oh-my-opencode 5.0.0-beta.9 → 5.0.0

package/packages/omo-codex/plugin/components/telemetry/hooks/hooks.json

@@ -7,7 +7,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook session-start",
 						"timeout": 5,
-						"statusMessage": "(OmO 5.0.0-beta.9) Recording Session Telemetry"
+						"statusMessage": "(OmO 5.0.0) Recording Session Telemetry"
 					}
 				]
 			}

package/packages/omo-codex/plugin/components/telemetry/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@code-yeongyu/codex-telemetry",
-	"version": "5.0.0-beta.9",
+	"version": "5.0.0",
 	"description": "Codex plugin component that emits omo-codex anonymous daily-active telemetry on SessionStart.",
 	"type": "module",
 	"packageManager": "npm@11.12.1",
@@ -43,11 +43,12 @@
 		"check": "tsc --noEmit && biome check . && npm run build"
 	},
 	"devDependencies": {
+		"@vitest/coverage-v8": "5.0.1",
 		"@oh-my-opencode/telemetry-core": "file:../../../../telemetry-core",
-		"@biomejs/biome": "2.4.16",
-		"@types/node": "^25.9.3",
-		"typescript": "^6.0.3",
-		"vitest": "^4.1.8"
+		"@biomejs/biome": "2.5.14",
+		"@types/node": "^26.6.2",
+		"typescript": "^7.0.2",
+		"vitest": "5.0.1"
 	},
 	"engines": {
 		"node": ">=20.0.0"

package/packages/omo-codex/plugin/components/telemetry/src/codex-hook.ts

@@ -1,7 +1,4 @@
-import {
-	type TelemetryDiagnosticErrorKind,
-	type TelemetryDiagnosticEvent,
-} from "@oh-my-opencode/telemetry-core";
+import type { TelemetryDiagnosticErrorKind, TelemetryDiagnosticEvent } from "@oh-my-opencode/telemetry-core";
 import {
 	createPluginPostHog,
 	getPostHogDistinctId,

package/packages/omo-codex/plugin/components/telemetry/src/posthog.ts

@@ -9,10 +9,10 @@ import {
 } from "@oh-my-opencode/telemetry-core";
 
 import {
-	MACHINE_ID_PREFIX,
 	createComponentTelemetryProductConfig,
 	getComponentTelemetryStateDir,
 	getComponentVersion,
+	MACHINE_ID_PREFIX,
 	writeComponentTelemetryDiagnostic,
 } from "./product-identity.js";
 
@@ -53,24 +53,14 @@ function resolveActivityStateProvider(options: CreatePluginPostHogOptions): Acti
 
 	if (options.stateDir === undefined) {
 		return () =>
-			getDailyActiveCaptureState(createDailyActiveCaptureStateInput(
-				getComponentTelemetryStateDir(),
-				options.now,
-			));
+			getDailyActiveCaptureState(createDailyActiveCaptureStateInput(getComponentTelemetryStateDir(), options.now));
 	}
 
 	const stateDir = options.stateDir;
-	return () =>
-		getDailyActiveCaptureState(createDailyActiveCaptureStateInput(
-			stateDir,
-			options.now,
-		));
+	return () => getDailyActiveCaptureState(createDailyActiveCaptureStateInput(stateDir, options.now));
 }
 
-function createDailyActiveCaptureStateInput(
-	stateDir: string,
-	now: Date | undefined,
-) {
+function createDailyActiveCaptureStateInput(stateDir: string, now: Date | undefined) {
 	if (now === undefined) {
 		return {
 			diagnostics: writeComponentTelemetryDiagnostic,

package/packages/omo-codex/plugin/components/telemetry/src/product-identity.ts

@@ -5,9 +5,9 @@ import {
 	DEFAULT_POSTHOG_HOST,
 	getTelemetryDiagnosticsFilePath,
 	resolveTelemetryStateDir,
-	writeTelemetryDiagnostic,
 	type TelemetryDiagnosticInput,
 	type TelemetryProductConfig,
+	writeTelemetryDiagnostic,
 } from "@oh-my-opencode/telemetry-core";
 
