrected order to kimi-k2.6 → k2p5 → kimi-k2.5
→ gpt-5.5 medium → glm-5 → big-pickle (was missing kimi-k2.5).
- Librarian/Explore: added missing minimax-m2.7 step between -highspeed and
claude-haiku-4-5.
- Metis chain: removed fictitious gemini-3.1-pro entry.
- Sisyphus-Junior chain: spelled out the actual fallback (was 'user-configurable').
- Temperatures: Sisyphus/Hephaestus do not set explicit temperature (model
default); Sisyphus-Junior is 0.1 via SISYPHUS_JUNIOR_DEFAULTS.
- Quick category default: gpt-5.4-mini (not gpt-5.4-mini-fast).
Team-mode corrections:
- Eligibility registry has 3 verdicts: eligible (sisyphus, atlas, sisyphus-junior),
conditional (hephaestus — needs D-36 teammate permission), hard-reject
(oracle, librarian, explore, multimodal-looker, metis, momus, prometheus).
- Schema has 11 fields, not 4: added max_messages_per_run, max_wall_clock_minutes,
max_member_turns, base_dir, message_payload_max_bytes, recipient_unread_max_bytes,
mailbox_poll_interval_ms.
- Hooks: 'team-session-events' is 4 sub-handlers in src/plugin/event.ts
(team-idle-wake-hint, team-lead-orphan-handler, team-member-error-handler,
team-member-status-handler), not a single Continuation-tier hook.
- Tier counts now show base + team-mode: ToolGuard 14/15, Transform 5/7.
- Total: 52 base hooks, 59 with team-mode.
Doc cascade for the Metis change:
- docs/guide/orchestration.md, agent-model-matching.md, installation.md
- docs/reference/configuration.md, features.md
OpenCode Desktop 1.14.x filters agents by `mode` field. The `mode` was
only present on the factory function as a static property, but not copied
to the generated AgentConfig object.
This fix copies `source.mode` to `base.mode` in `buildAgent()` when:
- source is a factory function (has `mode` static property)
- the generated config doesn't already define `mode`
Test: agent-builder.test.ts (4 pass)
Closes: #3835
Related: #3762, #3812, #3794, #3475, #3474, #3829, #3831, #3824, #3826, #3721, #3806, #3188
The caller-facing description told orchestrators WHAT `deep` is but
never specified goal cardinality, so they bundled multiple goals into
one call (e.g. "fix X + merge Y + deploy Z"). The deep agent's own
prompt was already configured to refuse such bundles, but only after
they arrived. The rule now lives on the caller side: ONE goal + ONE
deliverable per call; multiple goals must fan out as parallel `deep`
calls.
Uses new Function() to prevent the static ESM loader from seeing
the bun: protocol import at parse time. In Electron/Node.js, the
import() call is evaluated at runtime and gracefully returns null
when bun:sqlite is unavailable.
Fixes#3829, likely fixes#3762
- Remove plugin_loaded telemetry from index.ts (was 46.5% of all events, ~2.83M/month)
- Add enableLocalEvaluation: false to prevent feature flag polling/decide calls
- Add strictLocalEvaluation: true to prevent server fallback requests
- Add disableRemoteConfig: true to prevent remote config network requests
- Remove 'plugin_loaded' from PostHogActivityReason type
- Update tests: remove stale mocks, add SDK options verification test
- enableExceptionAutocapture: false already present (kept)
Estimated billing reduction: ~$960+/month from feature flag requests,
plus ~2.83M fewer events/month from plugin_loaded removal.
- DEEP_CATEGORY_PROMPT_APPEND_GPT_5_3_CODEX preserving all DEEP knowledge (atomic task treatment, root cause bias, ambition scaled, completion bar, status sparse) plus codex-specific additions: bias to action, parallel-batch exploration, code implementation discipline, worktree safety, plan closure, pragmatic final-message format\n- resolveDeepCategoryPromptAppend now routes codex first, then 5.5, else legacy (preserves existing 5.5 and 5.4 test invariants)\n- Tests: assert codex no longer falls back to legacy, content tests mirroring the 5.5 pattern (style markers, knowledge preservation, parallel-batch framing, materially different from siblings)
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
- Add isGpt5_2Model type guard\n- ORACLE_GPT_5_2_PROMPT consolidating all knowledge from Claude default, GPT-5.4 generic, and GPT-5.5 variants (XML-tagged blocks, concrete verbosity clamps, long-context re-grounding, anti-narration tool rules, high-risk self-check)\n- MOMUS_GPT_5_2_PROMPT preserving blocker-finder philosophy with new tool_usage_rules block for parallel reference verification\n- Momus GPT-5.2 reasoningEffort set to xhigh per evaluation rigor needs
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
All 5 prompts have been applied to the live codebase:
- sisyphus.md -> src/agents/sisyphus/gpt-5-5.ts
- sisyphus-junior -> src/agents/sisyphus-junior/gpt-5-5.ts
- hephaestus.md -> src/agents/hephaestus/gpt-5-5.ts
- oracle.md -> src/agents/oracle.ts (ORACLE_GPT_5_5_PROMPT inline)
- deep.md -> src/tools/delegate-task/openai-categories.ts (DEEP_CATEGORY_PROMPT_APPEND_GPT_5_5)
The drafts/ directory served its purpose as a design spec staging area
and is no longer the source of truth.
Agent names like \hephaestus\ cause 'Agent not found' errors because
sanitizeSubagentType() was only called in subagent-resolver.ts but not
in the direct manager.launch() path or background-executor.ts.
- manager.ts: strip leading/trailing backslash/quote chars from input.agent
before validation so \hephaestus\ → hephaestus
- background-executor.ts: call sanitizeSubagentType(args.subagent_type)
instead of passing raw value to manager.launch()
- agent-display-names.ts: reuse sanitizeSubagentType in stripAgentListSortPrefix
- Add unit tests for all three fix points
Fixes: sessions dying with 'Agent not found: \hephaestus\'
YeonGyu-Kim