- Strengthen Prometheus plan template with FORMAT constraint
- Add task label format check to Oracle phase-2 (N/6 → N/7)
- Add format checks to self-review checklist
- New plan-format-validator hook: compares raw checkbox count
against getPlanProgress() after plan writes, warns agent when
labels are malformed (0/0 or partial skip scenarios)
Add new `default_mode` config section with two boolean fields:
- `ultrawork`: Auto-inject ultrawork mode prompt on main session start
without requiring the "ultrawork"/"ulw" keyword. Wired through the
keyword-detector hook — injects once per session, respects existing
guards (non-OMO agents, planner agents, subagent sessions).
- `ralph_loop`: Auto-start ralph loop on first main session message
without requiring /ralph-loop or /ulw-loop commands. When ultrawork
is also enabled, the loop starts in ultrawork mode.
Usage:
```jsonc
{
"default_mode": {
"ultrawork": true, // Always get ultrawork prompt on start
"ralph_loop": true // Auto-start ralph loop
}
}
```
Files: 7 modified/added, ~65 LOC added.
- Add src/locales/ with en baseline and zh overrides (Partial<Record> fallback)
- Add src/shared/i18n.ts with initI18n/t/setLocale/getLocale (LANG env auto-detect)
- Add I18nConfigSchema with locale field to plugin config
- Internationalize 13 hardcoded strings in task-toast-manager
- Add 18 unit tests for i18n module
- Pin manager tests to en locale for determinism
Adds a new `notepad-write-guard` hook that intercepts Write tool calls
whose target path matches `**/.sisyphus/notepads/**` and throws an
actionable error instead of allowing the write to proceed.
Without this guard, an agent that hits an Edit hash-mismatch failure
could silently fall back to Write, destroying the entire history of an
append-only notepad file (decisions.md, issues.md, etc.). The file
carries an explicit "NEVER overwrite" warning that the agent ignores
under context pressure.
The guard is path-based so it works regardless of plan name or nesting
depth. Non-notepad `.sisyphus/**` paths (e.g. plan files) are
unaffected. The hook is wired into `create-tool-guard-hooks` under the
hook name `notepad-write-guard` and follows the same safeCreateHook +
HookName schema pattern as every other tool-guard hook.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add optional `displayName` field to AgentOverrideConfigSchema (next to
the existing `color` field) so users can specify localized agent names
in oh-my-openagent.json:
{ "agents": { "sisyphus": { "displayName": "总指挥" } } }
When set, the override takes precedence everywhere
AGENT_DISPLAY_NAMES[agentName] is used — TUI agent selector, the
agent list key, and the internal `name` field. When not set, behavior
is identical to before (hardcoded English names from AGENT_DISPLAY_NAMES).
Implementation touches:
- AgentOverrideConfigSchema: adds displayName?: z.string().optional()
- getAgentDisplayName / getAgentListDisplayName: accept optional overrides
map and check displayName before the hardcoded table
- remapAgentKeysToDisplayNames: forwards overrides map to name resolution
- agent-config-handler: passes pluginConfig.agents as the overrides map
Backward compatible — existing configs without displayName continue to
work unchanged.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add optional enabled_expansions field to keyword_detector config schema.
When set, acts as an allowlist - only those expansion types fire.
Empty array disables all expansions. Absent field keeps all enabled (backward-compatible).
Also supports coexistence with disabled_keywords denylist for fine-grained control.
- src/config/schema/keyword-detector.ts: add enabled_expansions field
- src/hooks/keyword-detector/detector.ts: apply allowlist filter in detectKeywordsWithType
- src/hooks/keyword-detector/hook.ts: pass enabled_expansions from config
- src/hooks/keyword-detector/index.test.ts: add 4 tests for enabled_expansions behavior
- assets/oh-my-opencode.schema.json: regenerate schema
Adds an opt-in `disabled_providers` config field plus the `shared/disabled-providers`
helper (`isProviderDisabled`, `filterDisabledProviderModels`, `applyDisabledProviders`)
that the plugin-config layer applies to resolved providers.