 export { DEFAULT_POSTHOG_API_KEY, DEFAULT_POSTHOG_HOST };

package/packages/omo-codex/plugin/components/telemetry/test/diagnostics.test.ts

@@ -1,17 +1,14 @@
 import { existsSync, mkdirSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from "node:fs";
 import { tmpdir } from "node:os";
 import path from "node:path";
+import { cleanupTelemetryDiagnostics } from "@oh-my-opencode/telemetry-core";
 import { afterEach, describe, expect, it } from "vitest";
-
-import {
-	cleanupTelemetryDiagnostics,
-} from "@oh-my-opencode/telemetry-core";
 import {
+	CACHE_DIR_NAME,
 	getComponentTelemetryDiagnosticsFilePath,
 	getComponentTelemetryStateDir,
 	writeComponentTelemetryDiagnostic,
 } from "../src/product-identity.js";
-import { CACHE_DIR_NAME } from "../src/product-identity.js";
 
 const originalXdgDataHome = process.env["XDG_DATA_HOME"];
 const tempDirectories: string[] = [];

package/packages/omo-codex/plugin/components/ultrawork/AGENTS.md

@@ -16,8 +16,9 @@ Conventions for human contributors and AI agents working on this repository.
 - `src/cli.ts`: `UserPromptSubmit` hook CLI. Reads JSON on stdin, writes a compact `<ultrawork-mode>` skill pointer to stdout when the keyword matches (full directive as fallback), exits 0 otherwise.
 - `src/codex-hook.ts`: pure detector/hook behavior; skips on context-pressure/recovery transcripts and when the directive is already in the transcript.
 - `src/skill-pointer.ts`: `buildUltraworkAdditionalContext()`: emits the <4096-byte pointer (Codex App truncates large hook output) directing the model to `create_goal` then read the bundled `ultrawork` skill; falls back to the full `ULTRAWORK_DIRECTIVE` when the plugin skills tree is absent. Pointer size + `ulw-loop` mirror byte-identity pinned by `plugin/test/ultrawork-skill-pointer.test.mjs`.
-- `directive.md`: bundled ultrawork directive text.
-- `skills/ultrawork/SKILL.md`: full directive as a skill, generated by `scripts/sync-directive.mjs`; pinned byte-for-byte to `directive.md` by `test/directive-source.test.ts`. `plugin/scripts/sync-skills.mjs` materializes it into the aggregate `plugin/skills/` tree the pointer path targets.
+- `src/directive-content.ts`: GENERATED bundled directive text (`export const ULTRAWORK_DIRECTIVE_TEXT`). Regenerate via `scripts/sync-directive.mjs`; freshness pinned to the canonical prompt by `test/directive-source.test.ts`. Checked in so a clean checkout builds without running generation.
+- `scripts/sync-directive.mjs`: reads the canonical `packages/prompts-core/prompts/ultrawork/codex.md` and writes two checked-in artifacts: `src/directive-content.ts` and `../ulw-loop/directive.md` (ulw-loop is a separately published standalone package with no prompts-core dependency, so it bundles its own byte-identical copy).
+- Aggregate `ultrawork` skill: `plugin/scripts/sync-skills.mjs` composes `plugin/skills/ultrawork/SKILL.md` by inlining the canonical prompt under skill frontmatter. It reads the canonical file DIRECTLY because `sync-skills` runs before `build-components` in the plugin build chain.
 - `skills/ulw-plan/`: dual-maintained copy of the ulw-plan skill (component copy wins over `packages/shared-skills/skills/ulw-plan/` in sync-skills; keep both in step by hand).
 - `agents/*.toml`: bundled Codex agent role files. Installed as regular files into `CODEX_HOME/agents/` by `src/cli/install-codex/link-cached-plugin-agents.ts` at install time. Public `sisyphuslabs` installs source them from Codex's installed-marketplace snapshot, not the versioned plugin cache, so they survive Codex auto-update cache pruning and temporary snapshot cleanup. No runtime `SessionStart` hook is involved.
 - `hooks/hooks.json`: registers the prompt-detector hook only.
@@ -27,13 +28,18 @@ Conventions for human contributors and AI agents working on this repository.
 
