lazycodex-ai 5.0.0-beta.8 → 5.0.0-beta.9

package/packages/omo-codex/plugin/test/teammode-communication.test.mjs

@@ -3,14 +3,12 @@ import { readFileSync } from "node:fs";
 import { join } from "node:path";
 import test from "node:test";
 
-import { root } from "./aggregate-plugin-fixture.mjs";
 import { cleanupTeamRoot, createTeamRoot, runTeam, teamDir } from "./teammode-safety-fixture.mjs";
 
-// The teammode guide.md is what every member actually reads. The real run of leader session
-// 019eed1e- proved members default to silence: 10 members, ~6 min, 4 end-of-work reports, zero
-// peer messages, zero mid-task reports, zero send_message_to_thread calls - because the prose said
-// "over-communicate relentlessly" (aspirational, no trigger) and never named the tool or targets.
-// These tests pin the fix: a concrete push-communication protocol is the default the manual renders.
+// The teammode guide.md is what every member actually reads. A real leader-session run proved members
+// default to silence when the guide never names the tool or the address book, so the tests below pin
+// only the machine tokens the generator must surface: the cross-thread tool name and the team.json
+// field paths members address messages by. Guide/prompt wording itself is prose and stays unpinned.
 
 function buildTwoMemberTeam(tempRoot, sessionId) {
 	runTeam(tempRoot, "init", "--name", "Comms", "--session-name", "frequent", "--session", sessionId);
@@ -39,69 +37,15 @@ test("#given a bound team #when the member field manual renders #then it names t
 		cleanupTeamRoot(tempRoot);
 	}
 });
-
-test("#given a bound team #when the member field manual renders #then it gives concrete per-moment cadence triggers, not aspirational 'constantly'", () => {
-	const tempRoot = createTeamRoot("omo-codex-teammode-comms-");
-	try {
-		buildTwoMemberTeam(tempRoot, "comms-cadence");
-		const guide = readGuide(tempRoot, "comms-cadence");
-
-		// then - a concrete heartbeat cadence the model can bind to
-		assert.match(guide, /every few tool calls/, "guide must give a concrete heartbeat trigger");
-		assert.match(guide, /WORKING:/, "guide must keep the WORKING heartbeat marker");
-		assert.match(guide, /BLOCKED:/, "guide must keep the BLOCKED marker");
-		// then - an explicit peer-notify rule so cross-cutting findings are pushed, not siloed
-		assert.match(guide, /to a \*\*peer\*\*/, "guide must have an explicit peer-notify rule");
-		assert.match(guide, /touches their slice/, "guide must trigger peer messages on slice-touching findings");
-		// then - the reassurance WHY that ties the two halves together: frequent reporting is what earns
-		// uninterrupted focus, so the leader has no reason to interrupt a member who keeps it informed
-		assert.match(guide, /uninterrupted focus/i, "guide must tell members frequent updates buy uninterrupted focus from the leader");
-		// then - the end-only directive that previously won is gone (it licensed batch-at-the-end reporting)
-		assert.doesNotMatch(guide, /the moment your work is complete/, "the standalone end-only report directive must be removed");
-	} finally {
-		cleanupTeamRoot(tempRoot);
-	}
-});
-
-test("#given a member bootstrap trigger #when it is generated #then it points at the push tool and a continuous cadence, not an end-of-work report", () => {
+test("#given a member bootstrap trigger #when it is generated #then it names the cross-thread push tool", () => {
 	const tempRoot = createTeamRoot("omo-codex-teammode-comms-");
 	try {
 		buildTwoMemberTeam(tempRoot, "comms-bootstrap");
 		const prompt = runTeam(tempRoot, "member-prompt", "--team", "comms-bootstrap", "--id", "A").stdout;
 
