oh-my-opencode 4.16.3 → 4.17.0

package/packages/omo-codex/plugin/test/migrate-codex-config.test.mjs

@@ -54,8 +54,8 @@ test("#given stale root reasoning config #when ensuring config #then replaces st
 	assert.equal(result.match(/^model_context_window\s*=/gm)?.length, 1);
 	assert.equal(result.match(/^model_reasoning_effort\s*=/gm)?.length, 1);
 	assert.equal(result.match(/^plan_mode_reasoning_effort\s*=/gm)?.length, 1);
-	assert.match(result, /model = "gpt-5\.5"/);
-	assert.match(result, /model_context_window = 400000/);
+	assert.match(result, /model = "gpt-5\.6-sol"/);
+	assert.match(result, /model_context_window = 372000/);
 	assert.match(result, /model_reasoning_effort = "high"/);
 	assert.match(result, /plan_mode_reasoning_effort = "xhigh"/);
 	assert.doesNotMatch(result, /gpt-5\.2/);
@@ -79,8 +79,8 @@ test("#given section settings reuse managed root keys #when ensuring config #the
 		].join("\n"),
 	);
 
-	assert.match(result, /^model = "gpt-5\.5"$/m);
-	assert.match(result, /^model_context_window = 400000$/m);
+	assert.match(result, /^model = "gpt-5\.6-sol"$/m);
+	assert.match(result, /^model_context_window = 372000$/m);
 	assert.match(result, /\[model_providers\.openai\]\nmodel = "provider-scoped-value"\nmodel_context_window = 123456/);
 	assert.match(result, /\[profiles\.review\]\nmodel_reasoning_effort = "medium"\nplan_mode_reasoning_effort = "medium"/);
 });
@@ -161,8 +161,8 @@ test("#given global and project-local stale Codex configs #when migrating #then
 	});
 
 	assert.deepEqual(result.changed.sort(), [join(codexHome, "config.toml"), projectConfig].sort());
-	assert.match(await readFile(join(codexHome, "config.toml"), "utf8"), /model = "gpt-5\.5"/);
-	assert.match(await readFile(projectConfig, "utf8"), /model_context_window = 400000/);
+	assert.match(await readFile(join(codexHome, "config.toml"), "utf8"), /model = "gpt-5\.6-sol"/);
+	assert.match(await readFile(projectConfig, "utf8"), /model_context_window = 372000/);
 });
 
 test("#given model catalog is unavailable and stale 272k config #when migrating #then fallback catalog still upgrades it", async () => {
@@ -183,8 +183,8 @@ test("#given model catalog is unavailable and stale 272k config #when migrating
 
 	const content = await readFile(join(codexHome, "config.toml"), "utf8");
 	assert.deepEqual(result.changed, [join(codexHome, "config.toml")]);
-	assert.match(content, /model = "gpt-5\.5"/);
-	assert.match(content, /model_context_window = 400000/);
+	assert.match(content, /model = "gpt-5\.6-sol"/);
+	assert.match(content, /model_context_window = 372000/);
 });
 
 test("#given model catalog is malformed and stale config #when migrating #then fallback catalog still upgrades it", async () => {
@@ -206,8 +206,8 @@ test("#given model catalog is malformed and stale config #when migrating #then f
 
 	const content = await readFile(join(codexHome, "config.toml"), "utf8");
 	assert.deepEqual(result.changed, [join(codexHome, "config.toml")]);
-	assert.match(content, /model = "gpt-5\.5"/);
-	assert.match(content, /model_context_window = 400000/);
+	assert.match(content, /model = "gpt-5\.6-sol"/);
+	assert.match(content, /model_context_window = 372000/);
 });
 
 test("#given user-customized Codex model config #when migrating #then user values are preserved without root multi-agent mode", async () => {
@@ -262,7 +262,7 @@ test("#given managed config state is malformed #when migrating #then migration i
 	const content = await readFile(join(codexHome, "config.toml"), "utf8");
 	const state = JSON.parse(await readFile(statePath, "utf8"));
 	assert.deepEqual(result.changed, [join(codexHome, "config.toml")]);
-	assert.match(content, /model_context_window = 400000/);
+	assert.match(content, /model_context_window = 372000/);
 	assert.equal(state.files[join(codexHome, "config.toml")].managed, true);
 });
 