 - Never let the hook block a turn. Exit code is always 0.
 - Never make a network call from the hook.
-- Keep the directive in `directive.md`. Do not inline it into TypeScript files.
+- The canonical directive lives in `packages/prompts-core/prompts/ultrawork/codex.md`. `src/directive-content.ts` is a GENERATED bundled artifact (regenerate via `scripts/sync-directive.mjs`; freshness enforced by `test/directive-source.test.ts`). Do not hand-edit `directive-content.ts`; do not read prompts-core from disk at runtime.
 - Keep bundled agent role prompts concise and model-specific; measure prompt length when changing them.
-- When editing `directive.md`, apply the `prompt-engineering` skill's entropy gate: every edit must reduce uncertainty per token. Re-measure character count before committing.
+- When editing the canonical `packages/prompts-core/prompts/ultrawork/codex.md`, apply the `prompt-engineering` skill's entropy gate: every edit must reduce uncertainty per token. Re-measure character count before committing, and re-run `scripts/sync-directive.mjs` so the generated artifacts stay in step.
 
 ## Commands
 
 ```bash
+# build / test / check (from the component directory)
+npm run build        # sync-directive -> wipe dist -> bun bundle src/cli.ts to dist/cli.js
+npm test             # vitest once (test:watch for watch mode)
+npm run check        # typecheck + biome + build
+
 # smoke test the hook
 PAYLOAD='{"cwd":"/tmp","hook_event_name":"UserPromptSubmit","model":"gpt-5.5","permission_mode":"default","session_id":"x","transcript_path":"","turn_id":"y","prompt":"please ultrawork"}'
 npm run build

package/packages/omo-codex/plugin/components/ultrawork/README.md

@@ -4,12 +4,14 @@ Codex plugin that injects a compact orchestration directive (the **ultrawork** p
 
 Bundled Codex agent role TOMLs in `agents/` are installed into `CODEX_HOME/agents/` by the omo-codex installer (`linkCachedPluginAgents`, in `src/cli/install-codex/link-cached-plugin-agents.ts`). Install-time writes regular file copies on every platform. For the public `sisyphuslabs` marketplace, those files are copied from Codex's local installed-marketplace snapshot so they keep resolving after Codex prunes old plugin-cache versions or temporary marketplace state. There is no runtime Python hook.
 
+All 12 bundled agent TOMLs set `model = "gpt-6-astra"`; each role keeps its own `model_reasoning_effort` (explorer and librarian `low`, the gate reviewer `low`, the code reviewer and `lazycodex-worker-high` `medium`, the rest `high`). When a user has customized an installed agent's effort, the installer keeps that effort while moving the model to `gpt-6-astra` (`src/install/managed-agent-reasoning-defaults.ts`).
+
 ## What the injected directive enforces
 
 | Mandate | Behavior |
 |---|---|
 | Goal + binding success criteria | Call `create_goal` (or open with a `# Goal` block) listing the deliverable + **3+ realistic QA scenarios** (happy path, edge cases, adjacent-surface regression). Each scenario MUST name which **Manual-QA channel** it will use. "Tests pass" is supporting signal, NEVER completion proof. |
-| Manual-QA channels (TESTS ALONE NEVER PROVE DONE) | A dedicated top-level section enumerates the **four** channels you can use to verify a criterion in reality: **(1) HTTP call** (`curl -i` / Playwright APIRequestContext), **(2) tmux** (`tmux new-session` + `send-keys` + `capture-pane`), **(3) Browser use** (in Codex, `browser:control-in-app-browser` first when no authenticated/persistent browser profile is needed; otherwise Playwright / puppeteer / Chromium driving the real page), **(4) Computer use** (OS-level GUI automation against the running app). Every criterion picks one channel, builds a real-usage scenario, runs it, and captures the artifact — every time. Aux surfaces (CLI stdout / DB diff / parsed config) only count for genuinely CLI- or data-shaped criteria. |
+| Manual-QA channels (TESTS ALONE NEVER PROVE DONE) | A dedicated top-level section enumerates the **four** channels you can use to verify a criterion in reality: **(1) HTTP call** (`curl -i` / an HTTP client from js eval), **(2) tmux** (`tmux new-session` + `send-keys` + `capture-pane`), **(3) Browser use** (in Codex, `browser:control-in-app-browser` first when no authenticated/persistent browser profile is needed; otherwise omowright driving the real page — the owned engine for a browser you launch, the attached engine for the user's signed-in browser), **(4) Computer use** (OS-level GUI automation against the running app). Every criterion picks one channel, builds a real-usage scenario, runs it, and captures the artifact — every time. Aux surfaces (CLI stdout / DB diff / parsed config) only count for genuinely CLI- or data-shaped criteria. |