-		// then - the first thing a member reads tells it to push via the tool as it works
+		// then - the first thing a member reads names the tool it can push through
 		assert.match(prompt, /codex_app\.send_message_to_thread/, "bootstrap must name the push tool");
-		assert.match(prompt, /never just one report at the end/, "bootstrap must reject end-only reporting");
-		// then - it no longer frames reporting as a one-shot completion event
-		assert.doesNotMatch(prompt, /report to the leader the moment you are done/, "the end-only bootstrap line must be removed");
 	} finally {
 		cleanupTeamRoot(tempRoot);
 	}
 });
-
-test("#given the leader-facing SKILL.md #when it describes communication #then it requires --session so members can reach the leader and frames members as pushing", () => {
-	const skill = readFileSync(join(root, "components", "teammode", "skills", "teammode", "SKILL.md"), "utf8");
-
-	// then - the leader is told members PUSH to it (not only that the leader sends)
-	assert.match(skill, /Members push to you/i, "SKILL.md must frame members as pushing to the leader");
-	// then - the --session requirement is stated WITH its reason (member->leader push needs a real leader thread)
-	assert.match(skill, /--session <your own thread id>/, "SKILL.md must require init --session <your own thread id>");
-	assert.match(skill, /stuck polling|cannot report to you/i, "SKILL.md must explain why --session matters");
-});
-
-// The leader (a GPT-5.5 main session) over-polls when nothing reframes silence as work: real jobdori
-// run 019f07a6- fired 6 leader->child pings, 4 pure "WORKING CHECK"/"NUDGE" nags that interrupted the
-// child mid-slice. The member guide already mandates frequent reporting; the missing half is telling the
-// leader to WAIT. These tests pin that the leader-facing skill reframes quiet-as-working and gates any
-// outbound ping behind concrete decision rules instead of letting anxiety drive a barrage.
-test("#given the leader-facing SKILL.md #when it covers waiting on members #then it reframes a quiet member as working and gates leader pings behind decision rules", () => {
-	const skill = readFileSync(join(root, "components", "teammode", "skills", "teammode", "SKILL.md"), "utf8");
-
-	// then - a quiet member between heartbeats is reframed as working, not a stall to chase
-	// (\s+ tolerates markdown line-wrapping between the two words)
-	assert.match(skill, /working,\s+not stalled/i, "SKILL.md must reframe a quiet member as working, not stalled");
-	// then - outbound leader messages are gated behind explicit decision rules, not anxiety
-	assert.match(skill, /Message a member only when/i, "SKILL.md must gate leader pings behind a concrete decision rule");
-	// then - the anti-pattern nag pings the real run produced are named as what NOT to send
-	assert.match(skill, /are you\s+done\?/i, "SKILL.md must name the 'are you done?' style nag as forbidden");
-});

package/packages/omo-codex/plugin/test/teammode-thread-links.test.mjs

@@ -71,46 +71,13 @@ test("#given a worktree-backed team has bound member threads #when guide and sta
 		const status = runTeam(tempRoot, "status", "--team", sessionId).stdout;
 		const prompt = runTeam(tempRoot, "member-prompt", "--team", sessionId, "--id", "A").stdout;
 
