@ngockhoale/ukit 2.6.11 → 2.7.1

package/templates/.omp/README.md

@@ -26,19 +26,23 @@ whatever was there before, so local edits are never silently lost — they move,
 
 ## Model roles
 
-`.omp/config.yml` defines four roles. Agent frontmatter references them as `@lite` / `@code` /
-`@smart` / `@vision`, so retargeting a whole tier is a one-line edit in one file.
+`.omp/config.yml` defines omp's native roles `smol` / `default` / `slow` / `vision` plus
+back-compat aliases `lite` / `code` / `smart` that resolve to the same models. Agent frontmatter
+references the native roles as `@smol` / `@default` / `@slow` / `@vision`, so retargeting a whole
+tier is a one-line edit in one file — but remember the matching `lite`/`code`/`smart` alias is an
+independent key: edit it too, or it keeps resolving to the old value.
 
 | Role | Default model | Agents using it |
 |------|---------------|-----------------|
-| `lite` | `unic-lite` | `ukit-small-task-maintainer` |
-| `code` | `unic-code` | `feature-implementer`, `bug-debugger` |
-| `smart` | `unic-smart` | `handoff-planner`, `code-reviewer` |
+| `smol` (alias `lite`) | `unic-lite` | `ukit-small-task-maintainer` |
+| `default` (alias `code`) | `unic-code` | `feature-implementer`, `bug-debugger` |
+| `slow` (alias `smart`) | `unic-smart` | `handoff-planner`, `code-reviewer` |
 | `vision` | `unic-vision` | `ukit-vision-analyst` |
 
 These are **literal model names on the UNIC gateway, not aliases**, and they ship as the installed
-default. If this project does not run against UNIC, a maintainer swaps the three cost tiers for the
-values in `orchestration.modelTiers[*].claudeModel` in `.ukit/storage/config.json`.
+default. If this project does not run against UNIC, a maintainer swaps the three cost tiers
+(`smol`/`default`/`slow` — and their `lite`/`code`/`smart` aliases) for the values in
+`orchestration.modelTiers[*].claudeModel` in `.ukit/storage/config.json`.
 
 `vision` is the exception and stays `unic-vision` either way: it is a *capability* lane, not a cost
 tier. `unic-code` and `unic-smart` cannot read images on this gateway, so substituting one of them

package/templates/.omp/RULES.md

@@ -40,12 +40,12 @@ work really is, read the matching `SKILL.md` without being asked. Users never na
 ## 6. Delegate to bind a model tier
 
 Your own model does not change mid-turn. A tier only applies when work is handed to a task-agent in
-`.omp/agents/`, whose `model:` field (`@lite` / `@code` / `@smart` / `@vision`) resolves through
+`.omp/agents/`, whose `model:` field (`@smol` / `@default` / `@slow` / `@vision`) resolves through
 `modelRoles` in `.omp/config.yml`.
 
-- `tiny-fix` → `@lite` · `local-fix`, `local-build`, `shared-edit`, `find-cause`, `map-impact` →
-  `@code` · `review-release` → `@smart`
-- Images: `@vision` only. `@code`/`@smart` cannot see images on the UNIC gateway and must never
+- `tiny-fix` → `@smol` · `local-fix`, `local-build`, `shared-edit`, `find-cause`, `map-impact` →
+  `@default` · `review-release` → `@slow`
+- Images: `@vision` only. `@default`/`@slow` cannot see images on the UNIC gateway and must never
   guess at their contents — hand every image to `ukit-vision-analyst` first.
 
 Doing everything inline is exactly what makes UKit look like it only has one model. Keep direct
@@ -73,5 +73,6 @@ last thing you emit is one short line naming what is unfinished and what you nee
 a status — the user cannot distinguish it from a crash.
 
 > Maintainer note, not a per-turn rule: `modelRoles` in `.omp/config.yml` ships UNIC gateway names.
-> On a non-UNIC provider, edit only the three cost tiers — `lite`, `code`, `smart` — never `vision`,
-> which stays `unic-vision` because it is a capability lane, not a cost tier.
+> On a non-UNIC provider, edit only the three cost tiers — `smol`, `default`, `slow` — never `vision`,
+> which stays `unic-vision` (capability lane, not a cost tier). Old keys `lite`/`code`/`smart` remain
+> as compat aliases — edit each alias alongside its tier (smol↔lite, default↔code, slow↔smart).

package/templates/.omp/agents/bug-debugger.md

@@ -1,7 +1,7 @@
 ---
 name: bug-debugger
 description: "Debugging specialist for reproducible errors, failing tests, and unexpected behavior. Use proactively when investigation will involve noisy logs, stack traces, or a self-contained reproduce-trace-fix-verify loop. Do not use for trivial obvious fixes or broad architecture ideation."
-model: "@code"
+model: "@default"
 tools: ["read","grep","glob","bash","edit","ast_edit"]
 ---
 

package/templates/.omp/agents/code-reviewer.md

@@ -1,7 +1,7 @@
 ---
 name: code-reviewer
 description: "Independent reviewer for handoff Phase 3, for spec/plan documents, and for non-blocking sidecar diff review of daily-flow edits. For code (default): use after executor reports STATUS: DONE on a handoff task, MUST run with a model different from the executor (configured in .ukit/storage/config.json → handoff.reviewer.model, default unic-smart), produces a verdict: APPROVED | APPROVED-WITH-MINOR | CHANGES-REQUESTED | CRITICAL. For spec/plan documents (set REVIEW_TARGET_TYPE=spec or plan): reviews a docs/plans/*.md file for completeness/consistency/clarity/scope/YAGNI, produces Status: Approved | Issues Found. For sidecar diff review (set REVIEW_TARGET_TYPE=diff): reviews the current uncommitted git diff after a local-build/shared-edit task, runs in the background and never blocks the main task, produces STATUS: clean | issues-found."
-model: "@smart"
+model: "@slow"
 tools: ["read","grep","glob","bash"]
 ---
 

package/templates/.omp/agents/feature-implementer.md

@@ -1,7 +1,7 @@
 ---
 name: feature-implementer
 description: "Implementation specialist for clear, self-contained coding tasks. Use proactively when the approach is clear and the work can be completed in a bounded pass with a concise summary. Do not use for trivial one-file tweaks or tightly coupled exploratory work."
-model: "@code"
+model: "@default"
 tools: ["read","edit","write","ast_edit","grep","glob","bash"]
 ---
 

package/templates/.omp/agents/handoff-planner.md

@@ -1,7 +1,7 @@
 ---
 name: handoff-planner
 description: "Handoff planning specialist for Phase 1+2. Use when creating a new handoff cycle: writes PLAN.md with full test plan, splits into TASK-xxx.md files with TDD-embedded test cases, and updates INDEX.md. Always use the strongest available model (Opus/unic-smart)."
-model: "@smart"
+model: "@slow"
 tools: ["read","edit","write","ast_edit","glob","bash"]
 ---
 

package/templates/.omp/agents/ukit-small-task-maintainer.md

@@ -1,7 +1,7 @@
 ---
 name: ukit-small-task-maintainer
 description: "Internal UKit maintenance subagent for low-risk, reversible UKit decisions. Use proactively when UKit needs to decide or perform safe cleanup such as pruning docs/TASKS.md, classifying queued work, choosing whether compact/summarization is appropriate, summarizing local docs/status, or maintaining small UKit runtime queues. Do not use for product implementation, security, release/publish, data-loss, architecture, or risky/shared code changes."
-model: "@lite"
+model: "@smol"
 tools: ["read","grep","glob","edit","write","ast_edit"]
 blocking: false
 ---
@@ -11,7 +11,7 @@ You are UKit's internal small-task maintainer. You run as a sidecar/parallel/non
 ## Model Policy
 