 | Surface + paired cleanup | Execution loop step 4 (**SURFACE-AS-SCENARIO**) runs the chosen channel scenario end-to-end. Step 5 (**CLEANUP, PAIRED**) tears down every QA-spawned process / tmux session / browser context / container / port / temp dir, with a one-line receipt appended to the notepad. Leftover state → NOT done. |
 | Durable /tmp notepad | `mktemp -t ulw-$(date +%Y%m%d-%H%M%S).XXXXXX.md` with sections `Plan`, `Success criteria + QA scenarios`, `Now`, `Todo`, `Findings`, `Learnings`. **Append**, never rewrite. |
 | Obsessive atomic todos | Every action — even one-line edits, `ls`, single test runs — becomes a todo. Format: `path: <action> for <criterion> — verify by <check>`. One in_progress at a time, mark completed immediately. |

package/packages/omo-codex/plugin/components/ultrawork/agents/explorer.toml

@@ -1,7 +1,7 @@
 name = "explorer"
 description = "Codebase search specialist for Codex sessions. Finds files and code in the working tree, returns absolute paths with structured results. Read-only."
 nickname_candidates = ["Explorer"]
-model = "gpt-5.6-luna"
+model = "gpt-6-astra"
 model_reasoning_effort = "low"
 service_tier = "fast"
 

package/packages/omo-codex/plugin/components/ultrawork/agents/lazycodex-clone-fidelity-reviewer.toml

@@ -1,7 +1,7 @@
 name = "lazycodex-clone-fidelity-reviewer"
 description = "Read-only LazyCodex clone / design-system fidelity reviewer. Verifies clone and design-port work is a rigorous, token-driven design system, not a pasted screenshot or hardcoded fake."
 nickname_candidates = ["Clone Fidelity Reviewer"]
-model = "gpt-5.6-terra"
+model = "gpt-6-astra"
 model_reasoning_effort = "high"
 
 developer_instructions = """

package/packages/omo-codex/plugin/components/ultrawork/agents/lazycodex-code-reviewer.toml

@@ -1,7 +1,7 @@
 name = "lazycodex-code-reviewer"
 description = "Read-only LazyCodex code-quality reviewer. Audits diffs, tests, and risk with strict artifact-backed findings."
 nickname_candidates = ["Code Reviewer"]
-model = "gpt-5.6-terra"
+model = "gpt-6-astra"
 model_reasoning_effort = "medium"
 
 developer_instructions = """

package/packages/omo-codex/plugin/components/ultrawork/agents/lazycodex-gate-reviewer.toml

@@ -1,7 +1,7 @@
 name = "lazycodex-gate-reviewer"
 description = "Read-only LazyCodex gate reviewer. Re-audits executor, code review, and QA artifacts before final approval."
 nickname_candidates = ["Gate Reviewer"]
-model = "gpt-5.6-sol"
+model = "gpt-6-astra"
 model_reasoning_effort = "low"
 
 developer_instructions = """

package/packages/omo-codex/plugin/components/ultrawork/agents/lazycodex-qa-executor.toml

@@ -1,7 +1,7 @@
 name = "lazycodex-qa-executor"
 description = "LazyCodex manual QA executor. Runs real scenarios and records artifact-backed surface evidence."
 nickname_candidates = ["QA Executor"]
-model = "gpt-5.6-luna"
+model = "gpt-6-astra"
 model_reasoning_effort = "high"
 
 developer_instructions = """

package/packages/omo-codex/plugin/components/ultrawork/agents/lazycodex-worker-high.toml

@@ -1,7 +1,7 @@
 name = "lazycodex-worker-high"
 description = "LazyCodex high-difficulty implementation worker, sized for LARGE changes: a new module or abstraction, a cross-module refactor, concurrency/security/migration work, or any real, complex, big problem that has ONE clear goal. Owns the smallest correct change and records evidence before claiming completion."
 nickname_candidates = ["High Worker"]
-model = "gpt-5.6-sol"
+model = "gpt-6-astra"
 model_reasoning_effort = "medium"
 
 developer_instructions = """

package/packages/omo-codex/plugin/components/ultrawork/agents/lazycodex-worker-low.toml

@@ -1,7 +1,7 @@
 name = "lazycodex-worker-low"
 description = "LazyCodex low-difficulty implementation worker, sized for SMALL changes: single-spot fixes, boilerplate, config/copy changes, and pattern-following edits confined to one file. Owns the smallest correct change and records evidence before claiming completion."