+		// then - guide, status, and bootstrap prompt all surface the member's bound thread link and cwd
 		assert.match(guide, /codex:\/\/threads\/019ef350-ee78-72a3-bd5e-e40cebc3d814/);
 		assert.match(guide, /codex:\/\/threads\/019ef2dd-5b99-7ae2-8461-ffa6ca309d23/);
 		assert.match(guide, /worktree `\/tmp\/review-worktree`/);
 		assert.match(status, /link=codex:\/\/threads\/019ef350-ee78-72a3-bd5e-e40cebc3d814/);
-		assert.match(prompt, /Your Codex thread link is codex:\/\/threads\/019ef350-ee78-72a3-bd5e-e40cebc3d814/);
-		assert.match(prompt, /Work inside `\/tmp\/review-worktree`/);
-		assert.match(prompt, /Before editing, verify that your assigned worktree exists and contains repo files/);
-		assert.match(prompt, /BLOCKED: worktree not ready/);
-	} finally {
-		cleanupTeamRoot(tempRoot);
-	}
-});
-
-test("#given a worktree member has no cwd bound yet #when guide and prompt render #then they tell Codex to wait for readiness", () => {
-	const tempRoot = createTeamRoot("omo-codex-teammode-worktree-wait-");
-	try {
-		const sessionId = "worktree-wait";
-		runTeam(tempRoot, "init", "--name", "Wait", "--session-name", "worktrees", "--session", sessionId, "--worktree", "--base-branch", "main");
-		addMember(tempRoot, sessionId, {
-			id: "A",
-			name: "worktree-driver",
-			focus: "drive a pending Codex worktree thread",
-			lens: "ownership",
-			deliverable: "ready worktree report",
-		});
-		addMember(tempRoot, sessionId, {
-			id: "B",
-			name: "integration-watch",
-			focus: "watch integration boundaries",
-			lens: "perspective",
-			deliverable: "integration notes",
-		});
-		runTeam(tempRoot, "bind-thread", "--team", sessionId, "--id", "A", "--thread", "019ef350-ee78-72a3-bd5e-e40cebc3d814");
-
-		const guide = readFileSync(`${teamDir(tempRoot, sessionId)}/guide.md`, "utf8");
-		const prompt = runTeam(tempRoot, "member-prompt", "--team", sessionId, "--id", "A").stdout;
-
-		assert.match(guide, /If Codex returns only `pendingWorktreeId`/);
-		assert.match(guide, /wait until Codex surfaces a real thread id/);
-		assert.match(prompt, /If this prompt arrived before your Codex worktree checkout is ready/);
+		assert.match(prompt, /codex:\/\/threads\/019ef350-ee78-72a3-bd5e-e40cebc3d814/);
+		assert.match(prompt, /\/tmp\/review-worktree/);
 	} finally {
 		cleanupTeamRoot(tempRoot);
 	}

package/packages/omo-codex/plugin/test/teammode-transport.test.mjs

@@ -3,7 +3,6 @@ import { existsSync, readFileSync, writeFileSync } from "node:fs";
 import { join } from "node:path";
 import test from "node:test";
 
-import { root } from "./aggregate-plugin-fixture.mjs";
 import {
 	cleanupTeamRoot,
 	createTeamRoot,
@@ -53,45 +52,6 @@ function addV2Members(tempRoot, sessionId) {
 	);
 }
 
-test("#given flat V2 tools are available #when the leader reads teammode #then transport selection and user announcement precede init", () => {
-	const skill = readFileSync(join(root, "components", "teammode", "skills", "teammode", "SKILL.md"), "utf8");
-	const inspectIndex = skill.indexOf("Inspect your active tool list");
-	const initIndex = skill.indexOf('team.mjs" init');
-
-	assert.notEqual(inspectIndex, -1, "skill must inspect the active tool list");
-	assert.notEqual(initIndex, -1, "skill must still document init");
-	assert.ok(inspectIndex < initIndex, "transport inspection must happen before init");
-	assert.match(skill, /spawn_agent.*task_name[\s\S]*send_message[\s\S]*followup_task[\s\S]*wait_agent[\s\S]*list_agents[\s\S]*interrupt_agent/);
-	assert.match(skill, /tell the user|announce.*transport/i);
-	assert.match(skill, /MultiAgentV2/i);
-	assert.match(skill, /Codex App.*fallback/i);
-});
-
-test("#given neither transport's tools are visible #when the leader reads teammode #then search hits are revalidated and fallback is capability-aware without team state", () => {
-	const skill = readFileSync(join(root, "components", "teammode", "skills", "teammode", "SKILL.md"), "utf8");
-
-	const searchIndex = skill.indexOf("tool_search");
-	const unavailableIndex = skill.indexOf("Teammode unavailable");
-	assert.notEqual(searchIndex, -1, "skill must route hidden tools through the tool_search check");
-	assert.notEqual(unavailableIndex, -1, "skill must give the leader unavailable announcement templates");
-	assert.ok(searchIndex < unavailableIndex, "tool_search must precede the unavailable conclusion");
-	assert.match(skill, /revalidate.*COMPLETE.*compatible transport set/is, "a deferred-tool hit must be revalidated as a complete transport");
-	assert.match(skill, /another visible plain-subagent mechanism.*spawn.*communicate.*observe/is, "plain-subagent fallback requires a complete visible lifecycle");
-	assert.match(skill, /Otherwise continue serially.*capability limitation/is, "missing all transports must continue serially rather than promise workers");
-	assert.match(skill, /Do NOT run `init`/, "the fallback must not create team state");
-	assert.doesNotMatch(skill, /splitting the work across plain fire-and-forget subagents/i, "the skill must not promise unavailable plain subagents");
-});
-
-test("#given a MultiAgentV2 team #when the leader spawns members #then guidance limits calls to exposed V2 fields", () => {
-	const skill = readFileSync(join(root, "components", "teammode", "skills", "teammode", "SKILL.md"), "utf8");
-
-	assert.match(skill, /using only the V2 schema fields/i);
-	assert.match(skill, /`task_name`[\s\S]*`message`[\s\S]*`fork_turns`/);
-	assert.match(skill, /role, priority, or task-specific routing instruction in `message`/i);
-	assert.match(skill, /V2 does not accept[\s\S]*`agent_type`, `model`, `reasoning_effort`, or `service_tier`/);
-	assert.match(skill, /inherit the[\s\S]*session model/i);
-});
-
 test("#given MultiAgentV2 transport #when members are added and bound #then task names and canonical agent paths form the address book", () => {
 	const tempRoot = createTeamRoot("omo-codex-teammode-v2-transport-");
 	try {
@@ -123,7 +83,6 @@ test("#given MultiAgentV2 transport #when members are added and bound #then task
 				{ id: "B", taskName: "mailbox_delivery", agentPath: "/root/mailbox_delivery", threadId: null, threadTitle: null, status: "active" },
 			],
 		);
-		assert.match(guide, /Transport:.*MultiAgentV2/i);
 		assert.match(guide, /members\[\]\.agentPath/);
 		assert.match(guide, /send_message/);
 		assert.match(guide, /followup_task/);
@@ -223,9 +182,7 @@ test("#given a V2 team #when the whole team is archived without a note #then no
 		const archiveEntry = team.log.find((entry) => entry.event === "archive");
 