 - Use the model selected by `subagents.smallTaskModel` when the host supports model selection for this subagent.
-- Default intended model: `unic-lite`.
+- Default intended model: `unic-lite` (frontmatter `@smol` resolves to `unic-lite` via `.omp/config.yml` modelRoles).
 - If the host cannot bind a model from config directly, still follow this role and report that the configured model is a hint.
 - This lane must run separately from the user's main task model. It must never replace, pause, or slow down the main task.
 

package/templates/.omp/config.yml

@@ -2,23 +2,56 @@
 # models may change during development; orchestration must not branch on vendor names.
 # Do NOT substitute sonnet/opus/haiku here. See PLAN.md §3 D15.
 #
-# Non-UNIC omp provider? A maintainer edits the three cost tiers to the values in
-# orchestration.modelTiers[*].claudeModel (.ukit/storage/config.json) — currently
-# lite: claude-haiku-4-5, code: claude-sonnet-5, smart: claude-opus-5.
+# Non-UNIC omp provider? A maintainer edits the three cost tiers — smol, default, slow —
+# to the values in orchestration.modelTiers[*].claudeModel (.ukit/storage/config.json) —
+# currently lite: claude-haiku-4-5, code: claude-sonnet-5, smart: claude-opus-5.
 # `vision` STAYS unic-vision: its claudeModel is already unic-vision, because
 # unic-code/unic-smart cannot read images on this gateway. claude-sonnet-5 is only
 # modelTiers.vision.fallbackModel, used when unicMode is off — never a drop-in here.
 modelRoles:
+  smol: unic-lite
+  default: unic-code
+  slow: unic-smart
+  vision: unic-vision
+  # Back-compat aliases — INDEPENDENT keys, not references. A maintainer overriding a
+  # cost tier above must edit the matching alias too (smol↔lite, default↔code,
+  # slow↔smart), or the alias keeps resolving to the old unic-* value.
   lite: unic-lite
   code: unic-code
   smart: unic-smart
-  vision: unic-vision
 
 tools:
-  approvalMode: write
+  # TASK-009 / SPEC FR-003: the unattended approval surface is pinned HERE —
+  # `approvalMode: yolo` plus all ten `tools.approval.*: allow`. The product
+  # source of truth is `orchestration.permissionMode: unattended`
+  # (.ukit/storage/config.json, written by TASK-008); this map is its omp-side
+  # rendering so installed projects run prompt-free out of the box.
+  # This SUPERSEDES the TASK-006/C34 omission decision (approvalMode left absent
+  # so the end user's global/runtime mode won): an interactive global would
+  # silently downgrade a shipped install to prompting, contradicting the
+  # unattended contract — the project-level pin is now required, not optional.
+  # `approvalMode: yolo` VERIFIED against omp v17.4.2 (2026-08-22) — same
+  # docContracts allowlist citation as compaction.thresholdTokens below.
+  # Safety under yolo is unchanged: the bash.patterns deny set below, the
+  # TASK-004 hook-bridge deny chain, and this approval map still gate dangerous
+  # ops — `allow` removes interactive prompts, not the deny checks.
+  # Residual risk: yolo + all-allow IS dangerously autonomous and is a
+  # deliberate, user-chosen posture (unattended mode). `eval` stays `allow`
+  # (was `prompt` pre-TASK-001): bash.patterns never covers the eval tool, but
+  # the TASK-004 bridge maps `eval` -> `Bash`, so every eval call is gated by
+  # the same block-dangerous chain as a bash command.
+  approvalMode: yolo
   approval:
     bash: allow
-    eval: prompt
+    eval: allow
+    task: allow
+    read: allow
+    grep: allow
+    write: allow
+    edit: allow
+    lsp: allow
+    browser: allow
+    computer: allow
 
 bash:
   # Translated from templates/.claude/hooks/block-dangerous.sh's DANGEROUS_PATTERNS array.
@@ -27,8 +60,9 @@ bash:
   # catches it. `allow` only ever matches an ENTIRE, non-compound command, so the trailing "*"
   # allow is NOT a universal escape hatch: any compound command (`&&`, `;`, `|`) not itself caught
   # by a `deny`/`prompt` entry falls through to `tools.approvalMode` instead of being auto-allowed.
-  # `bash.patterns` does not cover the `eval` tool at all — that is why `tools.approval.eval` above
-  # is `prompt`, and why TASK-004's bridge separately maps `eval` -> `Bash`.
+  # `bash.patterns` does not cover the `eval` tool at all — that is why TASK-004's bridge
+  # separately maps `eval` -> `Bash`, and why `tools.approval.eval: allow` above does NOT
+  # weaken eval safety: eval stays gated by the bridge's Bash chain (TASK-001).
   patterns:
     - match: "rm -rf /*"
       approval: deny

package/templates/.omp/hooks/pre/ukit-bridge.js

@@ -294,10 +294,18 @@ function translateExecResult(scriptName, execResult) {
   if (code === 2) {
     const structured = parseStructuredDecision(stdout);
     if (structured?.permissionDecision === 'ask') {
+      const askBase = structured.reason || stderr || `${scriptName} requires a human decision`;
+      // omp has no native `ask` — hook() converts this to a block. A bare
+      // "defers to a human" reason dead-ended under YOLO, so the reason must
+      // name the cause class + the recovery action and the chain must surface
+      // a display:true note (done in runScriptChain) so a deliberate block is
+      // distinguishable from a stall.
       return {
         block: false,
         ask: true,
-        reason: structured.reason || stderr || `${scriptName} requires a human decision`,
+        reason: `${askBase} [UKit ask→block: omp has no native "ask", so this gate decision was surfaced as a block. `
+          + 'Recovery: if the cause was an oversized or truncated payload, shrink the payload or re-send it; '
+          + 'if the gate is asking for a decision, decide explicitly — answer the question and re-send the call.]',
         stdout,
         stderr,
       };
@@ -628,6 +636,9 @@ export async function runScriptChain(
       return { block: true, reason: verdict.reason, context, invoked };
     }
     if (verdict.ask) {
+      // The block must be user-visible, not just model-visible — a deliberate
+      // ask→block has to be distinguishable from a silent stall.
+      sendContext(pi, [`[UKit] Gate asks for a human decision — the call was blocked: ${verdict.reason}`], 'nextTurn', { display: true });
       return { block: false, ask: true, reason: verdict.reason, context, invoked };
     }
   }

package/templates/AGENTS.md

@@ -26,6 +26,14 @@
 <!-- RULE: EXEC-04 -->
 - **Every stop says why — no silent idle.** Turns ending on a user-only action open with `WAITING ON YOU: <command/action>` plus a one-shot wakeup (~20-30 min) when available — an ended turn cannot observe external changes, so without it idle looks identical to a stall. Report any error verbatim the same turn.
 