@@ -670,15 +670,15 @@ test("#given global config starts with inline-comment features table #when full
 	const content = await readFile(configPath, "utf8");
 	const parsed = parseTomlWithPython(content);
 	assert.equal("multi_agent_mode" in parsed, false);
-	assert.equal(parsed.model, "gpt-5.5");
-	assert.equal(parsed.model_context_window, 400000);
+	assert.equal(parsed.model, "gpt-5.6-sol");
+	assert.equal(parsed.model_context_window, 372000);
 	assert.equal(parsed.model_reasoning_effort, "high");
 	assert.equal(parsed.plan_mode_reasoning_effort, "xhigh");
 	assert.equal(parsed.features.plugins, true);
 	assert.equal("multi_agent_mode" in parsed.features, false);
 	assert.equal("model" in parsed.features, false);
 	assert.equal("model_context_window" in parsed.features, false);
-	assert.match(content, /^model = "gpt-5\.5"\nmodel_context_window = 400000/m);
+	assert.match(content, /^model = "gpt-5\.6-sol"\nmodel_context_window = 372000/m);
 	assert.doesNotMatch(content, /^\s*multi_agent_mode\s*=/m);
 	assert.match(content, /\[features\] # keep comment\nplugins = true/);
 });

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

@@ -235,6 +235,15 @@ test("#given synced aggregate Codex skills #when they describe background orches
 	}
 });
 
+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, /Delegation by difficulty/);
+	assert.match(content, /Global Review and Debugging Gate/);
+	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");
 
@@ -245,6 +254,8 @@ test("#given review-work skill #when some lanes do not finish #then aggregate re
 	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, /Do not use `multi_agent_v1\.send_input` as an interrupt/);
 });
 

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

@@ -92,7 +92,7 @@ const startWorkOriginalHardRule = "- No completion claim while an applicable ult
 const startWorkCodexHardRule = "- No completion claim while an applicable ultraqa adversarial class was never probed. Each applicable class needs a captured observable result; each skipped class needs a one-line not-applicable reason in the ledger.\n- No `ORCHESTRATION COMPLETE`, final response, PR creation, PR handoff, or merge before the Global Review and Debugging Gate passes with recorded evidence.\n- No PR/branch implementation or review in the main worktree; create or use a task-owned git worktree first.\n- No unprefixed session ids in Boulder state. Codex sessions are always `codex:<session_id>`.";
 
 const reviewWorkCodexGatePattern =
-	/\nWhen `review-work` is used as a final implementation, PR, or `\$start-work`\ngate, it is blocking\. A timeout, missing deliverable, ack-only response,\nexplicit `BLOCKED:`, or inconclusive lane is not a pass\. Treat that lane as\nfailed, investigate the underlying uncertainty with the `debugging` skill when\nruntime behavior may be wrong, fix with evidence, and rerun the affected lane\nbefore claiming completion, creating or handing off a PR, or merging\.\n\nWhen reviewing a PR or branch, collect diff, file contents, and verification\nresults from a dedicated review worktree attached to that branch\. Never\ncheckout, test, or edit the review branch in the main worktree\.\n\nReview evidence must be safe to share\. Redact or mask secrets and sensitive\nuser data before including evidence in logs, PR bodies, or handoffs\. Never\ninclude raw tokens, credentials, auth headers, cookies, API keys, env dumps,\nprivate logs, or PII; summarize with lengths, hashes, and short non-sensitive\nprefixes when identity is needed\.\n/;
+	/\nWhen `review-work` is used as a final implementation, PR, or `\$start-work`\ngate, it is blocking\. A timeout, missing deliverable, ack-only response,\nexplicit `BLOCKED:`, or inconclusive lane is not a pass\. Treat that lane as\nfailed, investigate the underlying uncertainty with the `debugging` skill when\nruntime behavior may be wrong, fix with evidence, and rerun the affected lane\nbefore claiming completion, creating or handing off a PR, or merging\.\n\nA rejecting lane must name its blockers inline in its final message — each\nblocker cites the violated goal criterion or requirement plus an evidence\npointer\. A bare REJECT\/FAIL token without findings is not a verdict; treat it\nas an inconclusive lane \(one bounded respawn, then record it inconclusive with\nthat reason\)\.\n\nWhen reviewing a PR or branch, collect diff, file contents, and verification\nresults from a dedicated review worktree attached to that branch\. Never\ncheckout, test, or edit the review branch in the main worktree\.\n\nReview evidence must be safe to share\. Redact or mask secrets and sensitive\nuser data before including evidence in logs, PR bodies, or handoffs\. Never\ninclude raw tokens, credentials, auth headers, cookies, API keys, env dumps,\nprivate logs, or PII; summarize with lengths, hashes, and short non-sensitive\nprefixes when identity is needed\.\n/;
 
 export function removeCodexSkillOverlays(skillName, content) {
 	if (skillName === "ulw-research") {