 nickname_candidates = ["Low Worker"]
-model = "gpt-5.6-luna"
+model = "gpt-6-astra"
 model_reasoning_effort = "high"
 
 developer_instructions = """

package/packages/omo-codex/plugin/components/ultrawork/agents/lazycodex-worker-medium.toml

@@ -1,7 +1,7 @@
 name = "lazycodex-worker-medium"
 description = "LazyCodex medium-difficulty implementation worker, sized for MID-SIZED changes: a standard feature inside existing layers, touching a few files along established patterns. Owns the smallest correct change and records evidence before claiming completion."
 nickname_candidates = ["Medium Worker"]
-model = "gpt-5.6-terra"
+model = "gpt-6-astra"
 model_reasoning_effort = "high"
 
 developer_instructions = """

package/packages/omo-codex/plugin/components/ultrawork/agents/librarian.toml

@@ -1,7 +1,7 @@
 name = "librarian"
 description = "External open-source codebase and documentation researcher. Investigates libraries via gh CLI, web search, and webfetch, returning SHA-pinned GitHub permalink citations. Read-only."
 nickname_candidates = ["Librarian"]
-model = "gpt-5.6-luna"
+model = "gpt-6-astra"
 model_reasoning_effort = "low"
 service_tier = "fast"
 

package/packages/omo-codex/plugin/components/ultrawork/agents/metis.toml

@@ -1,7 +1,7 @@
 name = "metis"
 description = "Pre-planning analyst. Detects contradictions, ambiguity, missing constraints, and execution risks in a draft plan or request before the planner commits. Read-only."
 nickname_candidates = ["Analyst"]
-model = "gpt-5.6-sol"
+model = "gpt-6-astra"
 model_reasoning_effort = "high"
 
 developer_instructions = """

package/packages/omo-codex/plugin/components/ultrawork/agents/momus.toml

@@ -1,7 +1,7 @@
 name = "momus"
 description = "Deep plan reviewer. Verifies a work plan is executable: references exist, tasks are startable, QA scenarios are concrete. Runs at High and may take a long time; callers must wait for its terminal result instead of cancelling or duplicating it. Issues OKAY, ITERATE, or REJECT. Read-only."
 nickname_candidates = ["Reviewer"]
-model = "gpt-5.6-terra"
+model = "gpt-6-astra"
 model_reasoning_effort = "high"
 
 developer_instructions = """

package/packages/omo-codex/plugin/components/ultrawork/agents/plan.toml

@@ -1,7 +1,7 @@
 name = "plan"
 description = "Strategic planning consultant for work with unresolved design uncertainty after discovery. Produces one executable plan; never implements. Writes the plan to .omo/plans/<slug>.md."
 nickname_candidates = ["Planner"]
-model = "gpt-5.6-sol"
+model = "gpt-6-astra"
 model_reasoning_effort = "high"
 
 developer_instructions = """
@@ -11,7 +11,7 @@ Role: strategic planning consultant. You produce a single, bulletproof, executab
 You ARE the planner. You ARE NOT an implementer. You read, search, run read-only analysis, and write exactly ONE plan file - never source code, never product builds, never the actual feature. When the caller says "do X / fix X / build X", interpret it as "create a work plan for X". If the caller explicitly demands implementation, REFUSE and answer: "I'm a planner. I produce the work plan. Spawn a worker agent or execute the plan yourself to implement."
 
 # Goal
-Deliver ONE executable plan that a downstream executor can follow with no further interview. Every task is atomic, with explicit references, agent-executable acceptance criteria, QA scenarios, and a commit instruction. I fit work whose design remains open after discovery: ambiguous scope, competing decompositions, unclear boundaries, or uncertain dependency ordering. I am the wrong tool for a known checklist however many steps it has, for work the caller is delegating to another session, for a single-file edit with an obvious pattern, or when the caller already has a plan and just wants execution - say so instead of planning.
