oh-my-opencode 5.0.0-beta.1 → 5.0.0-beta.11

package/dist/skills/ulw-plan/references/full-workflow.md

@@ -136,7 +136,7 @@ No Metis, no plan file, no execution until the user approves. The UNCLEAR path a
 
 ## Phase 3 - Generate the plan (only after approval)
 1. Rerun `node "<skill-root>/scripts/scaffold-plan.mjs" <slug> [--clear|--unclear]` without `--draft-only`. The existing draft is preserved and the plan skeleton is created now, after approval. A plain rerun is a safe no-op; never hand-build the skeleton.
-2. **Metis gap analysis (mandatory):** spawn a metis reviewer for contradictions, missing constraints, scope-creep, unvalidated assumptions, and missing acceptance criteria; fold findings in silently.
+2. **Metis gap analysis (mandatory):** spawn a metis reviewer for contradictions, missing constraints — including unstated extrinsic ones: budget/spend, mandated stack, expected scale, target audience / compliance — scope-creep, unvalidated assumptions, and missing acceptance criteria; fold findings in silently; require each constraint gap to return as a proposed default plus reversibility, or a single owner-question when defaulting is unsafe.
 3. APPEND todo batches into the `## Todos` region with edit/apply_patch - never rewrite the script-emitted headers; 50+ todos is fine; one request -> one plan.
 4. Fill `## TL;DR (For humans)` LAST, after the detailed plan, so it summarizes the real plan, not an intention.
 5. Self-review: every todo has references + agent-executable acceptance criteria + happy+failure QA scenarios; no business-logic assumption without evidence; zero criteria need a human. HR6 backstop - confirm the plan's FIRST `## ` heading is `## TL;DR (For humans)` and that every header below it appears in the template order; if you ever hand-built or reordered the file, the human summary must still lead.
@@ -180,7 +180,7 @@ Every "present the plan summary/brief" above delivers THIS structure, in the use
 6. **Execution handoff** - the plan runs in a worker session via `$start-work <plan-name>`; introduce the options: `--worktree <absolute-path>` (task-owned worktree; required for PR/branch work), `--make-pr` (deliver as a PR; auto-creates a task-owned worktree), `--ship` (implies `--make-pr`, keeps working until the PR is reviewed and MERGED).
 
 ### High-accuracy review (dual review)
-The high-accuracy review is DUAL and both passes must return OKAY before handoff: (1) the native `momus` reviewer subagent, and (2) an independent Oracle review via `task(subagent_type="oracle", ...)` on the strongest available reasoning model, in a fully isolated sub-session with normal approval and sandbox policy. Do not add flags that disable approvals or sandboxing. Momus runs at High and may take substantially longer than other agents. One round = exactly ONE `momus` + ONE independent review, dispatched together against the COMPLETE plan file (todos + TL;DR filled) at the draft's exact recorded `plan_path`. Keep Momus in flight and wait for its terminal result: elapsed time alone never justifies cancelling, duplicating, replacing, or treating it as failed. After both verdicts return, fix every cited issue and resubmit both fresh until each approves. CLEAR: runs when the user opts in or `review_required: true`. UNCLEAR: runs automatically unless Classify=Trivial.
+The high-accuracy review is DUAL and both passes must return OKAY before handoff: (1) the native `momus` reviewer subagent, and (2) an independent Oracle review via `task(subagent_type="oracle", ...)` on the strongest available reasoning model, in a fully isolated sub-session with normal approval and sandbox policy. Do not add flags that disable approvals or sandboxing. Momus runs at High and may take substantially longer than other agents. One round = exactly ONE `momus` + ONE independent review, dispatched together against the COMPLETE plan file (todos + TL;DR filled) at the draft's exact recorded `plan_path`. Keep Momus in flight and wait for its terminal result: elapsed time alone never justifies cancelling, duplicating, replacing, or treating it as failed. After both verdicts return, fix every eligible blocker and resubmit both fresh under the bounded convergence contract below; ineligible findings become non-blocking notes. CLEAR: runs when the user opts in or `review_required: true`. UNCLEAR: runs automatically unless Classify=Trivial.
 
 Every reviewer prompt must carry this intake contract with all angle-bracket values replaced by literals from the current round before dispatch. Never pass `draft.plan_path`, `draft.plan_sha256`, field names, or another symbolic reference to an isolated reviewer. Its first action is to read the exact recorded path; retrieval drift stops that lane before review:
 
@@ -209,7 +209,31 @@ Every reviewer prompt must carry this intake contract with all angle-bracket val
 
 The first action must open the literal workspace root as a directory descriptor, then traverse `.omo`, `plans`, and the final target with descriptor-relative no-follow opens, `fstat` each ancestor as a directory and the final descriptor as a regular file, and hash all bytes read from that same final descriptor. If the platform cannot guarantee this chain, or any path/runtime/launch/receipt/digest check drifts, return `INCONCLUSIVE` before reviewing. Echo the literal workspace, runtime home, target, digest, round, and launch ID; the parent separately matches the completion envelope to the persisted session/process receipt. Never search or use another artifact.
 