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

@@ -252,13 +252,15 @@ test("#given synced ulw-loop skill #when worker guidance is inspected #then cont
 	);
 	const syncedSkill = await readFile(join(root, "skills", "ulw-loop", "SKILL.md"), "utf8");
 	const syncedWorkflow = await readFile(join(root, "skills", "ulw-loop", "references", "full-workflow.md"), "utf8");
+	// ulw-loop is V2-primary (gpt-5.6 sol/terra use the flat `wait_agent`); the `multi_agent_v1.*`
+	// namespace is documented only as the v1 fallback, so the wait_agent refs accept the bare token.
 	const requiredPatterns = [
-		["multi_agent_v1.wait_agent ref", /multi_agent_v1\.wait_agent/],
+		["wait_agent ref", /\bwait_agent\b/],
 		["local spawned-name tracking", /Track spawned agent names locally/],
 		["wait_agent mailbox path", /wait_agent.*mailbox signals/],
 		["progress status contract", /WORKING:/],
 		["long-running plan/reviewer background guidance", /Plan and reviewer agents may run for a long time/],
-		["bounded plan/reviewer polling", /multi_agent_v1\.wait_agent.*cycles/],
+		["bounded plan/reviewer polling", /wait_agent.*cycles/],
 		["single long wait guard", /single long blocking wait/],
 		["git-master checkpointing", /git-master/],
 		["touched-path commit-style probe", /touched-path commit history/],

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

@@ -6,47 +6,16 @@ import { fileURLToPath } from "node:url";
 
 const root = dirname(dirname(fileURLToPath(import.meta.url)));
 
-async function readUlwPlanCopies() {
+test("#given ulw-plan skill copies #when component source and packaged copy are compared #then they are byte-identical and expose the loader-parsed name", async () => {
+	// given
 	const componentPath = join(root, "components", "ultrawork", "skills", "ulw-plan", "SKILL.md");
 	const packagedPath = join(root, "skills", "ulw-plan", "SKILL.md");
-	return [
-		{ label: "component", path: componentPath, content: await readFile(componentPath, "utf8") },
-		{ label: "packaged", path: packagedPath, content: await readFile(packagedPath, "utf8") },
-	];
-}
 
-test("#given ulw-plan skill #when Codex delegation is inspected #then spawned planners block dependent work", async () => {
-	for (const copy of await readUlwPlanCopies()) {
-		assert.match(copy.content, /multi_agent_v1\.spawn_agent/, `${copy.label}: must document Codex spawning`);
-		assert.match(copy.content, /multi_agent_v1\.wait_agent/, `${copy.label}: must document Codex waiting`);
-		assert.match(
-			copy.content,
-			/Spawn every independent child for the current wave first/i,
-			`${copy.label}: must preserve independent spawn waves`,
-		);
-		assert.match(
-			copy.content,
-			/After the wave\s+is launched[\s\S]{0,240}multi_agent_v1\.wait_agent[\s\S]{0,240}terminal status/i,
-			`${copy.label}: must wait after the wave is launched`,
-		);
-		assert.doesNotMatch(
-			copy.content,
-			/Immediately after any `multi_agent_v1\.spawn_agent`/i,
-			`${copy.label}: must not serialize independent spawns`,
-		);
-		assert.match(copy.content, /terminal status/i, `${copy.label}: must wait until terminal status`);
-		assert.match(copy.content, /WORKING:/, `${copy.label}: must keep progress liveness guidance`);
-		assert.match(copy.content, /BLOCKED:/, `${copy.label}: must keep blocked liveness guidance`);
-		assert.match(
-			copy.content,
-			/timeout only means no new mailbox update arrived/i,
-			`${copy.label}: must frame wait timeouts as mailbox silence`,
-		);
-		assert.match(copy.content, /Fallback only when/, `${copy.label}: must keep explicit fallback conditions`);
-		assert.match(
-			copy.content,
-			/do not start dependent planning, drafting, approval-gate work, or final handoff/i,
-			`${copy.label}: must block dependent planning work before child results are integrated`,
-		);
-	}
+	// when
+	const component = await readFile(componentPath, "utf8");
+	const packaged = await readFile(packagedPath, "utf8");
+
+	// then
+	assert.equal(packaged, component);
+	assert.match(component, /^name: ulw-plan$/m);
 });

