oh-my-opencode 5.0.0-beta.8 → 5.0.0-beta.9

package/packages/shared-skills/skills/ultimate-browsing/engine/AGENTS.md

@@ -2,6 +2,116 @@
 
 **Generated:** 2026-08-10 / 38d268995
 
+## UPSTREAM BASELINE AND VERSION POLICY
+
+**READ THIS BEFORE TOUCHING `engine/**` OR PROPOSING AN UPSTREAM SYNC.**
+
+This engine is NOT project-original code. It is a vendored-and-modified snapshot of
+[fivetaku/insane-search](https://github.com/fivetaku/insane-search), and the version
+we run on is a deliberate choice, not an accident of neglect.
+
+### The pin
+
+| Fact | Value |
+|---|---|
+| Upstream project | `https://github.com/fivetaku/insane-search` |
+| Vendoring commit | `a4e4ed797` (2026-06-21) `feat(ultimate-browsing): vendor insane-search engine (junk-excluded)` |
+| De-personalization | `4743199a5` (2026-06-21) |
+| Pinned upstream baseline | upstream state as of 2026-06-21, **pre-0.7.0** (0.7.0 is dated 2026-06-22) |
+| Re-vendors since | none — every later change here is ours |
+
+We intentionally track a **pinned baseline plus local divergence**, not upstream HEAD.
+There is no submodule and no automated drift check for this engine (unlike the
+`frontend` skill's upstream submodules): the vendored files ARE the source of truth,
+and upstream is a reference we port FROM, deliberately, file by file.
+
+### Why we do not blind-rebase onto upstream HEAD
+
+1. **Upstream reset its public history.** On 2026-08-06 upstream published a single
+   squashed commit, `019ee16 refactor: reset public history at 0.14.0`, discarding the
+   prior public history through 0.13.x. There is no upstream commit graph to rebase onto and no
+   way to cherry-pick an individual upstream change by sha — only whole-file diffing
+   against a moving HEAD.
+2. **Upstream 0.14.0 REMOVED capability.** The endpoint-mining / internal-API
+   auto-derivation / site-recipe subsystems that upstream carried publicly between
+   0.12.0 and 0.14.0 are gone from upstream HEAD. Syncing to HEAD is therefore not
+   strictly an upgrade: parts of it are a downgrade relative to the intermediate
+   versions, and none of it is recoverable from the reset history.
+3. **Our tree diverged on purpose.** The KEEP list below is functionality upstream
+   never had. A wholesale overwrite with upstream HEAD would silently delete it.
+4. **Different threat model.** Our engine ships inside a published npm package and a
+   public marketplace mirror, under a CI no-site-name gate and a de-personalization
+   deny-list. Upstream carries neither constraint, so upstream code is not
+   drop-in-shippable here.
+
+### KEEP — our divergences a re-vendor MUST NOT regress
+
+These exist only in our tree. Any upstream sync that removes or bypasses one of them
+is a regression, not an upgrade:
+
+- **Phase 2.5 surrogate retrieval** (`surrogate.py`, `surrogates.yaml`) — archive /
+  reader / proxy routes tried before paying for a browser spin-up, with per-entry
+  `last_verified` staleness handling and `--allow-proxy` gating.
+- **Provenance / trust contract** (`result_schema.py`) — `Provenance` and `Trust`
+  literals on every result, so a snapshot can never be reported as the live page.
+- **Surrogate dead-end validation** (L1.5 in `validators.py`) — interstitial titles and
+  AMP-style redirect stubs rejected instead of returned as content.
+- **The no-site-name rule and its CI gate** (`bias_check.py`) — zero hard-coded site