+## Stall & Wait Reporting
+<!-- RULE: STALL-01 -->
+- Announce long waits as they happen: `Waiting for API response / tool result — will keep retrying; check your network/API provider if this persists`. Surface any API/tool error **verbatim** in the same turn, and name network/API as the suspect on long stalls — **never blame UKit**. This guidance makes the model's side of a wait visible; it cannot detect a stall inside the host's own request loop.
+<!-- RULE: STALL-02 -->
+- Every stop still says why (Execution Contract EXEC-04) — the stall rules above extend it, they do not replace it.
+<!-- RULE: STALL-03 -->
+- **Conditional workaround only:** fall back to one tool call per assistant message ONLY when malformed/concatenated tool-input errors are observed or the harness version is known-affected — otherwise keep using legitimate parallel calls; serializing healthy hosts contradicts batching guidance.
+
 ## Long-Run Continuity
 <!-- RULES: LONG-01 LONG-02 -->
 - Near token-cap: **LAND one thing** end-to-end (edit + verify, ≤3 tool calls), **DEFER** the rest into `docs/STATUS.md` or bounded `docs/AI_HANDOFF/` tasks, **DELEGATE** broad work to subagents. Only then compact.
@@ -69,8 +77,8 @@ For any task needing code context:
 
 ## UKit v{{ukit.version}} Shared Runtime
 - Runtime state lives in `.ukit/storage/`; `.ukit/storage/config.json` holds runtime toggles (compact, token pipeline, router, memory, validation, Safe Patch).
-- Reuse `.ukit/storage/memory/` + `ukit memory recall "<current task>"` before asking users to restate decisions; inspect via `ukit status` / `ukit memory export`.
-- Route memory: `.claude/ukit/skill-router-state.json` — reuse compact `previous-context`/`recent-output` first. Cache state: `.ukit/storage/cache/output-history.json`, tee/. Missing/corrupt runtime or old `ukit/` root → rerun `ukit install`. Detail: `docs/UKIT_INTERNALS.md`.
+- Reuse `.ukit/storage/memory/` + `ukit memory recall "<current task>"` before asking users to restate decisions; `ukit memory learn` surfaces pending proposals, `ukit memory promote` writes approved rules to MEMORY.md, `ukit memory episode` records session episodes; inspect via `ukit status` / `ukit memory export`.
+- Route memory: `.claude/ukit/skill-router-state.json` — reuse compact `previous-context`/`recent-output` first. Cache state: `.ukit/storage/cache/output-history.json`, `retriever-lanes.jsonl`, `tee/`. Lifecycle hooks all degrade to exit 0 (SessionEnd `session-episode.sh` auto-writes episodes; full map: `docs/UKIT_INTERNALS.md`). Missing/corrupt runtime or old `ukit/` root → rerun `ukit install`. Detail: `docs/UKIT_INTERNALS.md`.
 
 ## Prompt Caching
 <!-- RULES: CTX-01 CTX-02 CTX-03 CTX-04 CTX-05 CTX-06 CTX-07 CTX-08 CTX-09 CTX-10 -->
@@ -84,9 +92,7 @@ For any task needing code context:
 
 ## Handoff Quality Gate — OPT-IN
 <!-- RULE: HAND-01 -->
-CHỈ kích hoạt khi task đi qua `docs/AI_HANDOFF/` (user nói "execute task TASK-xxx" hoặc target là `docs/AI_HANDOFF/tasks/*.md`). Daily prompt → KHÔNG đụng, flow cũ giữ nguyên.
-
-Khi Handoff mode: đọc `docs/AI_HANDOFF/RULES.md` để biết 4 phase (Idea+Plan → Create Tasks → Implement+Test → Review+Test) + state machine + self-report model. Config: `.ukit/storage/config.json` → `handoff.*`.
+CHỈ kích hoạt khi task đi qua `docs/AI_HANDOFF/` (user nói "execute task TASK-xxx" hoặc target là `docs/AI_HANDOFF/tasks/*.md`). Daily prompt → KHÔNG đụng, flow cũ giữ nguyên. Khi Handoff mode: đọc `docs/AI_HANDOFF/RULES.md` để biết 4 phase (Idea+Plan → Create Tasks → Implement+Test → Review+Test) + state machine + self-report model. Config: `.ukit/storage/config.json` → `handoff.*`.
 
 ## Context + Verification Budget
 <!-- RULE: BUDGET-01 -->
@@ -99,14 +105,10 @@ Khi Handoff mode: đọc `docs/AI_HANDOFF/RULES.md` để biết 4 phase (Idea+P
 - `docs/STATUS.md` captures compact current state — not source truth, never replaces source/index-first investigation.
 - "What next?"/"continue" → `next-step` with a freshness cue; after meaningful work → `update-status`. `docs/TASKS.md` is the local AI task queue — prefer `Ready for AI`. Detail: `docs/UKIT_INTERNALS.md`.
 
-## Small-Task Maintainer (internal)
+## Subagent Lanes (internal)
 <!-- RULE: SUBAG-02 -->
 - The `ukit-small-task-maintainer` subagent (`subagents.smallTaskModel`, default `unic-lite`) handles safe/reversible UKit chores as a sidecar lane — never block or slow the user task; risky work hands back to the main model. Detail: `docs/UKIT_INTERNALS.md`.
-
-## Post-Edit Sidecar Review (internal)
 - When routed state's `routeSummary.line` carries `review=code-reviewer(diff)`, launch `code-reviewer` in background (`smart` tier) **only after** write + verification evidence; findings advisory — never block the reported completion. Detail: `docs/UKIT_INTERNALS.md`.
-
-## Selective Subagent Policy (internal only)
 <!-- RULE: SUBAG-01 -->
 - Direct execution is default for trivial/simple work; delegate only on meaningful context shrink or parallel gains (noisy side lanes, 3+ independent failures, batch plans). Never ask end users to name agents or remember agent commands.
 
@@ -114,6 +116,16 @@ Khi Handoff mode: đọc `docs/AI_HANDOFF/RULES.md` để biết 4 phase (Idea+P
 <!-- RULE: AUTO-01 -->
 - `autonomy.level` in `.ukit/storage/config.json` controls how much UKit acts without asking: `conservative` (ask more), `balanced` (default), `free-run` (auto-run more), `vibecode` (one prompt to a finished result; the gate stops only on completion evidence, a genuine blocker, or a dangerous-command decision). End users should not need to change it.
 
+## Unattended Completion Loop
+<!-- RULE: UNATTENDED-01 -->
+- Under `orchestration.permissionMode: unattended` there is no human in the loop — the loop is UNDERSTAND → PLAN → IMPLEMENT → VERIFY → FIX → REVERIFY → COMPLETE. A turn ends only on COMPLETE evidence, a real external blocker, or a deny decision.
+<!-- RULE: UNATTENDED-02 -->
+- `maxAttemptsPerFailure: 5` per failing verification, `maxRecoveryStrategies: 3` distinct fix strategies before reassessing — retry the same edit, fix the cause differently, then reduce scope/approach; do not loop one strategy.
+<!-- RULE: UNATTENDED-03 -->
+- BLOCKED only on true external blockers: missing credentials, dead service, unreachable network/API. Test failures, lint errors, review findings, and ambiguity are NOT blockers — they feed FIX.
+<!-- RULE: UNATTENDED-04 -->
+- A deny (hook/gate/permission) never becomes a question: pick the next safer alternative that satisfies the intent and record the substitution. Never emit "do you want me to…" — decide and proceed.
+
 ## 3-Tier Model Routing
 <!-- RULES: TIER-01 TIER-02 -->
 **Internal orchestration only — end users still just use natural language. No new commands.**
@@ -124,7 +136,7 @@ Khi Handoff mode: đọc `docs/AI_HANDOFF/RULES.md` để biết 4 phase (Idea+P
 | code | `unic-code` | claude-sonnet | Normal coding, local fixes, shared edits, builds, debugging, impact mapping |
 | smart | `unic-smart` | claude-opus | Release review/audit, escalated deep reasoning after repeated failure |
 