+Deliver ONE executable plan that reaches the ideal state for the affected user and that a downstream executor can follow with no further interview. Before drafting, name who the result touches (a customer, another programmer, a program or agent consuming it), how they use it today and after, the state in which nothing snags, regresses, or degrades for them (IS rows, each with a reason), and every gap from today (GAP rows, each with a reason); every task closes a GAP row and `## Success criteria` proves every IS row. "MVP" / "phase 1" subsets are never invented; when the ideal state exceeds the literal request, say so in one line and plan the ideal state. Every task is atomic, with explicit references, agent-executable acceptance criteria, QA scenarios, and a commit instruction. I fit work whose design remains open after discovery: ambiguous scope, competing decompositions, unclear boundaries, or uncertain dependency ordering. I am the wrong tool for a known checklist however many steps it has, for work the caller is delegating to another session, for a single-file edit with an obvious pattern, or when the caller already has a plan and just wants execution - say so instead of planning.
 
 # Phase 1 - Context gathering (MANDATORY - never plan blind)
 Fire parallel research BEFORE drafting:
@@ -31,11 +31,20 @@ Write ONE plan to `.omo/plans/<slug>.md` (create the directory if absent). No "P
 
 ## TL;DR
 > Summary:      <1-2 sentences>
+> For whom:     <the affected user and what changes for them>
 > Deliverables: <bullet list>
-> Effort:       <Quick | Short | Medium | Large | XL>
+> Effort:       <Quick | Short | Medium | Large | XL>  (one band, never hours/days: Quick = single edit, minutes of agent work; Short = one focused change, a few files; Medium = multi-file feature in one session; Large = several waves, one long session; XL = multi-session or architectural work)
 > Risk:         <Low | Medium | High> - <one-line driver>
 
 ## Scope
+### Affected user and ideal state
+**Affected user:** <who, and how they use it today and after>
+
+| Row | Statement | Reason |
+|-----|-----------|--------|
+| IS-1 | <what the user does, sees, or never has break> | <why this is the ideal for them> |
+| GAP-1 | <how today differs from IS-1> | <why it matters to them> |
+
 ### Must have
 - ...
 
@@ -81,6 +90,7 @@ Critical path: Task 1 -> Task 2 -> Task 6
 
   What to do: <clear implementation steps>
   Must NOT do: <explicit exclusions>
+  Closes: GAP-<n>
 
   Parallelization: Can parallel: <YES|NO> | Wave <N> | Blocks: [<tasks>] | Blocked by: [<tasks>]
 
@@ -94,10 +104,10 @@ Critical path: Task 1 -> Task 2 -> Task 6
   - [ ] <verifiable condition with the exact command or assertion>
 
   QA scenarios (MANDATORY - task incomplete without these):
-  > Name the exact tool AND its exact invocation - not "verify it works". Browser use: in Codex, use `browser:control-in-app-browser` first when available and no authenticated/persistent user browser profile is required; otherwise use Chrome to drive the page, or agent-browser (https://github.com/vercel-labs/agent-browser) when Chrome is unavailable. Computer use: OS-level GUI automation for a non-browser desktop app.
+  > Name the exact tool AND its exact invocation - not "verify it works". Browser use: in Codex, prefer `browser:control-in-app-browser`; otherwise omowright from js eval (staged in the `browser` skill) — `connectPipe`/`connectCloakProfile` for a browser you own, `connectBrowserSkill()` for the user's signed-in browser; never a clone of the live profile. Computer use: OS-level GUI automation for a non-browser desktop app.
   ```
   Scenario: <happy path>
-    Tool:     <bash | curl | tmux | browser:control-in-app-browser | playwright(real Chrome) | agent-browser | computer-use>
+    Tool:     <bash | curl | tmux | browser:control-in-app-browser | omowright(js eval; owned or attached engine) | computer-use>
     Steps:    <exact command / API call / page action with concrete inputs - URL, payload, keystrokes, selectors>
     Expected: <concrete, binary pass/fail observable>
     Evidence: <attemptDir>/task-<N>-<slug>.<ext>   (attemptDir = currentAttemptDir from `omo-agent-toolkit ulw-loop status --json`, .omo/evidence/ulw/<session>/<goalId>/a<attempt>)
@@ -116,7 +126,7 @@ Critical path: Task 1 -> Task 2 -> Task 6
 - [ ] F1. Plan compliance audit - every task done, every acceptance criterion met
 - [ ] F2. Code quality review - diagnostics clean, idioms match, no dead code
 - [ ] F3. Real manual QA - every QA scenario executed with evidence captured
-- [ ] F4. Scope fidelity - nothing extra shipped beyond Must-Have, nothing Must-NOT-Have introduced
+- [ ] F4. Ideal-state fidelity - delivered behavior checked against every IS row 1:1; a shortfall becomes new task rows, never a note; nothing Must-NOT-Have introduced
 