package/packages/omo-codex/plugin/test/ulw-research-skill-contract.test.mjs

@@ -1,10 +1,9 @@
-// allow: SIZE_OK - ULW research skill contract tests inspect one bundled prompt protocol; this release introduces the contract and future additions should split by protocol phase.
-
 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";
+
 import { sharedSkillsRootPath } from "@oh-my-opencode/shared-skills";
 
 const root = dirname(dirname(fileURLToPath(import.meta.url)));
@@ -18,286 +17,14 @@ async function readUlwResearchCopies() {
 	];
 }
 
-function frontmatterDescription(content) {
-	const match = content.match(/^---\r?\n[\s\S]*?\bdescription:\s*"([\s\S]*?)"\r?\n[\s\S]*?---/);
-	assert.notEqual(match, null, "SKILL.md frontmatter description not found");
-	return match[1];
-}
-
-function escapeRegExp(value) {
-	return value.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
-}
-
-function markdownSection(content, heading, nextHeading) {
-	const headingPattern = new RegExp(`^${escapeRegExp(heading)}\\r?$`, "m");
-	const headingMatch = content.match(headingPattern);
-	assert.notEqual(headingMatch, null, `SKILL.md section not found: ${heading}`);
-	assert.notEqual(headingMatch.index, undefined, `SKILL.md section index not found: ${heading}`);
-	const bodyStart = headingMatch.index + headingMatch[0].length;
-	if (nextHeading === undefined) {
-		return content.slice(bodyStart);
-	}
-	const nextHeadingIndex = content.indexOf(`\n${nextHeading}`, bodyStart);
-	assert.notEqual(nextHeadingIndex, -1, `SKILL.md next section not found: ${nextHeading}`);
-	return content.slice(bodyStart, nextHeadingIndex);
-}
-
-test("#given renamed research skill #when frontmatter is inspected #then ulw-research is the canonical name", async () => {
+test("#given ulw-research skill copies #when frontmatter is inspected #then the loader-parsed name is ulw-research", async () => {
 	for (const copy of await readUlwResearchCopies()) {
 		assert.match(copy.content, /^name: ulw-research$/m, `${copy.label}: frontmatter must expose ulw-research`);
 	}
 });
 