-The draft must record the native Momus session/result, the independent review session/result, and the fix/retry summary. Immediately before handoff, repeat the same live canonical-path and SHA-256 validation and require it to match the approved round digest; drift invalidates both approvals and starts a fresh round. Do not say "high-accuracy review completed" unless both receipts exist, both final verdicts are unconditional approval, and the final live-plan validation passes.
+### Bounded convergence (the review must terminate)
+Review rounds are capped at 5 (unlimited only on explicit user request), and an approval whose only remaining items are notes counts as approval. A finding may BLOCK only when it names at least one `blocker_eligibility` category below with its concrete evidence; every other finding - speculative durability, replay/crash-recovery, schema, CLI-parsing, state-machine, or hardening concerns the accepted scope never required - is recorded as a non-blocking note and becomes implementation/test work, never plan expansion. After round 1 the blocker ledger FREEZES: later rounds verify accepted ledger blockers, regressions introduced by fixes, and new findings that pass eligibility - they never rediscover the plan from scratch. Fixes apply the smallest edit that resolves the cited blocker; neither reviews nor fixes grow the plan's scope. Every reviewer prompt carries this convergence contract alongside the intake contract. On cap exhaustion without approval: STOP, report outstanding blockers, ask the user - continue / accept / adjust.
+
+<!-- ulw-plan-review-convergence-contract -->
+```json
+{
+  "max_rounds": 5,
+  "max_rounds_override": "explicit_user_request_only",
+  "on_cap_reached": "stop_report_outstanding_blockers_ask_user",
+  "blocker_eligibility": [
+    "explicit_requirement_or_accepted_decision",
+    "existing_failing_regression",
+    "reproducible_broken_flow",
+    "concrete_security_data_loss_or_compatibility_risk",
+    "external_api_provider_or_release_contract_conflict"
+  ],
+  "ineligible_finding_disposition": "non_blocking_note",
+  "approval_with_notes_counts_as_approval": true,
+  "ledger_freeze_after_round": 1,
+  "closure_round_scope": ["accepted_ledger_blockers", "regressions_introduced_by_fixes", "new_findings_passing_blocker_eligibility"],
+  "fix_edit_policy": "smallest_edit_no_scope_expansion"
+}
+```
+
+The draft must record the native Momus session/result, the independent review session/result, and the fix/retry summary, plus the convergence ledger (accepted blockers, non-blocking notes, round count). Immediately before handoff, repeat the same live canonical-path and SHA-256 validation and require it to match the approved round digest; drift invalidates both approvals and starts a fresh round. Do not say "high-accuracy review completed" unless both receipts exist, both final verdicts are unconditional approval, and the final live-plan validation passes.
 
 ## Delegation discipline (OpenCode-native)
 Every delegated prompt starts with `TASK:`, then DELIVERABLE / SCOPE / VERIFY; state the role inside the prompt and include only the context the child needs:

package/dist/skills/ulw-plan/references/intent-clear.md

@@ -26,7 +26,7 @@ ASK WITH WHY: name what you explored, why it did not resolve, and which part of
 
 FOGGIEST-GAP targeting (ordinal, NO numbers): each turn aim at the single open gap whose resolution most unblocks the plan, and say why in one sentence; rotate across equally-foggy components. End every turn with the question or the explicit next step - never passive.
 
-CLEARANCE CHECK after each turn: objective defined? scope IN/OUT explicit? approach decided? test strategy confirmed? no blocking ambiguity left? Any NO is your next question; all YES -> present the approval brief and stop.
+CLEARANCE CHECK after each turn: objective defined? scope IN/OUT explicit? approach decided? test strategy confirmed? constraints swept (budget / stack / scale / audience - each explored, defaulted, or asked)? no blocking ambiguity left? Any NO is your next question; all YES -> present the approval brief and stop.
 </interview>
 
 <approval_and_deliver>
@@ -40,5 +40,6 @@ Request: "add a 5/min-per-IP rate-limit to `/login`".
 3. Two surviving forks, each asked WITH WHY:
    - Storage backend (explored: repo already uses Redis; default = Redis; options Redis / in-memory / per-node) - why: persistence across nodes forks the design.
    - Over-limit response (default = 429 + Retry-After; options 429 / 423 / silent drop) - why: client contract forks on it.
+   - Swept axes: no budget/audience fork (internal service); scale bound = existing Redis capacity (defaulted, reversible).
 4. Approval brief -> explicit okay -> scaffold -> append todos -> if `review_required`, run dual review and deliver receipts; otherwise deliver with the optional review question.
 </worked_example>

package/dist/skills/ulw-plan/references/intent-unclear.md

@@ -20,13 +20,13 @@ TOPOLOGY LOCK still applies: enumerate the 1-6 independently-succeed/fail compon
 </research_protocol>
 
 <default_selection>
-For each open decision, adopt the defensible best-practice default (industry standard or repo convention), RECORD it in the draft's Open-assumptions ledger with rationale and reversibility, and proceed. NO numeric scoring - the ledger IS the audit trail. The ONLY default escalated to a single focused question is one that is irreversible, destructive, or safety-critical and research cannot settle.
+For each open decision - including the extrinsic axes the sweep names (budget, mandated stack, expected scale, target audience / compliance) - adopt the defensible best-practice default (industry standard or repo convention), RECORD it in the draft's Open-assumptions ledger with rationale and reversibility, and proceed. NO numeric scoring - the ledger IS the audit trail. The ONLY default escalated to a single focused question is one that is irreversible, destructive, or safety-critical, or commits real spend the user never authorized, and research cannot settle.
 