+  names, brands, or target domains in `engine/**`.
+- **Module split of the fetch chain** — `curl_probe` / `referers` / `url_transforms` /
+  `waf_detector` / `validators` / `executor` / `summary` as separate modules rather than
+  one monolith.
+- **The Python test suite** under `engine/tests/` with its HTML/JSON fixtures.
+- **De-personalization** — no personal absolute paths, no personal auth token literals,
+  no personal browser choice; enforced by `depersonalization-gate.test.ts`.
+- **Skill-level layering** — the engine is Tier 1 under a router that also owns Tier 1.5
+  (agent-reach) and Tier 2 (CloakBrowser + agent-browser). Upstream has no such tiering.
+
+### WANT — upstream improvements worth porting forward
+
+Our snapshot predates these; they are wanted, and each must be ported as a reviewed,
+site-agnostic change that preserves every KEEP item above. Port individually; never as
+a tree overwrite:
+
+- **Content quality**: dedicated markdown conversion of fetched HTML, main-content
+  extraction, PDF text extraction, and JSON-LD rescue when the HTML body is thin.
+- **Transient-failure retry** and **render-merge** of statically fetched HTML with the
+  browser-rendered DOM.
+- **Differential block classification** — distinguishing a bot-detection block from an
+  infrastructure or authentication failure, instead of collapsing both into `challenge`.
+- **Additional stealth fetch backends** beyond the current Playwright templates, and
+  additional WAF vendor profiles.
+- **Per-host route learning** — remembering which route succeeded for a host, with a TTL
+  and a bounded store. Must stay runtime state, never committed site knowledge (R4).
+- **Engine-level Phase 0 routing** — the official-public-API preference is currently only
+  a documented rule (R5) the agent can skip; upstream moved it into code so it cannot be
+  skipped. Worth adopting.
+
+### OUT OF SCOPE
+
+- **The removed upstream endpoint-mining / internal-API auto-derivation / site-recipe
+  subsystems.** They are absent from upstream HEAD and are not reconstructed here. They
+  also sit against R3/R4 and R7's anti-bias rule: discovered internal endpoints are
+  runtime findings, never committed engine knowledge.
+- **Any upstream code carrying site-specific selectors, domains, or brand names.** It
+  fails `bias_check.py` at the door; re-derive it site-agnostically or leave it out.
+- **Automated upstream tracking.** No submodule, no drift check, no auto-bump. Syncing is
+  a deliberate, reviewed, human-initiated act.
+
+### THE SYNC RULE
+
+Any future upstream sync preserves BOTH sides. Concretely:
+
+1. Diff the specific upstream capability you want against our tree — do not overwrite
+   files wholesale, and never `git checkout` upstream over `engine/`.
+2. Port it as its own reviewed change, keeping every KEEP item intact.
+3. Re-run `python3 engine/bias_check.py` and the `engine/tests/` suite; a port that
+   introduces a site name or breaks a fixture does not ship.
+4. Update the pin table above (baseline, date, what was ported) in the same change, plus
+   the provenance section of [`../ATTRIBUTION.md`](../ATTRIBUTION.md).
+5. If a port must drop a KEEP item, say so explicitly in the PR and get it agreed first —
+   silent regressions of the KEEP list are the failure mode this policy exists to prevent.
+
 ## OVERVIEW
 