-test("#given renamed research skill #when activation marker is inspected #then ulw-research is the canonical marker", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		assert.match(
-			copy.content,
-			/`ULW-RESEARCH MODE ENABLED!`/,
-			`${copy.label}: body must expose the ulw-research activation marker`,
-		);
-		assert.doesNotMatch(
-			copy.content,
-			/`ULTRARESEARCH MODE ENABLED!`/,
-			`${copy.label}: body must not expose the old ultraresearch activation marker`,
-		);
-	}
-});
-
-test("#given ulw-research skill #when scanned for non-English content #then it contains no Hangul", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		assert.doesNotMatch(
-			copy.content,
-			/[ᄀ-ᇿ㄰-㆏가-힣]/,
-			`${copy.label} copy contains Hangul characters`,
-		);
-	}
-});
-
-test("#given ulw-research description #when activation policy is inspected #then it gates on explicit research demands only", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		const description = frontmatterDescription(copy.content);
-		assert.match(description, /ulw-research/i, `${copy.label}: description must name the ulw-research trigger`);
-		if (copy.label === "shared") {
-			assert.match(description, /ultraresearch/i, `${copy.label}: description must preserve ultraresearch discoverability`);
-		} else {
-			assert.doesNotMatch(description, /ultraresearch/i, `${copy.label}: description must not expose ultraresearch`);
-		}
-		assert.match(description, /\bulw\b/i, `${copy.label}: description must preserve ulw discoverability`);
-		assert.match(description, /explicit/i, `${copy.label}: description must gate activation on explicit demand`);
-		assert.match(
-			description,
-			/ultra-precise investigation/i,
-			`${copy.label}: description must name the ultra-precise investigation trigger`,
-		);
-		assert.match(description, /\bresearch\b/i, `${copy.label}: description must name the research trigger`);
-	}
-});
-
-test("#given packaged ulw-research skill #when scanned for legacy aliases #then ultraresearch is not exposed", async () => {
-	const packaged = (await readUlwResearchCopies()).find((copy) => copy.label === "packaged");
-	assert.notEqual(packaged, undefined, "packaged copy not found");
-	assert.doesNotMatch(packaged.content, /ultraresearch/i, "packaged ulw-research must not expose ultraresearch");
-});
-
-test("#given packaged ulw-research skill #when Codex guidance is inspected #then compatibility guidance is preserved", async () => {
-	const packaged = (await readUlwResearchCopies()).find((copy) => copy.label === "packaged");
-	assert.notEqual(packaged, undefined, "packaged copy not found");
-	assert.match(packaged.content, /## Codex Harness Tool Compatibility/);
-	assert.match(packaged.content, /multi_agent_v1\.spawn_agent/);
-	assert.match(packaged.content, /multi_agent_v1\.wait_agent/);
-});
-
-test("#given ulw-research body #when authority is inspected #then it takes precedence over exploration-bounding instructions", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		assert.match(
-			copy.content,
-			/exploration-bounding|exploration (?:caps|budgets|limits)/i,
-			`${copy.label}: body must name the exploration-bounding instructions it overrides`,
-		);
-		assert.match(
-			copy.content,
-			/supersede|override|do(?:es)? not (?:bind|apply)/i,
-			`${copy.label}: body must state precedence while the mode is active`,
-		);
-	}
-});
-
-test("#given ulw-research worker protocol #when EXPAND flow is inspected #then markers travel as message text and workers never write files", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		assert.match(copy.content, /EXPAND/, `${copy.label}: body must keep the EXPAND marker protocol`);
-		assert.match(
-			copy.content,
-			/(?:reply|message|response) text|end (?:its|the|your) (?:reply|response|final message)/i,
-			`${copy.label}: EXPAND markers must be returned as message text`,
-		);
-		assert.match(
-			copy.content,
-			/read-only|cannot write files|never ask (?:a )?worker(?:s)? to write/i,
-			`${copy.label}: body must state the read-only worker constraint`,
-		);
-		assert.doesNotMatch(
-			copy.content,
-			/APPEND (?:your )?findings to \$SESSION_DIR/i,
-			`${copy.label}: workers must not be instructed to append session-dir files`,
-		);
-	}
-});
-
-test("#given ulw-research journaling #when ownership is inspected #then the orchestrator owns the session journal", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		assert.match(
-			copy.content,
-			/orchestrator[\s\S]{0,200}journal|journal[\s\S]{0,200}orchestrator/i,
-			`${copy.label}: body must assign session-journal writes to the orchestrator`,
-		);
-		assert.match(copy.content, /SESSION_DIR/, `${copy.label}: body must keep the session directory protocol`);
-	}
-});
-
-test("#given ulw-research expansion loop #when stop rules are inspected #then convergence rules and a depth cap are stated", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		assert.match(copy.content, /converg/i, `${copy.label}: body must define convergence`);
-		assert.match(copy.content, /depth/i, `${copy.label}: body must define an expansion depth cap`);
-		assert.match(
-			copy.content,
-			/minimum (?:of )?(?:2|two) expansion waves|at least (?:2|two) expansion waves/i,
-			`${copy.label}: body must require a minimum of two expansion waves before convergence`,
-		);
-	}
-});
-
-test("#given ulw-research under ultrawork #when coexistence is inspected #then marker and done-definition conflicts are resolved", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		assert.match(copy.content, /ultrawork|\bulw\b/i, `${copy.label}: body must address ultrawork coexistence`);
-		assert.match(
-			copy.content,
-			/first(?:-| )line/i,
-			`${copy.label}: body must resolve the first-line activation marker conflict`,
-		);
-	}
-});
-
-test("#given ulw-research worker sizing #when spawn guidance is inspected #then capable-model and high-effort routing is stated", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		assert.match(
-			copy.content,
-			/capable model|high(?:est)? (?:reasoning )?effort/i,
-			`${copy.label}: body must route research workers to a capable model or high effort`,
-		);
-	}
-});
-
-test("#given ulw-research execution substrate #when team usage is inspected #then it prefers a cooperating team with harness-native team tools", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		assert.match(
-			copy.content,
-			/cooperating team/i,