 ## Commit strategy
 - One logical change per commit. Conventional Commits (`<type>(<scope>): <subject>` body + footer).
@@ -125,7 +135,10 @@ Critical path: Task 1 -> Task 2 -> Task 6
 - Reference the plan file path in the final commit footer: `Plan: .omo/plans/<slug>.md`.
 
 ## Success criteria
-- All Must-Have shipped; all QA scenarios pass with captured evidence; F1-F4 approved; commit history clean.
+| IS | Delivering task(s) | Proving QA scenario | Evidence |
+|----|--------------------|---------------------|----------|
+| IS-1 | <N> | <scenario name from task N> | <attemptDir>/task-<N>-<slug>.<ext> |
+- Every IS row above has a delivering task and a proving scenario; all QA scenarios pass with captured evidence; F1-F4 approved; commit history clean.
 ```
 
 # Constraints

package/packages/omo-codex/plugin/components/ultrawork/biome.json

@@ -1,9 +1,9 @@
 {
-	"$schema": "https://biomejs.dev/schemas/2.4.16/schema.json",
+	"$schema": "https://biomejs.dev/schemas/2.5.9/schema.json",
 	"linter": {
 		"enabled": true,
 		"rules": {
-			"recommended": true,
+			"preset": "recommended",
 			"style": {
 				"noDefaultExport": "error",
 				"noEnum": "error",