 Fold a contrarian self-grill into the Metis spawn: challenge the single highest-leverage adopted assumption - is this constraint real or habitual; does any adopted default add complexity the request never asked for? - and return concrete reframes. The grill targets incidental complexity (unneeded abstraction, speculative capacity), NEVER the feature set: reducing, phasing, or deferring part of the request is not a reframe. Fold a reframe into the plan only as a recommended default plus rationale, never as a forced change.
 </default_selection>
 
 <high_accuracy_auto>
-Because the human did not steer, adversarial review SUBSTITUTES for the interview you skipped - this is what catches a bad default. Metis runs during plan generation as always; after Metis findings are folded and the plan file is complete, run the dual high-accuracy review defined in `full-workflow.md` AUTOMATICALLY - no "do you want a review?" question - and resubmit fresh until BOTH passes APPROVE, fixing every cited issue.
+Because the human did not steer, adversarial review SUBSTITUTES for the interview you skipped - this is what catches a bad default. Metis runs during plan generation as always; after Metis findings are folded and the plan file is complete, run the dual high-accuracy review defined in `full-workflow.md` AUTOMATICALLY - no "do you want a review?" question - and drive it to convergence under the bounded convergence contract in `full-workflow.md`: fix every eligible blocker and resubmit fresh, record ineligible findings as non-blocking notes, and on cap exhaustion stop and ask the user.
 
 TRIVIAL-TIER GUARD: if Classify sized the work Trivial, the auto-Momus loop is SUPPRESSED (Metis still runs once) - a vague-but-tiny request ("clean this up") must not trigger the full adversarial loop. UNCLEAR raises the research-plus-default posture; it does not override the Trivial cost guard for Momus.
 </high_accuracy_auto>
@@ -40,5 +40,5 @@ Request: "make auth better".
 1. Research waves -> current auth at `src/auth/*` and evidence for the requested improvement; best-practice baselines via librarian.
 2. Topology lock as an ANNOUNCEMENT, not a question: components refine the evidenced auth intent in full, such as session hardening, brute-force protection, and password policy when the repository supports them. MFA is an adjacent capability and stays in Scope OUT unless the user asks for it or evidence establishes it as part of the requested outcome.
 3. Adopted-defaults table (assumption | default | rationale | reversible?): bcrypt rounds 8 -> 12 (reversible), add 5/min-per-IP login limit (reversible), rotate session id on privilege change (reversible).
-4. Metis folded -> auto dual review (fix cited gaps until both approve) -> brief LEADING with the approach and the defaults, surfaced in the human TL;DR for veto.
+4. Metis folded -> auto dual review (fix eligible gaps under the bounded convergence contract) -> brief LEADING with the approach and the defaults, surfaced in the human TL;DR for veto.
 </worked_example>

package/dist/tools/delegate-task/builtin-categories.d.ts

@@ -2,5 +2,6 @@ import type { CategoryConfig } from "../../config/schema";
 export declare const DEFAULT_CATEGORIES: Record<string, CategoryConfig>;
 export declare const CATEGORY_PROMPT_APPENDS: Record<string, string>;
 export declare const CATEGORY_DESCRIPTIONS: Record<string, string>;
+export declare const CATEGORY_CALLER_GUIDANCE: Record<string, string | undefined>;
 export declare const CATEGORY_PROMPT_APPEND_RESOLVERS: Record<string, (model: string | undefined) => string>;
 export declare const BUILTIN_CATEGORY_REQUIRES_MODEL: Record<string, string>;

package/dist/tools/delegate-task/builtin-category-definition.d.ts

@@ -3,6 +3,7 @@ export type BuiltinCategoryDefinition = {
     name: string;
     config: CategoryConfig;
     description: string;
+    callerGuidance?: string;
     promptAppend: string;
     resolvePromptAppend?: (model: string | undefined) => string;
     requiresModel?: string;

package/dist/tools/delegate-task/tool-description.d.ts

@@ -6,4 +6,6 @@ export interface DelegateTaskPresentation {
     categoryExamples: string;
     description: string;
 }
-export declare function createDelegateTaskPresentation(options: DelegateTaskToolOptions): DelegateTaskPresentation;
+type DelegateTaskPresentationOptions = Pick<DelegateTaskToolOptions, "availableCategories" | "availableSkills" | "userCategories">;
+export declare function createDelegateTaskPresentation(options: DelegateTaskPresentationOptions): DelegateTaskPresentation;
+export {};

package/dist/tui.js

@@ -15197,7 +15197,7 @@ function finalize(ctx, schema) {
     result.$schema = "http://json-schema.org/draft-07/schema#";
   } else if (ctx.target === "draft-04") {
     result.$schema = "http://json-schema.org/draft-04/schema#";
-  } else if (ctx.target === "openapi-3.0") {} else {}
+  } else if (ctx.target === "openapi-3.0") {}
   if (ctx.external?.uri) {
     const id = ctx.external.registry.get(schema)?.id;
     if (!id)
@@ -15458,7 +15458,7 @@ var formatMap, stringProcessor = (schema, ctx, _json, _params) => {
     if (val === undefined) {
       if (ctx.unrepresentable === "throw") {
         throw new Error("Literal `undefined` cannot be represented in JSON Schema");
-      } else {}
+      }
     } else if (typeof val === "bigint") {
       if (ctx.unrepresentable === "throw") {
         throw new Error("BigInt literals cannot be represented in JSON Schema");
@@ -18837,15 +18837,16 @@ var init_codegraph = __esm(() => {
 });
 