-			`${copy.label}: body must encourage running the swarm as a cooperating team`,
-		);
-		assert.match(copy.content, /\bteammode\b/i, `${copy.label}: body must name the Codex teammode skill`);
-		assert.match(copy.content, /team_mode/i, `${copy.label}: body must name the OpenCode team_mode path`);
-	}
-});
-
-test("#given ulw-research team composition #when member slicing is inspected #then members map to part/ownership/perspective, never job titles", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		assert.match(
-			copy.content,
-			/by part, ownership, or perspective/i,
-			`${copy.label}: body must compose members by part, ownership, or perspective`,
-		);
-		assert.match(
-			copy.content,
-			/never a job title|not (?:a |by )?job title/i,
-			`${copy.label}: body must forbid vague job-title members`,
-		);
-	}
-});
-
-test("#given ulw-research team communication #when the raise law is inspected #then members broadcast every lead immediately rather than hoarding", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		assert.match(
-			copy.content,
-			/raise law|broadcast every lead/i,
-			`${copy.label}: body must state the raise/broadcast law`,
-		);
-		assert.match(copy.content, /over-communicate/i, `${copy.label}: body must demand over-communication`);
-		assert.match(
-			copy.content,
-			/the (?:moment|instant) it (?:surfaces|appears|lands)/i,
-			`${copy.label}: body must require raising leads the moment they surface`,
-		);
-		assert.match(
-			copy.content,
-			/hoard/i,
-			`${copy.label}: body must reject hoarding leads for a final dump`,
-		);
-	}
-});
-
-test("#given ulw-research default swarm #when team guidance is inspected #then teammode, many teammates, and hyperdebate are defaulted", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		const teamSection = markdownSection(copy.content, "## Run the swarm as a cooperating team", "## Worker ground rules");
-		assert.match(teamSection, /default(?:s)? to teammode|teammode by default/i, `${copy.label}: teammode must be the default`);
-		assert.match(teamSection, /many teammates|larger roster|5-8 teammates|5\+ teammates/i, `${copy.label}: body must prefer many teammates`);
-		assert.match(teamSection, /hyperdebate|ultradebate/i, `${copy.label}: body must require adversarial debate`);
-		assert.match(teamSection, /skeptic|red-team|cross-critique/i, `${copy.label}: body must include a critique perspective`);
-	}
-});
-
-test("#given ulw-research non-code verification #when the gate is inspected #then a claim graph / verified-claims data-flow-lock exists", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		assert.match(
-			copy.content,
-			/claim graph|verified-claims/i,
-			`${copy.label}: body must define the non-code claim-graph verification gate`,
-		);
-	}
-});
-
-test("#given ulw-research claim graph #when ownership is inspected #then workers never write the graph / verified-claims artifact", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		assert.doesNotMatch(
-			copy.content,
-			/worker[^.]*\b(?:write|append|create)s?\b[^.]*(?:claim[- ]graph|verified-claims)/i,
-			`${copy.label}: workers must not be instructed to write/append/create the claim graph or verified-claims`,
-		);
-	}
-});
-
-test("#given ulw-research report output #when defaults are inspected #then HTML/PDF reports go through frontend, visual QA, and reviewer approval", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		const phase0 = markdownSection(copy.content, "## Phase 0 — Decompose and open the journal", "## Phase 1 — Saturation wave");
-		const phase4 = markdownSection(copy.content, "## Phase 4 — Synthesize", "## Phase 5 — Final materials");
-		const phase5 = markdownSection(copy.content, "## Phase 5 — Final materials", "## Search craft");
-		assert.match(phase0, /Final material format:\s*<HTML\/PDF default \| explicit format \| markdown only>/, `${copy.label}: Phase 0 must track the default final-material contract`);
-		assert.match(phase4, /citation source of truth/i, `${copy.label}: Phase 4 synthesis must be a source of truth, not the default final artifact`);
-		assert.doesNotMatch(phase4, /When no report was requested, this is the deliverable/i, `${copy.label}: Phase 4 must not contradict default HTML/PDF final materials`);
-		assert.match(phase5, /Default final materials to HTML\/PDF unless the user explicitly asks/i, `${copy.label}: Phase 5 must default final materials to HTML/PDF`);
-		assert.match(phase5, /HTML first[\s\S]{0,120}PDF default/i, `${copy.label}: report output must default to HTML with PDF availability`);
-		assert.match(phase5, /\bfrontend\b/i, `${copy.label}: report assembly must load the frontend skill`);
-		assert.match(phase5, /visual-qa/i, `${copy.label}: report assembly must require visual-qa`);
-		assert.match(phase5, /ulw-loop|ULW loop/i, `${copy.label}: report QA must run under the ULW loop`);
-		assert.match(phase5, /reviewer[\s\S]{0,120}(?:approve|says no broken parts|no broken parts)/i, `${copy.label}: report completion must wait for reviewer approval`);
-	}
-});
-
-test("#given ulw-research final materials #when visual artifact guidance is inspected #then charts Mermaid graphs and imagegen are strongly required", async () => {
-	for (const copy of await readUlwResearchCopies()) {
-		const phase5 = markdownSection(copy.content, "## Phase 5 — Final materials", "## Search craft");
-		assert.match(phase5, /actively use charts/i, `${copy.label}: reports must strongly require charts`);
-		assert.match(phase5, /Mermaid graphs/i, `${copy.label}: reports must require Mermaid graphs`);
-		assert.match(phase5, /imagegen skill/i, `${copy.label}: reports must require imagegen visuals`);
-		assert.match(phase5, /generated (?:diagrams|visuals)|generated diagrams or editorial visuals/i, `${copy.label}: report assets must include generated visual guidance`);
-	}
-});
-
-test("#given ulw-research blocked sources #when escalation is inspected #then it routes through the ultimate-browsing skill", async () => {
+test("#given ulw-research skill copies #when scanned for non-English content #then they contain no Hangul", async () => {
 	for (const copy of await readUlwResearchCopies()) {
-		assert.match(
-			copy.content,
-			/ultimate-browsing/,
-			`${copy.label}: body must escalate blocked sources via the ultimate-browsing skill`,
-		);
+		assert.doesNotMatch(copy.content, /[ᄀ-ᇿ㄰-㆏가-힣]/, `${copy.label} copy contains Hangul characters`);
 	}
 });