-- A tier takes effect only when work is handed to an agent whose definition binds that model (`model:` frontmatter in `.claude/agents/*.md`; `model:` `@lite`/`@code`/`@smart`/`@vision` in `.omp/agents/*.md` via `modelRoles`) — the main session model never changes mid-turn.
+- A tier takes effect only when work is handed to an agent whose definition binds that model (`model:` frontmatter in `.claude/agents/*.md`; `model:` `@smol`/`@default`/`@slow`/`@vision` in `.omp/agents/*.md` via `modelRoles`) — the main session model never changes mid-turn.
 - Contract map: `tiny-fix` → lite · `local-fix`, `local-build`, `shared-edit`, `find-cause`, `map-impact` → code · `review-release` → smart. Escalation: same file/symbol failing `debugLoopThreshold` (default 2) times routes the next attempt one tier higher, capped at `smart`.
 - `unic-vision` is a capability lane, not a cost tier — unverified vision must never guess image contents; route images to `ukit-vision-analyst`. Harness table: `docs/UKIT_INTERNALS.md`.
 

package/templates/CLAUDE.md

@@ -26,6 +26,14 @@
 <!-- RULE: EXEC-04 -->
 - **Every stop says why — no silent idle.** Turns ending on a user-only action open with `WAITING ON YOU: <command/action>` plus a one-shot wakeup (~20-30 min) when available — an ended turn cannot observe external changes, so without it idle looks identical to a stall. Report any error verbatim the same turn.
 
+## Stall & Wait Reporting
+<!-- RULE: STALL-01 -->
+- Announce long waits as they happen: `Waiting for API response / tool result — will keep retrying; check your network/API provider if this persists`. Surface any API/tool error **verbatim** in the same turn, and name network/API as the suspect on long stalls — **never blame UKit**. This guidance makes the model's side of a wait visible; it cannot detect a stall inside the host's own request loop.
+<!-- RULE: STALL-02 -->
+- Every stop still says why (Execution Contract EXEC-04) — the stall rules above extend it, they do not replace it.
+<!-- RULE: STALL-03 -->
+- **Conditional workaround only:** fall back to one tool call per assistant message ONLY when malformed/concatenated tool-input errors are observed or the harness version is known-affected — otherwise keep using legitimate parallel calls; serializing healthy hosts contradicts batching guidance.
+
 ## Long-Run Continuity
 <!-- RULES: LONG-01 LONG-02 -->
 - Near token-cap: **LAND one thing** end-to-end (edit + verify, ≤3 tool calls), **DEFER** the rest into `docs/STATUS.md` or bounded `docs/AI_HANDOFF/` tasks, **DELEGATE** broad work to subagents. Only then compact.
@@ -69,8 +77,8 @@ For any task needing code context:
 
 ## UKit v{{ukit.version}} Shared Runtime
 - Runtime state lives in `.ukit/storage/`; `.ukit/storage/config.json` holds runtime toggles (compact, token pipeline, router, memory, validation, Safe Patch).
-- Reuse `.ukit/storage/memory/` + `ukit memory recall "<current task>"` before asking users to restate decisions; inspect via `ukit status` / `ukit memory export`.
-- Route memory: `.claude/ukit/skill-router-state.json` — reuse compact `previous-context`/`recent-output` first. Cache state: `.ukit/storage/cache/output-history.json`, tee/. Missing/corrupt runtime or old `ukit/` root → rerun `ukit install`. Detail: `docs/UKIT_INTERNALS.md`.
+- Reuse `.ukit/storage/memory/` + `ukit memory recall "<current task>"` before asking users to restate decisions; `ukit memory learn` surfaces pending proposals, `ukit memory promote` writes approved rules to MEMORY.md, `ukit memory episode` records session episodes; inspect via `ukit status` / `ukit memory export`.
+- Route memory: `.claude/ukit/skill-router-state.json` — reuse compact `previous-context`/`recent-output` first. Cache state: `.ukit/storage/cache/output-history.json`, `retriever-lanes.jsonl`, `tee/`. Lifecycle hooks all degrade to exit 0 (SessionEnd `session-episode.sh` auto-writes episodes; full map: `docs/UKIT_INTERNALS.md`). Missing/corrupt runtime or old `ukit/` root → rerun `ukit install`. Detail: `docs/UKIT_INTERNALS.md`.
 
 ## Prompt Caching
 <!-- RULES: CTX-01 CTX-02 CTX-03 CTX-04 CTX-05 CTX-06 CTX-07 CTX-08 CTX-09 CTX-10 -->
@@ -84,9 +92,7 @@ For any task needing code context:
 
 ## Handoff Quality Gate — OPT-IN
 <!-- RULE: HAND-01 -->
-CHỈ kích hoạt khi task đi qua `docs/AI_HANDOFF/` (user nói "execute task TASK-xxx" hoặc target là `docs/AI_HANDOFF/tasks/*.md`). Daily prompt → KHÔNG đụng, flow cũ giữ nguyên.
-
-Khi Handoff mode: đọc `docs/AI_HANDOFF/RULES.md` để biết 4 phase (Idea+Plan → Create Tasks → Implement+Test → Review+Test) + state machine + self-report model. Config: `.ukit/storage/config.json` → `handoff.*`.
+CHỈ kích hoạt khi task đi qua `docs/AI_HANDOFF/` (user nói "execute task TASK-xxx" hoặc target là `docs/AI_HANDOFF/tasks/*.md`). Daily prompt → KHÔNG đụng, flow cũ giữ nguyên. Khi Handoff mode: đọc `docs/AI_HANDOFF/RULES.md` để biết 4 phase (Idea+Plan → Create Tasks → Implement+Test → Review+Test) + state machine + self-report model. Config: `.ukit/storage/config.json` → `handoff.*`.
 
 ## Context + Verification Budget
 <!-- RULE: BUDGET-01 -->
@@ -99,14 +105,10 @@ Khi Handoff mode: đọc `docs/AI_HANDOFF/RULES.md` để biết 4 phase (Idea+P
 - `docs/STATUS.md` captures compact current state — not source truth, never replaces source/index-first investigation.
 - "What next?"/"continue" → `next-step` with a freshness cue; after meaningful work → `update-status`. `docs/TASKS.md` is the local AI task queue — prefer `Ready for AI`. Detail: `docs/UKIT_INTERNALS.md`.
 
-## Small-Task Maintainer (internal)
+## Subagent Lanes (internal)
 <!-- RULE: SUBAG-02 -->
 - The `ukit-small-task-maintainer` subagent (`subagents.smallTaskModel`, default `unic-lite`) handles safe/reversible UKit chores as a sidecar lane — never block or slow the user task; risky work hands back to the main model. Detail: `docs/UKIT_INTERNALS.md`.
-
-## Post-Edit Sidecar Review (internal)
 - When routed state's `routeSummary.line` carries `review=code-reviewer(diff)`, launch `code-reviewer` in background (`smart` tier) **only after** write + verification evidence; findings advisory — never block the reported completion. Detail: `docs/UKIT_INTERNALS.md`.
-
-## Selective Subagent Policy (internal only)
 <!-- RULE: SUBAG-01 -->
 - Direct execution is default for trivial/simple work; delegate only on meaningful context shrink or parallel gains (noisy side lanes, 3+ independent failures, batch plans). Never ask end users to name agents or remember agent commands.
 
@@ -114,6 +116,16 @@ Khi Handoff mode: đọc `docs/AI_HANDOFF/RULES.md` để biết 4 phase (Idea+P
 <!-- RULE: AUTO-01 -->
 - `autonomy.level` in `.ukit/storage/config.json` controls how much UKit acts without asking: `conservative` (ask more), `balanced` (default), `free-run` (auto-run more), `vibecode` (one prompt to a finished result; the gate stops only on completion evidence, a genuine blocker, or a dangerous-command decision). End users should not need to change it.
 