The routing changes in team-mode (team-runtime, tools/lifecycle, plugin/tool-registry)
are NOT in this PR — those are entangled with the `MemberSelectionMode` /
`ShutdownActor` refactors from the closed PR #3871 and need their own extraction
once those refactors land independently. This PR isolates the parts that are
cleanly independent: schema, helper, and config-layer wiring.
Companion to #4024 (live-tail tailer), both extracted from the closed PR #3871.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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
Adjacent "hpp ulw" or "ulw hpp" (8 form combinations: short/long, both
orders) triggers a fused mode that suppresses the standalone ultrawork
and hyperplan banners and toasts in favor of one combo banner. The
combo banner explicitly preserves hyperplan's mandatory adversarial
workflow contract (do NOT improvise, do NOT skip rounds) instead of
silently downgrading it.
Suppression runs as a named pipeline step (suppressComboStandalones)
immediately after detection and before all consumers (planner filter,
session filters, toasts, message injection), so standalone toast checks
naturally see the already-suppressed list. Combo is allowed in non-main
sessions like ultrawork, filtered for planner agents like both
standalones, and blocked in subagent sessions via the existing gate.
disabled_keywords uses the intersection rule: disabling either
"ultrawork" or "hyperplan" also disables the combo, so no flavored
content leaks via the combo embedding when either base keyword is
disabled.
Includes a same-PR refactor of KEYWORD_DETECTORS from {pattern, message}
to {type, pattern, message} tuple shape, dropping the parallel hardcoded
types array in detector.ts that previously coupled type assignment to
registry index. Future detector additions can no longer silently corrupt
DetectedKeyword.type via reorder or insertion.
10 behavioral contract tests in hyperplan-ultrawork.test.ts cover both
trigger orders, non-adjacent rejection, suppression of injection and
toast, intersection-rule disable behavior, session/agent policy, and
ultrawork variant routing through the combo. The pre-existing combined
"ultrawork hyperplan" assertion in hyperplan.test.ts is removed in
favor of the new file.
Plan distilled from a hyperplan adversarial review (5 members,
3 rounds: skeptic, validator, researcher, architect, creative).
Adds keyword_detector.disabled_keywords config so users can opt out of
specific keyword detectors individually without disabling the entire
keyword-detector hook. Allowed values: 'ultrawork', 'search', 'analyze',
'team'. Default empty/missing -> all four detectors active (no behavior
change for existing configs).
Motivation: an audit revealed search and analyze patterns trigger on
~30-60% of normal conversational user messages (e.g. 'how to', 'why is',
'show me', '왜', '어떻게'). The disable list is the immediate kill switch
while the patterns themselves are tightened in a separate PR.
Schema follows the existing per-feature config block convention shared
by team_mode, ralph_loop, runtime_fallback, and comment_checker. The
KeywordType enum (z.enum) lives next to the config schema and is
re-imported by the detector to keep the union type in lockstep with the
schema.
Threading:
pluginConfig.keyword_detector
-> create-transform-hooks.ts (factory wiring)
-> createKeywordDetectorHook(config)
-> detectKeywordsWithType(text, agent, model, disabledKeywords)
-> Set-based filter at the source-of-truth detector
Adds 8 regression tests covering per-keyword disable, multi-keyword
disable, partial disable (one keyword off, another still firing),
ultrawork toast suppression, undefined config, and empty array.
AgentOverridesSchema silently strips custom agent keys during Zod
parsing because only 14 built-in names are explicitly defined. Add
.catchall(AgentOverrideConfigSchema.optional()) so user-defined agent
configs survive validation and reach downstream consumers like
resolveModelAndFallbackChain().
Fixes#3229.