package/packages/omo-codex/scripts/install-config-reasoning.test.mjs

@@ -22,8 +22,8 @@ test("#given empty Codex config #when script installer updates config #then sets
 
 	// then
 	const content = await readFile(configPath, "utf8");
-	assert.match(content, /model = "gpt-5\.5"/);
-	assert.match(content, /model_context_window = 400000/);
+	assert.match(content, /model = "gpt-5\.6-sol"/);
+	assert.match(content, /model_context_window = 372000/);
 	assert.match(content, /model_reasoning_effort = "high"/);
 	assert.match(content, /plan_mode_reasoning_effort = "xhigh"/);
 });
@@ -61,8 +61,8 @@ test("#given existing model and reasoning config #when script installer updates
 	assert.equal(content.match(/^model_context_window\s*=/gm)?.length, 1);
 	assert.equal(content.match(/^model_reasoning_effort\s*=/gm)?.length, 1);
 	assert.equal(content.match(/^plan_mode_reasoning_effort\s*=/gm)?.length, 1);
-	assert.match(content, /model = "gpt-5\.5"/);
-	assert.match(content, /model_context_window = 400000/);
+	assert.match(content, /model = "gpt-5\.6-sol"/);
+	assert.match(content, /model_context_window = 372000/);
 	assert.match(content, /model_reasoning_effort = "high"/);
 	assert.match(content, /plan_mode_reasoning_effort = "xhigh"/);
 	assert.doesNotMatch(content, /model = "gpt-5\.2"/);
@@ -148,6 +148,6 @@ test("#given fallback model catalog #when catalog file is unavailable #then no m
 	const catalog = await readCodexModelCatalog(root);
 
 	// then
-	assert.equal(catalog.current.model, "gpt-5.5");
+	assert.equal(catalog.current.model, "gpt-5.6-sol");
 	assert.equal(catalog.managedProfiles.some((profile) => profile.model === "gpt-5.4"), false);
 });

package/packages/omo-codex/scripts/install-config.test.mjs

@@ -23,10 +23,11 @@ test("#given empty Codex config #when script installer updates config #then sets
 	});
 