+## Unattended Completion Loop
+<!-- RULE: UNATTENDED-01 -->
+- Under `orchestration.permissionMode: unattended` there is no human in the loop — the loop is UNDERSTAND → PLAN → IMPLEMENT → VERIFY → FIX → REVERIFY → COMPLETE. A turn ends only on COMPLETE evidence, a real external blocker, or a deny decision.
+<!-- RULE: UNATTENDED-02 -->
+- `maxAttemptsPerFailure: 5` per failing verification, `maxRecoveryStrategies: 3` distinct fix strategies before reassessing — retry the same edit, fix the cause differently, then reduce scope/approach; do not loop one strategy.
+<!-- RULE: UNATTENDED-03 -->
+- BLOCKED only on true external blockers: missing credentials, dead service, unreachable network/API. Test failures, lint errors, review findings, and ambiguity are NOT blockers — they feed FIX.
+<!-- RULE: UNATTENDED-04 -->
+- A deny (hook/gate/permission) never becomes a question: pick the next safer alternative that satisfies the intent and record the substitution. Never emit "do you want me to…" — decide and proceed.
+
 ## 3-Tier Model Routing
 <!-- RULES: TIER-01 TIER-02 -->
 **Internal orchestration only — end users still just use natural language. No new commands.**
@@ -124,7 +136,7 @@ Khi Handoff mode: đọc `docs/AI_HANDOFF/RULES.md` để biết 4 phase (Idea+P
 | code | `unic-code` | claude-sonnet | Normal coding, local fixes, shared edits, builds, debugging, impact mapping |
 | smart | `unic-smart` | claude-opus | Release review/audit, escalated deep reasoning after repeated failure |
 
-- A tier takes effect only when work is handed to an agent whose definition binds that model (`model:` frontmatter in `.claude/agents/*.md`; `model:` `@lite`/`@code`/`@smart`/`@vision` in `.omp/agents/*.md` via `modelRoles`) — the main session model never changes mid-turn.
+- A tier takes effect only when work is handed to an agent whose definition binds that model (`model:` frontmatter in `.claude/agents/*.md`; `model:` `@smol`/`@default`/`@slow`/`@vision` in `.omp/agents/*.md` via `modelRoles`) — the main session model never changes mid-turn.
 - Contract map: `tiny-fix` → lite · `local-fix`, `local-build`, `shared-edit`, `find-cause`, `map-impact` → code · `review-release` → smart. Escalation: same file/symbol failing `debugLoopThreshold` (default 2) times routes the next attempt one tier higher, capped at `smart`.
 - `unic-vision` is a capability lane, not a cost tier — unverified vision must never guess image contents; route images to `ukit-vision-analyst`. Harness table: `docs/UKIT_INTERNALS.md`.
 