Blocking fixes:
- B1: Return empty restrictions for unknown/custom agents instead of
EXPLORATION_AGENT_DENYLIST, allowing custom agents full tool access
- B2: Use Object.create(null) consistently across all 5 agent-loading
result objects to prevent prototype pollution
- B3: Add code comment documenting custom agent bash access trust model
- B4: Mock getOpenCodeConfigDir in opencode-config-agents-reader tests
to prevent global config dir leakage
Non-blocking fixes:
- N1: Use resolveAgentDefinitionPaths with project boundary enforcement
in opencode-config-agents-reader for path containment
- N2: Add session-scoped 30s TTL cache to resolveCallableAgents to
avoid redundant SDK IPC calls per tool invocation
- N3: Extract shared parseToolsConfig into src/shared/parse-tools-config.ts
replacing 4 duplicated local implementations
- N4: Add .min(1) to AgentDefinitionPathSchema rejecting empty paths
- N5: Add resolve-agent-definition-paths.test.ts covering tilde expansion,
relative paths, boundary enforcement, and null containmentDir
- N6: Validate agent mode against allowed values instead of bare type
assertion in opencode-config-agents-reader
Wave 1 of agent definitions enhancement (PR #2299):
Schema & Configuration:
- Add agent_definitions field to oh-my-opencode config schema
- Support list of file paths to .md or .json agent definition files
- Add to PARTIAL_STRING_ARRAY_KEYS for Set-union merge semantics
- Implement eager path resolution in loadPluginConfig() before merging
Path Resolution:
- Create resolve-agent-definition-paths.ts helper
- User-level paths resolve from ~/.config/opencode/ (no containment)
- Project-level paths resolve from project root (with containment check)
- Homedir expansion, absolute/relative path handling
JSON Agent Loader:
- Create parseJsonAgentFile() for .json/.jsonc agent definitions
- Validate required fields (name, prompt)
- Support tools as string (comma-separated) or array
- Map model via mapClaudeModelToOpenCode()
- Comprehensive test suite (7 test cases, all passing)
Type Extensions:
- Extend AgentScope: add 'definition-file' and 'opencode-config'
- Add AgentJsonDefinition interface for JSON agent schema
All automated checks passing:
- lsp_diagnostics clean on all changed files
- json-agent-loader.test.ts: 7/7 passing
- Full typecheck: zero new errors
- QA evidence saved to .sisyphus/evidence/
TASK_CLEANUP_DELAY_MS is the delay between a task reaching a terminal
state (completed/cancelled/errored) and its removal from the in-memory
task store. It is currently a hard-coded 10 minute constant, which is
too short for long-running background workflows: users routinely hit
'task not found' on background_output lookups when they inspect
results more than ~10 minutes after completion.
taskTtlMs (landed in #2825) already exposes the non-terminal task TTL
on BackgroundTaskConfigSchema. This PR mirrors that pattern for the
terminal-state cleanup delay:
- Add taskCleanupDelayMs: z.number().min(60000).optional() to
BackgroundTaskConfigSchema with JSDoc matching taskTtlMs's style.
- BackgroundManager.scheduleCompletionRemoval() reads
this.config?.taskCleanupDelayMs ?? TASK_CLEANUP_DELAY_MS, preserving
the existing 10 min default for unconfigured users.
- Regenerate assets/oh-my-opencode.schema.json.
Default: 600000 ms (10 min, unchanged from current hard-coded value).
Minimum: 60000 ms (1 min).
bun run typecheck: clean.
bun test src/features/background-agent: 411/411 pass.
- Fix zod/v4 imports in background-task schema tests
- Remove ZWSP prefix from agent-key-remapper test (fixed in #3136)
- Use toMatchObject for openai-only catalog tests (fallback_models added by #3144)
- Replace z.toJSONSchema (zod v4) with zodToJsonSchema (zod v3 compat)
- Fix task-list.ts type narrowing for zod v3 inferred types
YeonGyu-Kim