 // packages/omo-config-core/src/schema/memory.ts
-var OmoMemoryReflectionTriggerSchema, OmoMemoryReflectionSchema, OmoMemorySyncSchema, OmoMemorySearchSchema, OmoMemoryReflectionTriggerLayerSchema, OmoMemoryReflectionLayerSchema, OmoMemorySyncLayerSchema, OmoMemorySearchLayerSchema, OmoMemoryAgentOverridesSchema, OmoMemorySettingsSchema, OmoMemorySettingsLayerSchema;
+var OmoMemoryReflectionTriggerSchema, OmoMemoryReflectionSchema, OmoMemorySyncSchema, OmoMemorySearchSchema, OmoMemoryNudgeSchema, OmoMemoryFactsSchema, OmoMemoryDreamSchema, OmoMemoryPeopleSchema, OmoMemorySoulSchema, OmoMemoryReflectionTriggerLayerSchema, OmoMemoryReflectionLayerSchema, OmoMemorySyncLayerSchema, OmoMemorySearchLayerSchema, OmoMemoryNudgeLayerSchema, OmoMemoryFactsLayerSchema, OmoMemoryDreamLayerSchema, OmoMemoryPeopleLayerSchema, OmoMemorySoulLayerSchema, OmoMemoryAgentOverridesSchema, OmoMemorySettingsSchema, OmoMemorySettingsLayerSchema;
 var init_memory = __esm(() => {
   init_zod();
   OmoMemoryReflectionTriggerSchema = object({
-    step_count: number2().int().nonnegative().default(0),
+    step_count: number2().int().nonnegative().default(25),
     on_compaction: boolean2().default(true)
   }).strict();
   OmoMemoryReflectionSchema = object({
-    trigger: OmoMemoryReflectionTriggerSchema.default({ step_count: 0, on_compaction: true }),
+    enabled: boolean2().default(true),
+    trigger: OmoMemoryReflectionTriggerSchema.default({ step_count: 25, on_compaction: true }),
     merge: _enum2(["auto", "integration"]).default("auto"),
     category: string2().min(1).default("quick"),
     timeout_minutes: number2().int().positive().default(15),
@@ -18858,11 +18859,36 @@ var init_memory = __esm(() => {
   OmoMemorySearchSchema = object({
     enabled: boolean2().default(true)
   }).strict();
+  OmoMemoryNudgeSchema = object({
+    enabled: boolean2().default(true),
+    every_user_turns: number2().int().min(1).default(10)
+  }).strict();
+  OmoMemoryFactsSchema = object({
+    enabled: boolean2().default(true),
+    debounce_settles: number2().int().min(1).default(4)
+  }).strict();
+  OmoMemoryDreamSchema = object({
+    enabled: boolean2().default(true),
+    idle_minutes: number2().int().min(0).default(30),
+    min_hours_between: number2().int().min(1).default(24),
+    shutdown_launch: boolean2().default(true),
+    auto_select_max: number2().int().min(1).max(10).default(5),
+    auto_select_max_chars: number2().int().min(1e4).default(150000)
+  }).strict();
+  OmoMemoryPeopleSchema = object({
+    enabled: boolean2().default(true),
+    max_entries: number2().int().min(1).max(100).default(40),
+    max_entry_chars: number2().int().min(50).max(500).default(200)
+  }).strict();
+  OmoMemorySoulSchema = object({
+    edit_notice: boolean2().default(true)
+  }).strict();
   OmoMemoryReflectionTriggerLayerSchema = object({
     step_count: number2().int().nonnegative().optional(),
     on_compaction: boolean2().optional()
   }).strict();
   OmoMemoryReflectionLayerSchema = object({
+    enabled: boolean2().optional(),
     trigger: OmoMemoryReflectionTriggerLayerSchema.optional(),
     merge: _enum2(["auto", "integration"]).optional(),
     category: string2().min(1).optional(),
@@ -18876,10 +18902,39 @@ var init_memory = __esm(() => {
   OmoMemorySearchLayerSchema = object({
     enabled: boolean2().optional()
   }).strict();
+  OmoMemoryNudgeLayerSchema = object({
+    enabled: boolean2().optional(),
+    every_user_turns: number2().int().min(1).optional()
+  }).strict();
+  OmoMemoryFactsLayerSchema = object({
+    enabled: boolean2().optional(),
+    debounce_settles: number2().int().min(1).optional()
+  }).strict();
+  OmoMemoryDreamLayerSchema = object({
+    enabled: boolean2().optional(),
+    idle_minutes: number2().int().min(0).optional(),
+    min_hours_between: number2().int().min(1).optional(),
+    shutdown_launch: boolean2().optional(),
+    auto_select_max: number2().int().min(1).max(10).optional(),
+    auto_select_max_chars: number2().int().min(1e4).optional()
+  }).strict();
+  OmoMemoryPeopleLayerSchema = object({
+    enabled: boolean2().optional(),
+    max_entries: number2().int().min(1).max(100).optional(),
+    max_entry_chars: number2().int().min(50).max(500).optional()
+  }).strict();
+  OmoMemorySoulLayerSchema = object({
+    edit_notice: boolean2().optional()
+  }).strict();
   OmoMemoryAgentOverridesSchema = object({
     enabled: boolean2().optional(),
     agent: string2().min(1).optional(),
     reflection: OmoMemoryReflectionLayerSchema.optional(),
+    nudge: OmoMemoryNudgeLayerSchema.optional(),
+    facts: OmoMemoryFactsLayerSchema.optional(),
+    dream: OmoMemoryDreamLayerSchema.optional(),
+    people: OmoMemoryPeopleLayerSchema.optional(),
+    soul: OmoMemorySoulLayerSchema.optional(),
     sync: OmoMemorySyncLayerSchema.optional(),
     search: OmoMemorySearchLayerSchema.optional(),
     compile_warn_tokens: number2().int().positive().optional()
@@ -18887,13 +18942,27 @@ var init_memory = __esm(() => {