package/templates/adapter-presets/opencode/opencode.template.json

@@ -1 +1 @@
-{"$schema":"https://opencode.ai/config.json","default_agent":"build","share":"disabled","compaction":{"auto":true,"prune":true,"reserved":10000},"watcher":{"ignore":[".git/**","node_modules/**",".cache/**",".ukit/**",".claude/ukit/permission-usage.json",".claude/ukit/permission-audit.log"]},"permission":{"doom_loop":"deny"},"command":{"ukit-route":{"description":"Internal shared UKit route. Run at the start of every non-trivial task to get skill and context hints before writing code.","agent":"build","template":"Run `node .claude/ukit/index/route-task.mjs \"<task>\" --adapter opencode`; reuse `.claude/ukit/skill-router-state.json`."},"ukit-context":{"description":"Internal UKit context.","agent":"build","template":"Run `node .claude/ukit/index/resolve-context.mjs \"<intent>\" [--target <file>]`."},"ukit-verify":{"description":"Internal UKit verify lane.","agent":"build","template":"Run `node .claude/ukit/index/verify-context.mjs \"<intent>\" [--target <file>]`."},"ukit-triage":{"description":"Internal UKit triage.","agent":"build","template":"Run `node .claude/ukit/index/triage.mjs \"<error>\"`."},"ukit-query":{"description":"Internal UKit query.","agent":"build","template":"Run `node .claude/ukit/index/query-index.mjs \"<error|symbol|path>\"`."},"ukit-index":{"description":"Internal UKit index.","agent":"build","template":"Run `node .claude/ukit/index/refresh-index.mjs` (fallback: `node .claude/ukit/index/build-index.mjs`)."},"ukit-handoff-status":{"description":"Handoff dashboard — show current cycle status (read-only).","agent":"build","template":"Read `docs/AI_HANDOFF/INDEX.md`, `docs/AI_HANDOFF/ACTIVE.md`, and `docs/AI_HANDOFF/PLAN.md`. Report: active cycle name, task table with status, any blockers. No writes."},"ukit-handoff-create":{"description":"Create a new handoff cycle — Phase 1+2: write PLAN.md + TASK-xxx.md files.","agent":"build","template":"Read `.claude/commands/ukit/create-handoff.md` for full instructions, then execute. Description: <what to build>"},"ukit-handoff-implement":{"description":"Execute handoff tasks — Phase 3: implement the next Ready task.","agent":"build","template":"Read `.claude/commands/ukit/implement-handoff.md` for full instructions, then execute. Task ID (optional): <TASK-xxx>"},"ukit-handoff-review":{"description":"Review handoff results — Phase 4: verify implementation and give verdict.","agent":"build","template":"Read `.claude/commands/ukit/review-handoff.md` for full instructions, then execute. Task ID (optional): <TASK-xxx>"},"ukit-handoff-clear":{"description":"Archive and reset the current handoff cycle.","agent":"build","template":"Read `.claude/commands/ukit/clear-handoff.md` for full instructions, then execute."}},"agent":{"build":{"description":"UKit build agent. Follow AGENTS.md. For every non-trivial task: run /ukit-route first, use index-first loop, activate matching skill, never claim done after read-only steps. Keep internal ukit-* helpers hidden; users only need ukit install.","permission":{"edit":"allow","task":"allow","skill":"allow","bash":{"*":"ask","pwd":"allow","ls":"allow","ls *":"allow","find *":"allow","rg *":"allow","grep *":"allow","cat *":"allow","sed *":"allow","head *":"allow","tail *":"allow","wc *":"allow","echo *":"allow","printf *":"allow","awk *":"allow","tr *":"allow","cut *":"allow","sort *":"allow","uniq *":"allow","diff *":"allow","jq *":"allow","stat *":"allow","file *":"allow","which *":"allow","date *":"allow","basename *":"allow","dirname *":"allow","realpath *":"allow","xargs *":"allow","mkdir *":"allow","touch *":"allow","cp *":"allow","vitest *":"allow","jest *":"allow","git status":"allow","git status *":"allow","git diff":"allow","git diff *":"allow","git log":"allow","git log *":"allow","git show *":"allow","git grep *":"allow","git rev-parse *":"allow","git branch *":"allow","git stash list":"allow","git ls-files *":"allow","git tag *":"allow","node .claude/ukit/index/*":"allow","node .claude/ukit/runtime/*":"allow","{{runtime.packageManager}} test":"allow","{{runtime.packageManager}} test *":"allow","{{runtime.packageManager}} lint":"allow","{{runtime.packageManager}} lint *":"allow","{{runtime.packageManager}} typecheck":"allow","{{runtime.packageManager}} typecheck *":"allow","{{runtime.packageManager}} build":"allow","{{runtime.packageManager}} build *":"allow","npm run test":"allow","npm run test *":"allow","npm run lint":"allow","npm run lint *":"allow","npm run typecheck":"allow","npm run typecheck *":"allow","npm run build":"allow","npm run build *":"allow","pnpm test":"allow","pnpm test *":"allow","pnpm lint":"allow","pnpm lint *":"allow","pnpm typecheck":"allow","pnpm typecheck *":"allow","pnpm build":"allow","pnpm build *":"allow","pnpm run test":"allow","pnpm run test *":"allow","pnpm run lint":"allow","pnpm run lint *":"allow","pnpm run typecheck":"allow","pnpm run typecheck *":"allow","pnpm run build":"allow","pnpm run build *":"allow","bun test":"allow","bun test *":"allow","bun run test":"allow","bun run test *":"allow","bun run lint":"allow","bun run lint *":"allow","bun run typecheck":"allow","bun run typecheck *":"allow","bun run build":"allow","bun run build *":"allow","git commit":"ask","git commit *":"ask","git push":"ask","git push *":"ask","git clean":"deny","git clean *":"deny","git reset":"deny","git reset *":"deny","rm *":"deny"}}},"plan":{"permission":{"edit":"ask","bash":"ask"}}}}
+{"$schema":"https://opencode.ai/config.json","default_agent":"build","share":"disabled","compaction":{"auto":true,"prune":true,"reserved":10000},"watcher":{"ignore":[".git/**","node_modules/**",".cache/**",".ukit/**",".claude/ukit/permission-usage.json",".claude/ukit/permission-audit.log"]},"permission":{"doom_loop":"deny"},"command":{"ukit-route":{"description":"Internal shared UKit route. Run at the start of every non-trivial task to get skill and context hints before writing code.","agent":"build","template":"Run `node .claude/ukit/index/route-task.mjs \"<task>\" --adapter opencode`; reuse `.claude/ukit/skill-router-state.json`."},"ukit-context":{"description":"Internal UKit context.","agent":"build","template":"Run `node .claude/ukit/index/resolve-context.mjs \"<intent>\" [--target <file>]`."},"ukit-verify":{"description":"Internal UKit verify lane.","agent":"build","template":"Run `node .claude/ukit/index/verify-context.mjs \"<intent>\" [--target <file>]`."},"ukit-triage":{"description":"Internal UKit triage.","agent":"build","template":"Run `node .claude/ukit/index/triage.mjs \"<error>\"`."},"ukit-query":{"description":"Internal UKit query.","agent":"build","template":"Run `node .claude/ukit/index/query-index.mjs \"<error|symbol|path>\"`."},"ukit-index":{"description":"Internal UKit index.","agent":"build","template":"Run `node .claude/ukit/index/refresh-index.mjs` (fallback: `node .claude/ukit/index/build-index.mjs`)."},"ukit-handoff-status":{"description":"Handoff dashboard — show current cycle status (read-only).","agent":"build","template":"Read `docs/AI_HANDOFF/INDEX.md`, `docs/AI_HANDOFF/ACTIVE.md`, and `docs/AI_HANDOFF/PLAN.md`. Report: active cycle name, task table with status, any blockers. No writes."},"ukit-handoff-create":{"description":"Create a new handoff cycle — Phase 1+2: write PLAN.md + TASK-xxx.md files.","agent":"build","template":"Read `.claude/commands/ukit/create-handoff.md` for full instructions, then execute. Description: <what to build>"},"ukit-handoff-implement":{"description":"Execute handoff tasks — Phase 3: implement the next Ready task.","agent":"build","template":"Read `.claude/commands/ukit/implement-handoff.md` for full instructions, then execute. Task ID (optional): <TASK-xxx>"},"ukit-handoff-review":{"description":"Review handoff results — Phase 4: verify implementation and give verdict.","agent":"build","template":"Read `.claude/commands/ukit/review-handoff.md` for full instructions, then execute. Task ID (optional): <TASK-xxx>"},"ukit-handoff-clear":{"description":"Archive and reset the current handoff cycle.","agent":"build","template":"Read `.claude/commands/ukit/clear-handoff.md` for full instructions, then execute."}},"agent":{"build":{"description":"UKit build agent. Follow AGENTS.md. For every non-trivial task: run /ukit-route first, use index-first loop, activate matching skill, never claim done after read-only steps. Keep internal ukit-* helpers hidden; users only need ukit install.","permission":{"edit":"allow","task":"allow","skill":"allow","bash":{"*":"ask","pwd":"allow","ls":"allow","ls *":"allow","find *":"allow","rg *":"allow","grep *":"allow","cat *":"allow","sed *":"allow","head *":"allow","tail *":"allow","wc *":"allow","echo *":"allow","printf *":"allow","awk *":"allow","tr *":"allow","cut *":"allow","sort *":"allow","uniq *":"allow","diff *":"allow","jq *":"allow","stat *":"allow","file *":"allow","which *":"allow","date *":"allow","basename *":"allow","dirname *":"allow","realpath *":"allow","xargs *":"allow","mkdir *":"allow","touch *":"allow","cp *":"allow","vitest *":"allow","jest *":"allow","git status":"allow","git status *":"allow","git diff":"allow","git diff *":"allow","git log":"allow","git log *":"allow","git show *":"allow","git grep *":"allow","git rev-parse *":"allow","git branch *":"allow","git stash list":"allow","git ls-files *":"allow","git tag *":"allow","git add *":"allow","git checkout *":"allow","git switch *":"allow","git restore *":"allow","git mv *":"allow","mv *":"allow","node *":"allow","node .claude/ukit/index/*":"allow","node .claude/ukit/runtime/*":"allow","npx *":"allow","npm test":"allow","npm test *":"allow","{{runtime.packageManager}} test":"allow","{{runtime.packageManager}} test *":"allow","{{runtime.packageManager}} lint":"allow","{{runtime.packageManager}} lint *":"allow","{{runtime.packageManager}} typecheck":"allow","{{runtime.packageManager}} typecheck *":"allow","{{runtime.packageManager}} build":"allow","{{runtime.packageManager}} build *":"allow","npm run test":"allow","npm run test *":"allow","npm run lint":"allow","npm run lint *":"allow","npm run typecheck":"allow","npm run typecheck *":"allow","npm run build":"allow","npm run build *":"allow","pnpm test":"allow","pnpm test *":"allow","pnpm lint":"allow","pnpm lint *":"allow","pnpm typecheck":"allow","pnpm typecheck *":"allow","pnpm build":"allow","pnpm build *":"allow","pnpm run test":"allow","pnpm run test *":"allow","pnpm run lint":"allow","pnpm run lint *":"allow","pnpm run typecheck":"allow","pnpm run typecheck *":"allow","pnpm run build":"allow","pnpm run build *":"allow","bun test":"allow","bun test *":"allow","bun run test":"allow","bun run test *":"allow","bun run lint":"allow","bun run lint *":"allow","bun run typecheck":"allow","bun run typecheck *":"allow","bun run build":"allow","bun run build *":"allow","git commit":"allow","git commit *":"allow","git push":"allow","git push *":"allow","git clean":"deny","git clean *":"deny","git reset":"deny","git reset *":"deny","rm *":"deny"}}},"plan":{"permission":{"edit":"ask","bash":"ask"}}}}

package/templates/docs/UKIT_INTERNALS.md

@@ -179,7 +179,7 @@ whose own definition binds that model.
 | Harness | Agent definitions | How to launch one |
 |---------|-------------------|-------------------|
 | Claude Code | `.claude/agents/*.md` (`model:` frontmatter) | Agent tool, `subagent_type: "<name>"` |
-| omp | `.omp/agents/*.md` (`model: "@lite"` / `"@code"` / `"@smart"` / `"@vision"`, resolved through `modelRoles` in `.omp/config.yml`) | task-agent `<name>` |
+| omp | `.omp/agents/*.md` (`model: "@smol"` / `"@default"` / `"@slow"` / `"@vision"`, resolved through `modelRoles` in `.omp/config.yml`) | task-agent `<name>` |
 
 When a task's contract maps to a tier other than the current session model, hand it to the
 matching agent instead of doing it inline. Doing everything inline is exactly what makes

package/templates/instructions/core.md

@@ -23,6 +23,14 @@
 <!-- RULE: EXEC-04 -->
 - **Every stop says why — no silent idle.** Turns ending on a user-only action open with `WAITING ON YOU: <command/action>` plus a one-shot wakeup (~20-30 min) when available — an ended turn cannot observe external changes, so without it idle looks identical to a stall. Report any error verbatim the same turn.
 