 A 17-module Python package embedded in the `ultimate-browsing` skill: a site-agnostic fetch chain that escalates from a cheap curl probe to a real browser, with declarative WAF and surrogate registries. Not "optional scripts" — it has its own CLI entry (`python3 -m engine URL`), two YAML config schemas, a 4-file test suite, and a standalone CI guard. Package exports (`__init__.py`): `fetch`, `FetchResult`, `Attempt`, `Verdict`, `ValidationResult`, `validate`, `CHALLENGE_MARKERS`, `detect`, `TRANSFORMS`, `apply_transform`.

package/dist/tools/call-omo-agent/background-agent-executor.d.ts

@@ -1,5 +0,0 @@
-import type { BackgroundManager } from "../../features/background-agent";
-import type { PluginInput } from "@opencode-ai/plugin";
-import type { CallOmoAgentArgs } from "./types";
-import type { ToolContextWithMetadata } from "./tool-context-with-metadata";
-export declare function executeBackgroundAgent(args: CallOmoAgentArgs, toolContext: ToolContextWithMetadata, manager: BackgroundManager, client: PluginInput["client"]): Promise<string>;

package/packages/omo-codex/plugin/test/aggregate-skills.test.mjs

@@ -1,92 +0,0 @@
-import assert from "node:assert/strict";
-import { readdir, readFile, stat } from "node:fs/promises";
-import { basename, dirname, join } from "node:path";
-import test from "node:test";
-
-import {
-	findInvalidSpawnAgentRoleParameters,
-	findSpawnAgentCallsWithoutForkContextFalse,
-	root,
-} from "./aggregate-plugin-fixture.mjs";
-import { listSkillFiles } from "./sync-skills-test-support.mjs";
-
-test("#given synced skills with Codex compatibility guidance #when spawn_agent is documented #then invalid role parameters are absent", async () => {
-	const skillsDir = join(root, "skills");
-	const skillEntries = await readdir(skillsDir, { withFileTypes: true });
-	const skillFiles = skillEntries
-		.filter((entry) => entry.isDirectory())
-		.map((entry) => join(skillsDir, entry.name, "SKILL.md"));
-
-	const invalidCalls = [];
-	for (const skillPath of skillFiles) {
-		const content = await readFile(skillPath, "utf8");
-		for (const call of findInvalidSpawnAgentRoleParameters(content)) {
-			invalidCalls.push(`${basename(dirname(skillPath))}/${basename(skillPath)}: ${call}`);
-		}
-	}
-
-	assert.deepEqual(invalidCalls, []);
-});
-
-test('#given synced skills and bundled rules #when role-specific agents are spawned #then they set fork_context=false', async () => {
-	const skillsDir = join(root, "skills");
-	const skillEntries = await readdir(skillsDir, { withFileTypes: true });
-	const promptFiles = skillEntries
-		.filter((entry) => entry.isDirectory())
-		.map((entry) => join(skillsDir, entry.name, "SKILL.md"));
-	promptFiles.push(join(root, "components", "rules", "bundled-rules", "hephaestus", "gpt-5.5.md"));
-	promptFiles.push(join(root, "components", "rules", "bundled-rules", "hephaestus", "gpt-5.6.md"));
-
-	const missingForkContext = [];
-	for (const promptPath of promptFiles) {
-		const content = await readFile(promptPath, "utf8");
-		for (const call of findSpawnAgentCallsWithoutForkContextFalse(content)) {
-			missingForkContext.push(`${basename(dirname(promptPath))}/${basename(promptPath)}: ${call}`);
-		}
-	}
-
-	assert.deepEqual(missingForkContext, []);
-});
-
-test("#given long-running orchestration prompts #when waiting on child agents #then parent liveness is surfaced", async () => {
-	const promptFiles = [
-		join(root, "skills", "ulw-loop", "SKILL.md"),
-		join(root, "skills", "ulw-loop", "references", "full-workflow.md"),
-		join(root, "skills", "review-work", "SKILL.md"),
-		join(root, "skills", "start-work", "SKILL.md"),
-		join(root, "components", "rules", "bundled-rules", "hephaestus", "gpt-5.5.md"),
-		join(root, "components", "rules", "bundled-rules", "hephaestus", "gpt-5.6.md"),
-	];
-
-	const missingLivenessGuidance = [];
-	for (const promptPath of promptFiles) {
-		const content = await readFile(promptPath, "utf8");
-		if (!/active\s+subagent count/.test(content) || !/latest `WORKING:` phase/.test(content)) {
-			missingLivenessGuidance.push(`${basename(dirname(promptPath))}/${basename(promptPath)}`);
-		}
-	}
-
-	assert.deepEqual(missingLivenessGuidance, []);
-});
-
-test("#given packaged Codex prompt surfaces #when inspected #then removed sparkshell guidance is absent", async () => {
-	const promptRoots = [
-		join(root, "skills"),
-		join(root, "components", "rules", "bundled-rules"),
-		join(root, "components", "ultrawork", "agents"),
-		join(root, "components", "ulw-loop", "skills"),
-	];
-	const promptFilePattern = /\.(?:json|md|toml|ya?ml)$/i;
-	const removedSparkshellPattern = /\b(?:sparkshell|spark[-_\s]+shell)\b/i;
-	const matches = [];
-
-	for (const promptRoot of promptRoots) {
-		for (const relativePath of await listSkillFiles(promptRoot)) {
-			if (!promptFilePattern.test(relativePath)) continue;
-			const content = await readFile(join(promptRoot, relativePath), "utf8");
-			if (removedSparkshellPattern.test(content)) matches.push(`${promptRoot}/${relativePath}`);
-		}
-	}
-
-	assert.deepEqual(matches, []);
-});