   OmoMemorySettingsSchema = object({
     enabled: boolean2().default(true),
     agent: string2().min(1).default("auto"),
+    tool_exposure: _enum2(["direct", "search"]).default("direct"),
     reflection: OmoMemoryReflectionSchema.default({
-      trigger: { step_count: 0, on_compaction: true },
+      enabled: true,
+      trigger: { step_count: 25, on_compaction: true },
       merge: "auto",
       category: "quick",
       timeout_minutes: 15,
       sandbox: "auto"
     }),
+    nudge: OmoMemoryNudgeSchema.default({ enabled: true, every_user_turns: 10 }),
+    facts: OmoMemoryFactsSchema.default({ enabled: true, debounce_settles: 4 }),
+    dream: OmoMemoryDreamSchema.default({
+      enabled: true,
+      idle_minutes: 30,
+      min_hours_between: 24,
+      shutdown_launch: true,
+      auto_select_max: 5,
+      auto_select_max_chars: 150000
+    }),
+    people: OmoMemoryPeopleSchema.default({ enabled: true, max_entries: 40, max_entry_chars: 200 }),
+    soul: OmoMemorySoulSchema.default({ edit_notice: true }),
     sync: OmoMemorySyncSchema.default({ enabled: true }),
     search: OmoMemorySearchSchema.default({ enabled: true }),
     compile_warn_tokens: number2().int().positive().default(30000),
@@ -18902,7 +18971,13 @@ var init_memory = __esm(() => {
   OmoMemorySettingsLayerSchema = object({
     enabled: boolean2().optional(),
     agent: string2().min(1).optional(),
+    tool_exposure: _enum2(["direct", "search"]).optional(),
     reflection: OmoMemoryReflectionLayerSchema.optional(),
+    nudge: OmoMemoryNudgeLayerSchema.optional(),
+    facts: OmoMemoryFactsLayerSchema.optional(),
+    dream: OmoMemoryDreamLayerSchema.optional(),
+    people: OmoMemoryPeopleLayerSchema.optional(),
+    soul: OmoMemorySoulLayerSchema.optional(),
     sync: OmoMemorySyncLayerSchema.optional(),
     search: OmoMemorySearchLayerSchema.optional(),
     compile_warn_tokens: number2().int().positive().optional(),
@@ -18941,7 +19016,7 @@ function resolveOmoTaskSettings(input, resolveParallelism = availableParallelism
     residency_max_children: record2["residency_max_children"] ?? Math.max(8, resolveParallelism() * 3)
   });
 }
-var ResidencyMaxChildrenInputSchema, OmoTaskWaitSchema, OmoTaskTeamSettingsSchema, OmoTaskWarningsSchema, OmoTaskSettingsSchema, OmoTaskWaitLayerSchema, OmoTaskTeamSettingsLayerSchema, OmoTaskWarningsLayerSchema, OmoTaskSettingsLayerSchema;
+var ResidencyMaxChildrenInputSchema, OmoTaskWaitSchema, OmoTaskTeamSettingsSchema, OmoTaskWarningsSchema, OmoTaskDagSettingsSchema, OmoTaskSettingsSchema, OmoTaskDagSettingsLayerSchema, OmoTaskWaitLayerSchema, OmoTaskTeamSettingsLayerSchema, OmoTaskWarningsLayerSchema, OmoTaskSettingsLayerSchema;
 var init_task = __esm(() => {
   init_zod();
   ResidencyMaxChildrenInputSchema = union([number2().int().positive(), literal("unlimited")]);
@@ -18958,6 +19033,16 @@ var init_task = __esm(() => {
   OmoTaskWarningsSchema = object({
     unavailable_categories: boolean2().default(true)
   }).strict();
+  OmoTaskDagSettingsSchema = object({
+    max_nodes_per_run: number2().int().positive().default(64),
+    max_runs_per_session: number2().int().positive().default(16),
+    subscriber_ring: number2().int().positive().default(1000),
+    heartbeat_ms: number2().int().positive().default(15000),
+    history_default_limit: number2().int().positive().default(256),
+    history_max_limit: number2().int().positive().default(1000),
+    retention_days: number2().int().positive().default(7),
+    max_prompt_bytes: number2().int().positive().default(262144)
+  }).strict();
   OmoTaskSettingsSchema = object({
     default_execution_mode: _enum2(["in-process", "process"]).default("in-process"),
     default_concurrency: number2().int().positive().default(5),
@@ -18975,7 +19060,18 @@ var init_task = __esm(() => {
       max_members: 8,
       max_parallel_members: 4,
       max_wall_clock_minutes: 120
-    })
+    }),
+    dag: OmoTaskDagSettingsSchema.optional()
+  }).strict();
+  OmoTaskDagSettingsLayerSchema = object({
+    max_nodes_per_run: number2().int().positive().optional(),
+    max_runs_per_session: number2().int().positive().optional(),
+    subscriber_ring: number2().int().positive().optional(),
+    heartbeat_ms: number2().int().positive().optional(),
+    history_default_limit: number2().int().positive().optional(),
+    history_max_limit: number2().int().positive().optional(),
+    retention_days: number2().int().positive().optional(),
+    max_prompt_bytes: number2().int().positive().optional()
   }).strict();
   OmoTaskWaitLayerSchema = object({
     min_ms: number2().int().positive().optional(),
@@ -19003,7 +19099,8 @@ var init_task = __esm(() => {
     resume_children: boolean2().optional(),
     warnings: OmoTaskWarningsLayerSchema.optional(),
     wait: OmoTaskWaitLayerSchema.optional(),
-    team: OmoTaskTeamSettingsLayerSchema.optional()
+    team: OmoTaskTeamSettingsLayerSchema.optional(),
+    dag: OmoTaskDagSettingsLayerSchema.optional()
   }).strict();
 });
 