+## Stall & Wait Reporting
+<!-- RULE: STALL-01 -->
+- Announce long waits as they happen: `Waiting for API response / tool result — will keep retrying; check your network/API provider if this persists`. Surface any API/tool error **verbatim** in the same turn, and name network/API as the suspect on long stalls — **never blame UKit**. This guidance makes the model's side of a wait visible; it cannot detect a stall inside the host's own request loop.
+<!-- RULE: STALL-02 -->
+- Every stop still says why (Execution Contract EXEC-04) — the stall rules above extend it, they do not replace it.
+<!-- RULE: STALL-03 -->
+- **Conditional workaround only:** fall back to one tool call per assistant message ONLY when malformed/concatenated tool-input errors are observed or the harness version is known-affected — otherwise keep using legitimate parallel calls; serializing healthy hosts contradicts batching guidance.
+
 ## Long-Run Continuity
 <!-- RULES: LONG-01 LONG-02 -->
 - Near token-cap: **LAND one thing** end-to-end (edit + verify, ≤3 tool calls), **DEFER** the rest into `docs/STATUS.md` or bounded `docs/AI_HANDOFF/` tasks, **DELEGATE** broad work to subagents. Only then compact.
@@ -66,8 +74,8 @@ For any task needing code context:
 
 ## UKit v{{ukit.version}} Shared Runtime
 - Runtime state lives in `.ukit/storage/`; `.ukit/storage/config.json` holds runtime toggles (compact, token pipeline, router, memory, validation, Safe Patch).
-- Reuse `.ukit/storage/memory/` + `ukit memory recall "<current task>"` before asking users to restate decisions; inspect via `ukit status` / `ukit memory export`.
-- Route memory: `.claude/ukit/skill-router-state.json` — reuse compact `previous-context`/`recent-output` first. Cache state: `.ukit/storage/cache/output-history.json`, tee/. Missing/corrupt runtime or old `ukit/` root → rerun `ukit install`. Detail: `docs/UKIT_INTERNALS.md`.
+- Reuse `.ukit/storage/memory/` + `ukit memory recall "<current task>"` before asking users to restate decisions; `ukit memory learn` surfaces pending proposals, `ukit memory promote` writes approved rules to MEMORY.md, `ukit memory episode` records session episodes; inspect via `ukit status` / `ukit memory export`.
+- Route memory: `.claude/ukit/skill-router-state.json` — reuse compact `previous-context`/`recent-output` first. Cache state: `.ukit/storage/cache/output-history.json`, `retriever-lanes.jsonl`, `tee/`. Lifecycle hooks all degrade to exit 0 (SessionEnd `session-episode.sh` auto-writes episodes; full map: `docs/UKIT_INTERNALS.md`). Missing/corrupt runtime or old `ukit/` root → rerun `ukit install`. Detail: `docs/UKIT_INTERNALS.md`.
 
 ## Prompt Caching
 <!-- RULES: CTX-01 CTX-02 CTX-03 CTX-04 CTX-05 CTX-06 CTX-07 CTX-08 CTX-09 CTX-10 -->
@@ -81,9 +89,7 @@ For any task needing code context:
 
 ## Handoff Quality Gate — OPT-IN
 <!-- RULE: HAND-01 -->
-CHỈ kích hoạt khi task đi qua `docs/AI_HANDOFF/` (user nói "execute task TASK-xxx" hoặc target là `docs/AI_HANDOFF/tasks/*.md`). Daily prompt → KHÔNG đụng, flow cũ giữ nguyên.
-
-Khi Handoff mode: đọc `docs/AI_HANDOFF/RULES.md` để biết 4 phase (Idea+Plan → Create Tasks → Implement+Test → Review+Test) + state machine + self-report model. Config: `.ukit/storage/config.json` → `handoff.*`.
+CHỈ kích hoạt khi task đi qua `docs/AI_HANDOFF/` (user nói "execute task TASK-xxx" hoặc target là `docs/AI_HANDOFF/tasks/*.md`). Daily prompt → KHÔNG đụng, flow cũ giữ nguyên. Khi Handoff mode: đọc `docs/AI_HANDOFF/RULES.md` để biết 4 phase (Idea+Plan → Create Tasks → Implement+Test → Review+Test) + state machine + self-report model. Config: `.ukit/storage/config.json` → `handoff.*`.
 
 ## Context + Verification Budget
 <!-- RULE: BUDGET-01 -->
@@ -96,14 +102,10 @@ Khi Handoff mode: đọc `docs/AI_HANDOFF/RULES.md` để biết 4 phase (Idea+P
 - `docs/STATUS.md` captures compact current state — not source truth, never replaces source/index-first investigation.
 - "What next?"/"continue" → `next-step` with a freshness cue; after meaningful work → `update-status`. `docs/TASKS.md` is the local AI task queue — prefer `Ready for AI`. Detail: `docs/UKIT_INTERNALS.md`.
 
-## Small-Task Maintainer (internal)
+## Subagent Lanes (internal)
 <!-- RULE: SUBAG-02 -->
 - The `ukit-small-task-maintainer` subagent (`subagents.smallTaskModel`, default `unic-lite`) handles safe/reversible UKit chores as a sidecar lane — never block or slow the user task; risky work hands back to the main model. Detail: `docs/UKIT_INTERNALS.md`.
-
-## Post-Edit Sidecar Review (internal)
 - When routed state's `routeSummary.line` carries `review=code-reviewer(diff)`, launch `code-reviewer` in background (`smart` tier) **only after** write + verification evidence; findings advisory — never block the reported completion. Detail: `docs/UKIT_INTERNALS.md`.
-
-## Selective Subagent Policy (internal only)
 <!-- RULE: SUBAG-01 -->
 - Direct execution is default for trivial/simple work; delegate only on meaningful context shrink or parallel gains (noisy side lanes, 3+ independent failures, batch plans). Never ask end users to name agents or remember agent commands.
 
@@ -111,6 +113,16 @@ Khi Handoff mode: đọc `docs/AI_HANDOFF/RULES.md` để biết 4 phase (Idea+P
 <!-- RULE: AUTO-01 -->
 - `autonomy.level` in `.ukit/storage/config.json` controls how much UKit acts without asking: `conservative` (ask more), `balanced` (default), `free-run` (auto-run more), `vibecode` (one prompt to a finished result; the gate stops only on completion evidence, a genuine blocker, or a dangerous-command decision). End users should not need to change it.
 