package/packages/omo-codex/plugin/test/sync-skills-orchestration.test.mjs

@@ -1,314 +0,0 @@
-import assert from "node:assert/strict";
-import { readdir, readFile } from "node:fs/promises";
-import { dirname, join } from "node:path";
-import test from "node:test";
-import { fileURLToPath } from "node:url";
-import { codexHarnessToolCompatibility, insertCodexCompatibilityGuidance } from "../scripts/sync-skills.mjs";
-
-const root = dirname(dirname(fileURLToPath(import.meta.url)));
-
-async function listSkillNames() {
-	const skillsRoot = join(root, "skills");
-	const entries = await readdir(skillsRoot, { withFileTypes: true });
-	return entries
-		.filter((entry) => entry.isDirectory())
-		.map((entry) => entry.name)
-		.sort();
-}
-
-async function readSkill(skillName) {
-	return readFile(join(root, "skills", skillName, "SKILL.md"), "utf8");
-}
-
-async function readSharedSkill(skillName) {
-	return readFile(join(root, "../../shared-skills/skills", skillName, "SKILL.md"), "utf8");
-}
-
-function patternFromParts(parts, flags) {
-	return new RegExp(parts.join(""), flags);
-}
-
-const multiAgentV2RoleGuidance =
-	"If instead a flat `spawn_agent` with a required `task_name` exists (`multi_agent_v2`), rewrite every `multi_agent_v1.*` example:";
-const loadSkillsGuidance =
-	"When translating `load_skills=[...]`, include the requested skill names in the spawned agent's `message`.";
-
-test("#given synced aggregate Codex skills #when they contain OpenCode orchestration examples #then Codex tool compatibility guidance is injected", async () => {
-	// given
-	const opencodeOnlyToolPattern = /\b(?:call_omo_agent|background_output|team_[a-z_]+|task)\s*\(/;
-
-	// when / then
-	for (const skillName of await listSkillNames()) {
-		const content = await readSkill(skillName);
-		if (!opencodeOnlyToolPattern.test(content)) continue;
-
-		const compatibilityMatches = content.match(/## Codex Harness Tool Compatibility/g) ?? [];
-		const compatibilityIndex = content.indexOf("## Codex Harness Tool Compatibility");
-		assert.notEqual(compatibilityIndex, -1, `${skillName} is missing Codex compatibility guidance`);
-		assert.equal(compatibilityMatches.length, 1, `${skillName} must not duplicate Codex compatibility guidance`);
-		assert.ok(
-			compatibilityIndex < content.search(opencodeOnlyToolPattern),
-			`${skillName} must explain Codex tool translation before OpenCode-only examples`,
-		);
-		assert.ok(content.includes(multiAgentV2RoleGuidance), `${skillName} missing multi_agent_v2 role guidance`);
-		assert.ok(content.includes(loadSkillsGuidance), `${skillName} missing load_skills guidance`);
-	}
-});
-
-test("#given late variant Codex compatibility guidance #when adapting a skill #then it is moved without duplication", () => {
-	// given
-	const content = `---
-name: example
----
-
-# Example Skill
-
-call_omo_agent(subagent_type="explore", prompt="inspect")
-
-## Codex Harness Tool Compatibility
-
-Older variant guidance.
-
-When translating \`load_skills=[...]\`, name the skills inside the spawned agent's \`message\`. If a code block below conflicts with this section, this section wins.
-
----
-
-## Next Section
-
-task(category="quick", prompt="verify")
-`;
-
-	// when
-	const adapted = insertCodexCompatibilityGuidance(content);
-
-	// then
-	const compatibilityIndex = adapted.indexOf("## Codex Harness Tool Compatibility");
-	const firstToolIndex = adapted.search(/\b(?:call_omo_agent|task)\s*\(/);
-	assert.notEqual(compatibilityIndex, -1);
-	assert.ok(compatibilityIndex < firstToolIndex);
-	assert.equal(adapted.match(/## Codex Harness Tool Compatibility/g)?.length, 1);
-	assert.doesNotMatch(adapted, /Older variant guidance/);
-	assert.doesNotMatch(adapted, /name the skills inside the spawned agent's `message`/);
-	assert.match(adapted, /\n---\n\n## Next Section/);
-});
-
-test("#given early custom Codex compatibility guidance #when adapting a skill #then it is preserved exactly", () => {
-	// given
-	const content = `---
-name: example
----
-
-## Codex Harness Tool Compatibility
-
-Custom guidance for this skill, including \`dispatchInternalPrompt(...)\`.
-
-# Example Skill
-
-call_omo_agent(subagent_type="explore", prompt="inspect")
-`;
-
-	// when
-	const adapted = insertCodexCompatibilityGuidance(content);
-
-	// then
-	assert.equal(adapted, content);
-});
-
-test("#given early generated stale Codex compatibility guidance #when adapting a skill #then it is replaced", () => {
-	// given