@@ -19058,6 +19155,19 @@ var init_team = __esm(() => {
   OmoTeamsConfigLayerSchema = record(string2(), OmoTeamSpecLayerSchema);
 });
 
+// packages/omo-config-core/src/schema/telemetry.ts
+var OmoTelemetrySettingsShape, OmoTelemetrySettingsLayerSchema, OmoTelemetrySettingsSchema;
+var init_telemetry = __esm(() => {
+  init_zod();
+  OmoTelemetrySettingsShape = {
+    enabled: boolean2()
+  };
+  OmoTelemetrySettingsLayerSchema = object(OmoTelemetrySettingsShape).partial().strict();
+  OmoTelemetrySettingsSchema = OmoTelemetrySettingsLayerSchema.extend({
+    enabled: boolean2().default(true)
+  }).strict();
+});
+
 // packages/omo-config-core/src/schema/config.ts
 var OmoOpenCodeHarnessConfigSchema, OmoTypedHarnessConfigSchema, OmoConfigProfileSchema, OmoConfigSchema, OmoConfigLayerSchema;
 var init_config = __esm(() => {
@@ -19069,6 +19179,7 @@ var init_config = __esm(() => {
   init_model_catalog();
   init_task();
   init_team();
+  init_telemetry();
   OmoOpenCodeHarnessConfigSchema = record(string2(), unknown());
   OmoTypedHarnessConfigSchema = object({
     categories: OmoCategoriesConfigSchema.optional(),
@@ -19077,7 +19188,8 @@ var init_config = __esm(() => {
     task: OmoTaskSettingsLayerSchema.optional(),
     teams: OmoTeamsConfigLayerSchema.optional(),
     models: OmoModelCatalogLayerSchema.optional(),
-    memory: OmoMemorySettingsLayerSchema.optional()
+    memory: OmoMemorySettingsLayerSchema.optional(),
+    telemetry: OmoTelemetrySettingsLayerSchema.optional()
   }).strict();
   OmoConfigProfileSchema = object({
     categories: OmoCategoriesConfigSchema.optional(),
@@ -19087,6 +19199,7 @@ var init_config = __esm(() => {
     teams: OmoTeamsConfigLayerSchema.optional(),
     models: OmoModelCatalogLayerSchema.optional(),
     memory: OmoMemorySettingsLayerSchema.optional(),
+    telemetry: OmoTelemetrySettingsLayerSchema.optional(),
     "[opencode]": OmoOpenCodeHarnessConfigSchema.optional(),
     "[senpi]": OmoTypedHarnessConfigSchema.optional(),
     "[codex]": OmoTypedHarnessConfigSchema.optional()
@@ -19100,6 +19213,7 @@ var init_config = __esm(() => {
     teams: OmoTeamsConfigSchema.optional(),
     models: OmoModelCatalogSchema.optional(),
     memory: OmoMemorySettingsSchema.optional(),
+    telemetry: OmoTelemetrySettingsSchema.optional(),
     "[opencode]": OmoOpenCodeHarnessConfigSchema.optional(),
     "[senpi]": OmoTypedHarnessConfigSchema.optional(),
     "[codex]": OmoTypedHarnessConfigSchema.optional(),
@@ -19116,6 +19230,7 @@ var init_config = __esm(() => {
     teams: OmoTeamsConfigLayerSchema.optional(),
     models: OmoModelCatalogLayerSchema.optional(),
     memory: OmoMemorySettingsLayerSchema.optional(),
+    telemetry: OmoTelemetrySettingsLayerSchema.optional(),
     "[opencode]": OmoOpenCodeHarnessConfigSchema.optional(),
     "[senpi]": OmoTypedHarnessConfigSchema.optional(),
     "[codex]": OmoTypedHarnessConfigSchema.optional(),
@@ -19138,6 +19253,7 @@ var init_schema = __esm(() => {
   init_model_ref();
   init_task();
   init_team();
+  init_telemetry();
 });
 