+## Unattended Completion Loop
+<!-- RULE: UNATTENDED-01 -->
+- Under `orchestration.permissionMode: unattended` there is no human in the loop — the loop is UNDERSTAND → PLAN → IMPLEMENT → VERIFY → FIX → REVERIFY → COMPLETE. A turn ends only on COMPLETE evidence, a real external blocker, or a deny decision.
+<!-- RULE: UNATTENDED-02 -->
+- `maxAttemptsPerFailure: 5` per failing verification, `maxRecoveryStrategies: 3` distinct fix strategies before reassessing — retry the same edit, fix the cause differently, then reduce scope/approach; do not loop one strategy.
+<!-- RULE: UNATTENDED-03 -->
+- BLOCKED only on true external blockers: missing credentials, dead service, unreachable network/API. Test failures, lint errors, review findings, and ambiguity are NOT blockers — they feed FIX.
+<!-- RULE: UNATTENDED-04 -->
+- A deny (hook/gate/permission) never becomes a question: pick the next safer alternative that satisfies the intent and record the substitution. Never emit "do you want me to…" — decide and proceed.
+
 ## 3-Tier Model Routing
 <!-- RULES: TIER-01 TIER-02 -->
 **Internal orchestration only — end users still just use natural language. No new commands.**
@@ -121,7 +133,7 @@ Khi Handoff mode: đọc `docs/AI_HANDOFF/RULES.md` để biết 4 phase (Idea+P
 | code | `unic-code` | claude-sonnet | Normal coding, local fixes, shared edits, builds, debugging, impact mapping |
 | smart | `unic-smart` | claude-opus | Release review/audit, escalated deep reasoning after repeated failure |
 
-- A tier takes effect only when work is handed to an agent whose definition binds that model (`model:` frontmatter in `.claude/agents/*.md`; `model:` `@lite`/`@code`/`@smart`/`@vision` in `.omp/agents/*.md` via `modelRoles`) — the main session model never changes mid-turn.
+- A tier takes effect only when work is handed to an agent whose definition binds that model (`model:` frontmatter in `.claude/agents/*.md`; `model:` `@smol`/`@default`/`@slow`/`@vision` in `.omp/agents/*.md` via `modelRoles`) — the main session model never changes mid-turn.
 - Contract map: `tiny-fix` → lite · `local-fix`, `local-build`, `shared-edit`, `find-cause`, `map-impact` → code · `review-release` → smart. Escalation: same file/symbol failing `debugLoopThreshold` (default 2) times routes the next attempt one tier higher, capped at `smart`.
 - `unic-vision` is a capability lane, not a cost tier — unverified vision must never guess image contents; route images to `ukit-vision-analyst`. Harness table: `docs/UKIT_INTERNALS.md`.
 

package/templates/instructions/layout.yaml

@@ -14,6 +14,7 @@ outputs:
       - { from: core, heading: Core Rule }
       - { from: core, heading: Fast Classification }
       - { from: core, heading: Execution Contract (mandatory) }
+      - { from: core, heading: Stall & Wait Reporting }
       - { from: core, heading: Long-Run Continuity }
       - { from: core, heading: Index-First Loop }
       - { from: core, heading: Automatic Skill Activation (mandatory) }
@@ -25,10 +26,9 @@ outputs:
       - { from: core, heading: Handoff Quality Gate — OPT-IN }
       - { from: core, heading: Context + Verification Budget }
       - { from: core, heading: Living Status Workflow }
-      - { from: core, heading: Small-Task Maintainer (internal) }
-      - { from: core, heading: Post-Edit Sidecar Review (internal) }
-      - { from: core, heading: Selective Subagent Policy (internal only) }
+      - { from: core, heading: Subagent Lanes (internal) }
       - { from: core, heading: Adaptive Autonomy }
+      - { from: core, heading: Unattended Completion Loop }
       - { from: core, heading: 3-Tier Model Routing }
       - { from: core, heading: Skills }
       - { from: core, heading: Project Snapshot }
@@ -46,6 +46,7 @@ outputs:
       - { from: core, heading: Core Rule }
       - { from: core, heading: Fast Classification }
       - { from: core, heading: Execution Contract (mandatory) }
+      - { from: core, heading: Stall & Wait Reporting }
       - { from: core, heading: Long-Run Continuity }
       - { from: core, heading: Index-First Loop }
       - { from: core, heading: Automatic Skill Activation (mandatory) }
@@ -57,10 +58,9 @@ outputs:
       - { from: core, heading: Handoff Quality Gate — OPT-IN }
       - { from: core, heading: Context + Verification Budget }
       - { from: core, heading: Living Status Workflow }
-      - { from: core, heading: Small-Task Maintainer (internal) }
-      - { from: core, heading: Post-Edit Sidecar Review (internal) }
-      - { from: core, heading: Selective Subagent Policy (internal only) }
+      - { from: core, heading: Subagent Lanes (internal) }
       - { from: core, heading: Adaptive Autonomy }
+      - { from: core, heading: Unattended Completion Loop }
       - { from: core, heading: 3-Tier Model Routing }
       - { from: 'overlay:agents', heading: Session Start — OpenCode }
       - { from: 'overlay:agents', heading: Project Owner Instructions — Codex and OpenCode }
@@ -88,6 +88,7 @@ outputs:
       - { from: core, heading: Core Rule }
       - { from: core, heading: Fast Classification }
       - { from: core, heading: Execution Contract (mandatory) }
+      - { from: core, heading: Stall & Wait Reporting }
       - { from: core, heading: Long-Run Continuity }
       - { from: core, heading: Index-First Loop }
       - { from: core, heading: Automatic Skill Activation (mandatory) }
@@ -99,10 +100,9 @@ outputs:
       - { from: core, heading: Handoff Quality Gate — OPT-IN }
       - { from: core, heading: Context + Verification Budget }
       - { from: core, heading: Living Status Workflow }
-      - { from: core, heading: Small-Task Maintainer (internal) }
-      - { from: core, heading: Post-Edit Sidecar Review (internal) }
-      - { from: core, heading: Selective Subagent Policy (internal only) }
+      - { from: core, heading: Subagent Lanes (internal) }
       - { from: core, heading: Adaptive Autonomy }
+      - { from: core, heading: Unattended Completion Loop }
       - { from: core, heading: 3-Tier Model Routing }
       - { from: core, heading: Skills }
       - { from: core, heading: Project Snapshot }
@@ -121,6 +121,7 @@ outputs:
       - { from: core, heading: Core Rule }
       - { from: core, heading: Fast Classification }
       - { from: core, heading: Execution Contract (mandatory) }
+      - { from: core, heading: Stall & Wait Reporting }
       - { from: core, heading: Long-Run Continuity }
       - { from: core, heading: Index-First Loop }
       - { from: core, heading: Automatic Skill Activation (mandatory) }
@@ -132,10 +133,9 @@ outputs:
       - { from: core, heading: Handoff Quality Gate — OPT-IN }
       - { from: core, heading: Context + Verification Budget }
       - { from: core, heading: Living Status Workflow }
-      - { from: core, heading: Small-Task Maintainer (internal) }
-      - { from: core, heading: Post-Edit Sidecar Review (internal) }
-      - { from: core, heading: Selective Subagent Policy (internal only) }
+      - { from: core, heading: Subagent Lanes (internal) }
       - { from: core, heading: Adaptive Autonomy }
+      - { from: core, heading: Unattended Completion Loop }
       - { from: core, heading: 3-Tier Model Routing }
       - { from: 'overlay:agents', heading: Session Start — OpenCode }
       - { from: 'overlay:agents', heading: Project Owner Instructions — Codex and OpenCode }