-	const content = `---
-name: example
----
-
-## Codex Harness Tool Compatibility
-
-This skill may include examples copied from the OpenCode harness. In Codex, do not call OpenCode-only tools such as \`call_omo_agent(...)\`, \`task(...)\`, \`background_output(...)\`, or \`team_*(...)\` literally. Translate those examples to Codex native tools:
-
-| OpenCode example | Codex tool to use |
-| --- | --- |
-| \`call_omo_agent(subagent_type="explore", ...)\` | \`spawn_agent({"task_name":"...","message":"TASK: act as an explorer. ..."})\` |
-| \`background_output(task_id="...")\` | \`wait_agent(...)\` for mailbox signals |
-
-Obsolete generated compatibility prose.
-
-More obsolete generated compatibility prose.
-
-When translating \`load_skills=[...]\`, include the requested skill names in the spawned agent's \`message\`. If a code block below conflicts with this section, this section wins.
-
-# Example Skill
-
-call_omo_agent(subagent_type="explore", prompt="inspect")
-`;
-
-	// when
-	const adapted = insertCodexCompatibilityGuidance(content);
-
-	// then
-	assert.match(adapted, /multi_agent_v1\.spawn_agent/);
-	assert.match(adapted, /fork_context":false/);
-	assert.match(adapted, /"agent_type":"explorer"/);
-	assert.match(adapted, /multi_agent_v1\.wait_agent/);
-	assert.match(adapted, /"task_name":"<lowercase_digits_underscores>"/);
-	assert.match(adapted, /fork_turns/);
-	assert.doesNotMatch(adapted, /\| `spawn_agent\({"task_name"/);
-	assert.doesNotMatch(adapted, /Obsolete generated compatibility prose/);
-});
-
-test("#given generated Codex compatibility guidance #when adapting a skill #then multi-agent role and load_skills guidance are both present", () => {
-	// given
-	const content = `---
-name: example
----
-
-# Example Skill
-
-task(subagent_type="oracle", load_skills=["debugging"], prompt="verify")
-`;
-
-	// when
-	const adapted = insertCodexCompatibilityGuidance(content);
-
-	// then
-	assert.ok(adapted.includes(multiAgentV2RoleGuidance));
-	assert.ok(adapted.includes(loadSkillsGuidance));
-});
-
-test("#given generated guidance before a template export #when adapting a skill #then the export wrapper is preserved", () => {
-	// given
-	const content = `---
-name: refactor
----
-
-## Codex Harness Tool Compatibility
-
-Older variant guidance.
-
-When translating \`load_skills=[...]\`, name the skills inside the spawned agent's \`message\`. If a code block below conflicts with this section, this section wins.
-
-export const REFACTOR_TEMPLATE = \`# Refactor
-
-call_omo_agent(subagent_type="explore", prompt="inspect")
-\`
-`;
-
-	// when
-	const adapted = insertCodexCompatibilityGuidance(content);
-
-	// then
-	assert.match(adapted, /export const REFACTOR_TEMPLATE = `# Refactor/);
-	assert.match(adapted, /multi_agent_v1\.spawn_agent/);
-	assert.doesNotMatch(adapted, /Older variant guidance/);
-});
-
-test("#given synced aggregate Codex skills #when they describe background orchestration #then liveness is framed as progress rather than timeout failure", async () => {
-	// given
-	const orchestrationPattern = /\b(?:run_in_background|background_output|wait_agent)\b/;
-	const requiredPatterns = [
-		["working progress message", /WORKING:/],
-		["blocked progress message", /BLOCKED:/],
-		["mailbox timeout framing", /timeout only means no new mailbox update arrived/],
-		// Skills route by session tool surface: the namespaced V1 tool or the flat V2 tool both count.
-		["wait-agent tool ref", /multi_agent_v1\.wait_agent|`wait_agent`/],
-		["explicit fallback conditions", /Fallback only when|Mark a file for retry only when/],
-	];
-	const bannedPatterns = [
-		["timeout as failure", patternFromParts(["fails or ", "times out"], "i")],
-		["failed or timed out", patternFromParts(["failed or ", "timed out"], "i")],
-		["two waits heuristic", patternFromParts(["After two ", "waits"])],
-		["unresponsive timeout framing", patternFromParts(["timeout", ".*", "un" + "responsive"], "i")],
-		["old status-tool warning", patternFromParts(["polling or ", "status tool"])],
-		["large status replay wording", patternFromParts(["large agent status", " and latest-message"])],
-		["old wait-agent aphorism", patternFromParts(["wait_agent", ".*", "signal, not ", "proof"], "i")],
-	];
-
-	// when / then
-	for (const skillName of await listSkillNames()) {
-		const content = await readSkill(skillName);
-		if (!orchestrationPattern.test(content)) continue;
-
-		for (const [label, pattern] of requiredPatterns) {