 // packages/omo-config-core/src/loader/merge.ts
@@ -20964,10 +21080,10 @@ var init_category_model_requirements = __esm(() => {
     quick: {
       fallbackChain: [
         { providers: ["kimi-for-coding"], model: "kimi-for-coding-highspeed" },
-        { providers: ["quotio-openai"], model: "gpt-5.6-luna-fast", variant: "low" },
+        { providers: ["openai-codex"], model: "gpt-5.6-luna-fast", variant: "low" },
         { providers: ["deepseek"], model: "deepseek-v4-flash", variant: "off" },
         {
-          providers: ["qwen-token-plan", "alibaba-token-plan", "bailian-coding-plan", "opencode-go", "vercel"],
+          providers: ["qwen-token-plan", "alibaba-token-plan", "bailian-coding-plan", "vercel"],
           model: "qwen3.6-flash",
           variant: "low"
         },
@@ -20983,6 +21099,11 @@ var init_category_model_requirements = __esm(() => {
     },
     "unspecified-low": {
       fallbackChain: [
+        {
+          providers: ["xai", "github-copilot", "opencode", "vercel"],
+          model: "grok-4.6",
+          variant: "xhigh"
+        },
         {
           providers: ["openai", "quotio-openai", "github-copilot", "opencode", "vercel"],
           model: "gpt-5.6-terra",
@@ -77849,6 +77970,47 @@ var init_model_capabilities_generated = __esm(() => {
           input: 272000,
           output: 128000
         }
+      },
+      "grok-4.6": {
+        id: "grok-4.6",
+        family: "grok",
+        reasoning: true,
+        temperature: true,
+        toolCall: true,
+        modalities: {
+          input: [
+            "text",
+            "image"
+          ],
+          output: [
+            "text"
+          ]
+        },
+        limit: {
+          context: 500000,
+          output: 500000
+        }
+      },
+      "xai/grok-4.6": {
+        id: "xai/grok-4.6",
+        family: "grok",
+        reasoning: true,
+        temperature: true,
+        toolCall: true,
+        modalities: {
+          input: [
+            "text",
+            "image",
+            "pdf"
+          ],
+          output: [
+            "text"
+          ]
+        },
+        limit: {
+          context: 500000,
+          output: 500000
+        }
       }
     }
   };
@@ -78022,24 +78184,14 @@ var init_agent_display_names = __esm(() => {
 // packages/omo-opencode/src/tools/delegate-task/anthropic-categories.ts
 var UNSPECIFIED_HIGH_CATEGORY_PROMPT_APPEND = `<Category_Context>
 You are working on tasks that don't fit specific categories but require substantial effort.
-
-<Selection_Gate>
-BEFORE selecting this category, VERIFY ALL conditions:
-1. Task does NOT fit: quick (trivial), visual-engineering (UI), ultrabrain (deep logic), artistry (creative), writing (docs)
-2. Task requires substantial effort across multiple systems/modules
-3. Changes have broad impact or require careful coordination
-4. NOT just "complex" - must be genuinely unclassifiable AND high-effort
-
-If task fits ANY other category, DO NOT select unspecified-high.
-If task is unclassifiable but moderate-effort, use unspecified-low instead.
-</Selection_Gate>
-</Category_Context>`, ANTHROPIC_CATEGORIES;
+</Category_Context>`, UNSPECIFIED_HIGH_CATEGORY_CALLER_GUIDANCE = `<Selection_Gate>Use only when no specialist category fits and substantial effort spans systems/modules with broad impact. Use unspecified-low for contained moderate work.</Selection_Gate>`, ANTHROPIC_CATEGORIES;
 var init_anthropic_categories = __esm(() => {
   ANTHROPIC_CATEGORIES = [
     {
       name: "unspecified-high",
       config: { model: "kimi-for-coding/k3", variant: "max" },
       description: "Tasks that don't fit other categories, high effort required",
+      callerGuidance: UNSPECIFIED_HIGH_CATEGORY_CALLER_GUIDANCE,
       promptAppend: UNSPECIFIED_HIGH_CATEGORY_PROMPT_APPEND
     }
   ];
@@ -78296,64 +78448,10 @@ Approach:
 - Minimal viable implementation
 - Skip unnecessary abstractions
 - Direct and concise
-</Category_Context>
-
-<Caller_Warning>
-THIS CATEGORY USES A SMALLER/FASTER MODEL (gpt-5.6-luna-fast).
-
-The model executing this task is optimized for speed over depth. Your prompt MUST be:
-
-**EXHAUSTIVELY EXPLICIT** - Leave NOTHING to interpretation:
-1. MUST DO: List every required action as atomic, numbered steps
-2. MUST NOT DO: Explicitly forbid likely mistakes and deviations
-3. EXPECTED OUTPUT: Describe exact success criteria with concrete examples
-
-**WHY THIS MATTERS:**
-- Smaller models benefit from explicit guardrails
-- Vague instructions may lead to unpredictable results