 		assert.equal(team.status, "archived");
-		assert.doesNotMatch(result.stdout, /closed all members/i, "V2 has no runtime close/archive operation to claim");
 		assert.match(result.stdout, /no runtime archive operation/i);
-		assert.doesNotMatch(archiveEntry.detail, /all members closed/i);
 		assert.match(archiveEntry.detail, /no runtime archive operation/i);
 	} finally {
 		cleanupTeamRoot(tempRoot);
@@ -261,7 +218,6 @@ test("#given a codex_app team #when one member is archived #then the existing wo
 		const result = runTeam(tempRoot, "archive", "--team", "app-archive-member", "--id", "A");
 
 		assert.match(result.stdout, /archived member A/);
-		assert.doesNotMatch(result.stdout, /no runtime archive operation/i);
 	} finally {
 		cleanupTeamRoot(tempRoot);
 	}

package/packages/omo-codex/plugin/test/teammode-worktree.test.mjs

@@ -83,24 +83,21 @@ test("#given a worktree team #when worktree-add A #then a real git worktree on a
 		assert.match(result.stdout, /A/);
 		assert.match(result.stdout, /wait for the real Codex thread id/);
 		assert.match(result.stdout, /bind-thread before sending bootstrap/);
-		assert.doesNotMatch(result.stdout, /Tell that member to:/);
 	} finally {
 		cleanupTeamRoot(tempRoot);
 	}
 });
 
-test("#given worktree-add ran #when the field manual is regenerated #then it flips the member's guide to ISOLATION IS ON with the derived branch", () => {
+test("#given worktree-add ran #when the field manual is regenerated #then it shows the member's derived worktree branch", () => {
 	const tempRoot = createTeamRoot("omo-codex-teammode-wt-guide-");
 	try {
 		initGitRepo(tempRoot);
 		bootstrapTeam(tempRoot, "wt-guide", { worktree: false });
-		// before: no isolation, so the manual tells members to signal collisions instead
-		assert.match(readFileSync(join(teamDir(tempRoot, "wt-guide"), "guide.md"), "utf8"), /does not use isolated git worktrees/);
 
 		runTeam(tempRoot, "worktree-add", "--team", "wt-guide", "--id", "A");
 