-			assert.match(content, pattern, `${skillName} missing ${label}`);
-		}
-		for (const [label, pattern] of bannedPatterns) {
-			assert.doesNotMatch(content, pattern, `${skillName} still has ${label}`);
-		}
-	}
-});
-
-test("#given packaged start-work and ulw-plan skills #when inspected #then PR delivery options and the handoff explanation ship", async () => {
-	// given
-	const startWork = await readSkill("start-work");
-	const workflow = await readFile(join(root, "skills", "ulw-plan", "references", "full-workflow.md"), "utf8");
-
-	// when / then
-	assert.match(startWork, /--make-pr/);
-	assert.match(startWork, /--ship/);
-	assert.match(startWork, /implies `--make-pr`/i);
-	assert.match(startWork, /IMPLIES worktree mode/i);
-	assert.match(startWork, /Goal and todo discipline/i);
-	assert.match(startWork, /create_goal/);
-	assert.match(startWork, /one todo per column-zero checkbox/i);
-
-	assert.match(workflow, /Handoff explanation/i);
-	assert.match(workflow, /Added beyond the request/i);
-	assert.match(workflow, /\$start-work <plan-name>/);
-	assert.match(workflow, /--make-pr/);
-	assert.match(workflow, /--ship/);
-	assert.match(workflow, /COUNT the rows/i);
-});
-
-test("#given start-work skill #when synced for Codex #then the difficulty-tier delegation guidance survives the overlay", async () => {
-	const content = await readSkill("start-work");
-
-	assert.match(content, /lazycodex-worker-medium/);
-	assert.match(content, /Codex tier mapping for the delegation router/);
-	assert.match(content, /Global Review and Debugging Gate/);
-	assert.match(content, /full commit SHA/);
-	assert.match(content, /re-read the ledger record/);
-	assert.match(content, /exact lane\/SHA pair/);
-	assert.doesNotMatch(content, /works the same on both surfaces/);
-});
-
-test("#given review-work skill #when some lanes do not finish #then aggregate result remains bounded", async () => {
-	const content = await readSkill("review-work");
-
-	assert.match(content, /pending\/PASS\/FAIL\/INCONCLUSIVE/);
-	assert.match(content, /Preserve completed lane results immediately/);
-	assert.match(content, /ALL 5 lanes have a terminal state/);
-	assert.match(content, /REVIEW INCONCLUSIVE - not approved/);
-	assert.match(content, /Overall Verdict: PASSED \/ FAILED \/ INCONCLUSIVE/);
-	assert.match(content, /PASS\/FAIL\/INCONCLUSIVE \| HIGH\/MED\/LOW/);
-	assert.match(content, /Do not spin in repeated/);
-	assert.match(content, /bare REJECT\/FAIL token without findings is not a verdict/);
-	assert.match(content, /cites the violated goal criterion/);
-	assert.match(content, /append a durable task-evidence record/);
-	assert.match(content, /full commit SHA/);
-	assert.match(content, /re-read that record/);
-	assert.match(content, /exact lane\/SHA pair/);
-	assert.match(content, /Do not use `multi_agent_v1\.send_input` as an interrupt/);
-});
-
-test("#given PR and review skills #when synced for Codex #then worktree lifecycle is mandatory", async () => {
-	const startWork = await readSkill("start-work");
-	const reviewWork = await readSkill("review-work");
-	const sharedStartWork = await readSharedSkill("start-work");
-
-	assert.match(startWork, /PR creation, PR handoff, branch handoff, or merge/);
-	assert.match(startWork, /Finish the PR\/branch lifecycle from its task-owned worktree/);
-	assert.match(startWork, /merge by default unless explicitly opted out/);
-	assert.match(startWork, /No PR\/branch implementation or review in the main worktree/);
-
-	assert.match(sharedStartWork, /required for PR\/branch work/);
-	assert.match(sharedStartWork, /No PR\/branch implementation, review, or merge in the main worktree/);
-	assert.doesNotMatch(sharedStartWork, /If worktree mode was used/);
-	assert.doesNotMatch(sharedStartWork, /merge or hand off exactly as requested/);
-
-	assert.match(reviewWork, /dedicated review worktree attached to that branch/);
-	assert.match(reviewWork, /Never\s+checkout, test, or edit the review branch in the main worktree/);
-});
-
-test("#given generated Codex compatibility guidance #when multi-agent lifecycle tools are mentioned #then optional tools are guarded by the active tools list", () => {
-	assert.match(codexHarnessToolCompatibility, /when exposed in the active tools list/, "send_input/close_agent must be marked optional (lazycodex#116)");
-	assert.match(codexHarnessToolCompatibility, /multi_agent_v1\.spawn_agent/);
-	assert.match(codexHarnessToolCompatibility, /multi_agent_v1\.wait_agent/);
-});