-- Implicit expectations may be missed
-**PROMPT STRUCTURE (MANDATORY):**
-\`\`\`
-TASK: [One-sentence goal]
-
-MUST DO:
-1. [Specific action with exact details]
-2. [Another specific action]
-...
-
-MUST NOT DO:
-- [Forbidden action + why]
-- [Another forbidden action]
-...
-
-EXPECTED OUTPUT:
-- [Exact deliverable description]
-- [Success criteria / verification method]
-\`\`\`
-
-If your prompt lacks this structure, REWRITE IT before delegating.
-</Caller_Warning>`, UNSPECIFIED_LOW_CATEGORY_PROMPT_APPEND = `<Category_Context>
+</Category_Context>`, QUICK_CATEGORY_CALLER_GUIDANCE = `<Caller_Warning>Small/fast model: before delegating, write an explicit prompt with numbered must-do steps, forbidden deviations, and concrete success criteria.</Caller_Warning>`, UNSPECIFIED_LOW_CATEGORY_PROMPT_APPEND = `<Category_Context>
 You are working on tasks that don't fit specific categories but require moderate effort.
-
-<Selection_Gate>
-BEFORE selecting this category, VERIFY ALL conditions:
-1. Task does NOT fit: quick (trivial), visual-engineering (UI), ultrabrain (deep logic), artistry (creative), writing (docs)
-2. Task requires more than trivial effort but is NOT system-wide
-3. Scope is contained within a few files/modules
-
-If task fits ANY other category, DO NOT select unspecified-low.
-This is NOT a default choice - it's for genuinely unclassifiable moderate-effort work.
-</Selection_Gate>
-</Category_Context>
-
-<Caller_Warning>
-THIS CATEGORY USES A LIGHTWEIGHT MODEL (gpt-5.6-luna).
-
-**PROVIDE CLEAR STRUCTURE:**
-1. MUST DO: Enumerate required actions explicitly
-2. MUST NOT DO: State forbidden actions to prevent scope creep
-3. EXPECTED OUTPUT: Define concrete success criteria
-</Caller_Warning>`, OPENAI_CATEGORIES;
+</Category_Context>`, UNSPECIFIED_LOW_CATEGORY_CALLER_GUIDANCE = `<Selection_Gate>Use only when no specialist category fits, effort is moderate, and scope stays within a few files/modules. Prefer any matching specialist category.</Selection_Gate>
+<Caller_Warning>Provide explicit must-do steps, forbidden scope, and concrete success criteria.</Caller_Warning>`, OPENAI_CATEGORIES;
 var init_openai_categories = __esm(() => {
   init_types6();
   OPENAI_CATEGORIES = [
@@ -78375,12 +78473,14 @@ var init_openai_categories = __esm(() => {
       name: "quick",
       config: { model: "kimi-for-coding/kimi-for-coding-highspeed" },
       description: "Trivial tasks - single file changes, typo fixes, simple modifications",
+      callerGuidance: QUICK_CATEGORY_CALLER_GUIDANCE,
       promptAppend: QUICK_CATEGORY_PROMPT_APPEND
     },
     {
       name: "unspecified-low",
-      config: { model: "openai/gpt-5.6-luna", variant: "xhigh" },
+      config: { model: "xai/grok-4.6", variant: "xhigh" },
       description: "Tasks that don't fit other categories, low effort required",
+      callerGuidance: UNSPECIFIED_LOW_CATEGORY_CALLER_GUIDANCE,
       promptAppend: UNSPECIFIED_LOW_CATEGORY_PROMPT_APPEND
     }
   ];
@@ -78390,7 +78490,7 @@ var init_openai_categories = __esm(() => {
 function buildCategoryRecord(selector) {
   return Object.fromEntries(BUILTIN_CATEGORIES.map((definition2) => [definition2.name, selector(definition2)]));
 }
-var BUILTIN_CATEGORIES, DEFAULT_CATEGORIES, CATEGORY_PROMPT_APPENDS, CATEGORY_DESCRIPTIONS, CATEGORY_PROMPT_APPEND_RESOLVERS, BUILTIN_CATEGORY_REQUIRES_MODEL;
+var BUILTIN_CATEGORIES, DEFAULT_CATEGORIES, CATEGORY_PROMPT_APPENDS, CATEGORY_DESCRIPTIONS, CATEGORY_CALLER_GUIDANCE, CATEGORY_PROMPT_APPEND_RESOLVERS, BUILTIN_CATEGORY_REQUIRES_MODEL;
 var init_builtin_categories = __esm(() => {
   init_anthropic_categories();
   init_google_categories();
@@ -78405,6 +78505,7 @@ var init_builtin_categories = __esm(() => {
   DEFAULT_CATEGORIES = buildCategoryRecord((definition2) => definition2.config);
   CATEGORY_PROMPT_APPENDS = buildCategoryRecord((definition2) => definition2.promptAppend);
   CATEGORY_DESCRIPTIONS = buildCategoryRecord((definition2) => definition2.description);
+  CATEGORY_CALLER_GUIDANCE = buildCategoryRecord((definition2) => definition2.callerGuidance);
   CATEGORY_PROMPT_APPEND_RESOLVERS = Object.fromEntries(BUILTIN_CATEGORIES.filter((definition2) => definition2.resolvePromptAppend !== undefined).map((definition2) => [definition2.name, definition2.resolvePromptAppend]));
   BUILTIN_CATEGORY_REQUIRES_MODEL = Object.fromEntries(BUILTIN_CATEGORIES.filter((definition2) => definition2.requiresModel !== undefined).map((definition2) => [definition2.name, definition2.requiresModel]));
 });