+		// then - the regenerated guide carries the derived branch recorded in team state
 		const guide = readFileSync(join(teamDir(tempRoot, "wt-guide"), "guide.md"), "utf8");
-		assert.match(guide, /ISOLATION IS ON/);
 		assert.match(guide, /team\/wt-guide\/A/, "the member's row must show its derived worktree branch");
 	} finally {
 		cleanupTeamRoot(tempRoot);
@@ -225,7 +222,6 @@ test("#given a member branch that cannot be merged #when integrate runs #then it
 		const out = `${result.stdout}${result.stderr}`;
 		assert.notEqual(result.status, 0);
 		assert.match(out, /could not integrate|not something we can merge|ghost-branch-404/i, "must surface git's actual reason");
-		assert.doesNotMatch(out, /Conflicting files/, "a non-conflict failure must NOT be mislabeled as a merge conflict");
 	} finally {
 		cleanupTeamRoot(tempRoot);
 	}

package/packages/omo-codex/plugin/test/ultrawork-skill-pointer.test.mjs

@@ -33,7 +33,6 @@ test("#given synced skills #when the ultrawork skill is inspected #then it carri
 	const directive = readFileSync(join(root, "components", "ultrawork", "directive.md"), "utf8");
 	assert.match(skill, /^---\nname: ultrawork\n/);
 	assert.equal(skill.endsWith(directive), true);
-	assert.match(skill, /## 1\. Create the goal with binding success criteria/);
 });
 
 test("#given the built ultrawork CLI #when a ulw prompt is submitted #then a compact skill pointer is emitted", () => {
@@ -42,10 +41,8 @@ test("#given the built ultrawork CLI #when a ulw prompt is submitted #then a com
 	const output = JSON.parse(result.stdout);
 	const context = output.hookSpecificOutput.additionalContext;
 	assert.match(context, /^<ultrawork-mode>/);
-	assert.match(context, /First user-visible line this turn MUST be exactly:/);
 	assert.match(context, /create_goal/);
 	assert.equal(context.includes(skillPath), true);
-	assert.equal(context.includes("Tier triage"), false);
 	assert.equal(Buffer.byteLength(context, "utf8") < POINTER_MAX_BYTES, true);
 });
 

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

@@ -54,15 +54,12 @@ function matchesCas(state, expected, clauses) {
 
 for (const surface of surfaces) {
 	test(`#given ${surface.name} #when deeper review becomes required before plan completion #then durable request state covers explicit and automatic review without inventing a digest`, async () => {
-		const skill = await readFile(surface.skillPath, "utf8");
 		const workflow = await readFile(surface.workflowPath, "utf8");
 		const contract = readJsonContract(workflow, "ulw-plan-review-request-state-contract");
 
 		assert.equal(contract.transition, "replace");
 		assert.equal(contract.phase, "review_requested");
 		assert.deepEqual(contract.applies_when, ["explicit_review_modifier_before_complete_plan", "intent=unclear_and_nontrivial"]);
-		assert.match(skill, /Include `--review-required`[\s\S]{0,180}non-Trivial UNCLEAR/);
-		assert.match(workflow, /--draft-only/);
 		assert.equal(contract.atomic, true);
 		assert.equal(contract.review_required, true);
 		assert.equal(contract.plan_path, ".omo/plans/<slug>.md");

package/packages/omo-codex/scripts/install-dist/install-local.mjs

@@ -1,5 +1,5 @@
 #!/usr/bin/env node
-// omo-codex-install:1d8359e77ebe41655f091cd2e455f320cde2f9c681f0651797c47d8fdfa2dd76:3ebe53198af1a035e21991b814b41ddb4819c09cfde23b8864be33a92c636428
+// omo-codex-install:1d8359e77ebe41655f091cd2e455f320cde2f9c681f0651797c47d8fdfa2dd76:c76513d859dcf200fa0178cedc7bbd268cbb9a16c2f2b30d3edd344daec24755
 var __defProp = Object.defineProperty;
 var __returnValue = (v) => v;
 function __exportSetter(name, newValue) {
@@ -5927,7 +5927,7 @@ var package_default;
 var init_package = __esm(() => {
   package_default = {
     name: "@oh-my-opencode/omo-codex",
-    version: "5.0.0-beta.8",
+    version: "5.0.0-beta.9",
     type: "module",
     private: true,
     description: "Codex harness adapter for oh-my-openagent. Vendored Codex plugin namespace (omo) + TypeScript installer + telemetry.",