 	// then
+	// The stamped default model is v2-preferred, so the installer must not
+	// introduce agents.max_threads (Codex rejects it under MultiAgentV2).
 	const config = await readFile(configPath, "utf8");
 	assert.doesNotMatch(config, /^\s*multi_agent_mode\s*=/m);
-	assert.match(config, /\[agents\]/);
-	assert.match(config, /max_threads = 1000/);
+	assert.doesNotMatch(config, /^\s*max_threads\s*=/m);
 	assert.match(config, /\[features\.multi_agent_v2\]/);
 const v2Section = multiAgentV2Section(config);
 	assert.doesNotMatch(v2Section, /^enabled\s*=/m);
@@ -281,11 +282,15 @@ test("#given sisyphuslabs config without explicit source #when script installer
 
 test("#given existing MultiAgentV2 table #when script installer updates config #then preserves unrelated tuning while setting subagent thread limits", async () => {
 	// given
+	// A pinned v1 model keeps this on the preserve-user-disable path; the
+	// stamped v2-preferred default would clear the disable instead.
 	const root = await mkdtemp(join(tmpdir(), "omo-codex-script-config-multi-agent-existing-"));
 	const configPath = join(root, "config.toml");
 	await writeFile(
 		configPath,
 		[
+			'model = "gpt-5.5"',
+			"",
 			"[features.multi_agent_v2]",
 			"enabled = false",
 			"usage_hint_enabled = false",
@@ -327,9 +332,11 @@ test("#given empty Codex config #when script installer updates config #then sets
 	});
 
 	// then
+	// The stamped default model is v2-preferred, so agents.max_threads is not
+	// introduced (Codex rejects it under MultiAgentV2).
 	const config = await readFile(configPath, "utf8");
 	const v2Section = config.slice(config.indexOf("[features.multi_agent_v2]"));
-	assert.match(config, /\[agents\][\s\S]*?max_threads = 1000/);
+	assert.doesNotMatch(config, /^\s*max_threads\s*=/m);
 	assert.match(v2Section, /max_concurrent_threads_per_session = 1000/);
 	assert.doesNotMatch(v2Section, /hide_spawn_agent_metadata/);
 });
@@ -402,11 +409,15 @@ const v2Section = multiAgentV2Section(config);
 
 test("#given legacy boolean MultiAgentV2 flag false #when script installer updates config #then normalizes to a disabled table config", async () => {
 	// given
+	// A pinned v1 model keeps the legacy boolean materializing as a disabled
+	// table; the stamped v2-preferred default would drop the disable instead.
 	const root = await mkdtemp(join(tmpdir(), "omo-codex-script-config-multi-agent-legacy-false-"));
 	const configPath = join(root, "config.toml");
 	await writeFile(
 		configPath,
 		[
+			'model = "gpt-5.5"',
+			"",
 			"[features]",
 			"multi_agent_v2 = false",
 			"plugins = false",
@@ -434,11 +445,15 @@ test("#given legacy boolean MultiAgentV2 flag false #when script installer updat
 
 test("#given legacy agents max_threads #when script installer updates config #then raises the root subagent thread cap", async () => {
 	// given
+	// A pinned v1 model keeps the legacy low-cap raise path exercised; the
+	// stamped v2-preferred default would remove agents.max_threads instead.
 	const root = await mkdtemp(join(tmpdir(), "omo-codex-script-config-multi-agent-legacy-threads-"));
 	const configPath = join(root, "config.toml");
 	await writeFile(
 		configPath,
 		[
+			'model = "gpt-5.5"',
+			"",
 			"[agents]",
 			"max_threads = 16",
 			"max_depth = 4",
@@ -471,11 +486,15 @@ const v2Section = multiAgentV2Section(config);
 
 test("#given managed agent role sections #when script installer updates config #then preserves role config while raising only root agents max_threads", async () => {
 	// given
+	// A pinned v1 model keeps the legacy low-cap raise path exercised; the
+	// stamped v2-preferred default would remove agents.max_threads instead.
 	const root = await mkdtemp(join(tmpdir(), "omo-codex-script-config-multi-agent-role-section-"));
 	const configPath = join(root, "config.toml");
 	await writeFile(
 		configPath,
 		[
+			'model = "gpt-5.5"',
+			"",
 			"[agents]",
 			"max_threads = 16",
 			"",