package/packages/omo-codex/plugin/test/ulw-plan-scope-contract.test.mjs

@@ -1,24 +0,0 @@
-import assert from "node:assert/strict";
-import { readFile } from "node:fs/promises";
-import { dirname, join } from "node:path";
-import test from "node:test";
-import { fileURLToPath } from "node:url";
-
-const pluginRoot = dirname(dirname(fileURLToPath(import.meta.url)));
-const repositoryRoot = dirname(dirname(dirname(pluginRoot)));
-const componentReference = join(pluginRoot, "components", "ultrawork", "skills", "ulw-plan", "references", "intent-unclear.md");
-const sharedReference = join(repositoryRoot, "packages", "shared-skills", "skills", "ulw-plan", "references", "intent-unclear.md");
-
-test("#given an unclear auth-improvement request #when ulw-plan derives its full-scope components #then it preserves evidenced intent without inventing reduction or MFA expansion", async () => {
-	const [component, shared] = await Promise.all([
-		readFile(componentReference, "utf8"),
-		readFile(sharedReference, "utf8"),
-	]);
-
-	for (const reference of [component, shared]) {
-		assert.match(reference, /components that refine the user's requested or evidence-backed intent/i);
-		assert.match(reference, /neither collapse into an invented reduced subset nor expand into adjacent features/i);
-		assert.match(reference, /MFA is an adjacent capability.*Scope OUT unless the user asks.*evidence establishes/i);
-		assert.doesNotMatch(reference, /MFA - all four planned in full/i);
-	}
-});