package/packages/shared-skills/skills/ultimate-browsing/ATTRIBUTION.md

@@ -1,19 +1,46 @@
 # ATTRIBUTION / NOTICE
 
 This skill (`ultimate-browsing`, part of `@oh-my-opencode/shared-skills`) ships
-project-original content plus two third-party tools that it installs at runtime
-(it does NOT vendor their source). Each runtime tool's license and required
-notices are reproduced below.
+project-original content, one vendored-and-modified upstream engine, plus two
+third-party tools that it installs at runtime (it does NOT vendor their source).
+Each component's provenance, license, and required notices are reproduced below.
 
 ---
 
-## 1. Project-original content (no third-party source vendored)
+## 1. insane-search engine — vendored upstream snapshot, modified
+
+`engine/**` originates from the **insane-search** project and is NOT
+project-original code, despite being heavily modified since import.
+
+- Upstream source: https://github.com/fivetaku/insane-search
+- Vendored into this repository on 2026-06-21 by commit
+  **`a4e4ed797`** (`feat(ultimate-browsing): vendor insane-search engine (junk-excluded)`),
+  via an explicit file whitelist that excluded caches and smoke-test junk.
+- Baseline: the upstream state as of that date, a **pre-0.7.0 snapshot**.
+  Upstream's CHANGELOG dates 0.7.0 to 2026-06-22; imported files carry no
+  version marker. We have never re-vendored since; the tree has diverged in
+  both directions.
+- Modifications by this project (non-exhaustive): de-personalization
+  (`4743199a5`), the Phase 2.5 surrogate retrieval stage and surrogate registry,
+  the provenance/trust result contract, the `bias_check.py` no-site-name CI gate,
+  module split of the fetch chain, and the Python test suite under
+  `engine/tests/`.
+- No upstream `LICENSE` file was included in the vendored snapshot, so this
+  repository has no upstream license text to reproduce here. Do not infer
+  project-original licensing from that absence; treat `engine/**` as
+  upstream-derived when reasoning about provenance.
+
+The binding version policy — which upstream baseline we sit on, why we stay
+pinned, what a future re-vendor must preserve, and what it must not import — is
+[`engine/AGENTS.md` §UPSTREAM BASELINE AND VERSION POLICY](engine/AGENTS.md).
+
+---
+
+## 2. Project-original content (no third-party source vendored)
 
 The following are authored by the oh-my-openagent project and carry no third-party
 license obligation:
 
-- `engine/**` — the insane-search Tier-1 fetch engine (curl_cffi grid, WAF
-  detection, Playwright fallback templates, `bias_check.py` no-site-name gate).
 - `references/insane-search/**` and `references/agent-reach/**` — the Tier-1 and
   Tier-1.5 reference docs.
 - `scripts/extract_cookies.py`, `scripts/cookie_paths.py`, `scripts/cookie_crypto.py`
@@ -26,7 +53,7 @@ user installs separately; this skill includes none of their source.
 
 ---
 
-## 2. CloakBrowser (CloakHQ) — Tier-2 stealth Chromium (runtime dependency)
+## 3. CloakBrowser (CloakHQ) — Tier-2 stealth Chromium (runtime dependency)
 
 The Tier-2 stealth browser is **CloakBrowser**, installed at runtime via `pip`
 (`pip install cloakbrowser`). No CloakBrowser source is vendored in this repository.
@@ -73,7 +100,7 @@ SOFTWARE.
 
 ---
 
-## 3. agent-browser (vercel-labs) — Tier-2 CDP automation CLI (runtime dependency)
+## 4. agent-browser (vercel-labs) — Tier-2 CDP automation CLI (runtime dependency)
 
 The Tier-2 automation CLI is **agent-browser**, installed at runtime via `npm`
 (`npm i -g agent-browser`). No agent-browser source is vendored in this repository.

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/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, []);
-});