oh-my-opencode 4.16.1 → 4.16.3

package/packages/omo-codex/scripts/install-generated-bundle.test.mjs

@@ -1,9 +1,12 @@
 import assert from "node:assert/strict";
-import { readFile } from "node:fs/promises";
+import { mkdtemp, readFile, writeFile } from "node:fs/promises";
+import { tmpdir } from "node:os";
 import { dirname, join } from "node:path";
 import test from "node:test";
 import { fileURLToPath } from "node:url";
 
+import { updateCodexConfig } from "./install-dist/install-local.mjs";
+
 const scriptsDir = dirname(fileURLToPath(import.meta.url));
 const entrypointPath = join(scriptsDir, "install-local.mjs");
 
@@ -53,3 +56,110 @@ test("#given generated installer output #when importing direct bundle #then comp
 		assert.equal(typeof module[name], "function", `${name} must be exported`);
 	}
 });
+
+test("#given no root model #when generated bundle updates config #then it does not introduce agents max_threads", async () => {
+	// given
+	const root = await mkdtemp(join(tmpdir(), "omo-codex-generated-no-root-model-"));
+	const configPath = join(root, "config.toml");
+	await writeFile(configPath, ['model_reasoning_effort = "high"', "", "[features]", "plugins = false", ""].join("\n"));
+
+	// when
+	await updateCodexConfig({
+		configPath,
+		repoRoot: "/repo/packages/omo-codex",
+		marketplaceName: "debug",
+		marketplaceSource: { sourceType: "local", source: "/repo/packages/omo-codex" },
+		pluginNames: ["omo"],
+	});
+
+	// then
+	const config = await readFile(configPath, "utf8");
+	assert.doesNotMatch(config, /^\s*max_threads\s*=/m);
+	assert.match(config, /max_concurrent_threads_per_session = 1000/);
+});
+
+test("#given explicit v1 model_catalog_json and stale models_cache v2 #when generated bundle updates config #then explicit catalog preserves disable and cap", async () => {
+	// given
+	const root = await mkdtemp(join(tmpdir(), "omo-codex-generated-catalog-v1-"));
+	const configPath = join(root, "config.toml");
+	const catalogPath = join(root, "custom-catalog.json");
+	await writeFile(
+		configPath,
+		[
+			'model = "gpt-5.6-sol"',
+			`model_catalog_json = "${catalogPath}"`,
+			"",
+			"[features]",
+			"multi_agent_v2 = false",
+			"",
+			"[agents]",
+			"max_threads = 16",
+			"",
+		].join("\n"),
+	);
+	await writeFile(catalogPath, JSON.stringify({ models: [{ slug: "gpt-5.6-sol", multi_agent_version: "v1" }] }));
+	await writeFile(join(root, "models_cache.json"), JSON.stringify({ models: [{ slug: "gpt-5.6-sol", multi_agent_version: "v2" }] }));
+
+	// when
+	await updateCodexConfig({
+		configPath,
+		repoRoot: "/repo/packages/omo-codex",
+		marketplaceName: "debug",
+		marketplaceSource: { sourceType: "local", source: "/repo/packages/omo-codex" },
+		pluginNames: ["omo"],
+	});
+
+	// then
+	const config = await readFile(configPath, "utf8");
+	const v2Section = sectionText(config, "[features.multi_agent_v2]");
+	assert.match(v2Section, /^enabled = false$/m);
+	assert.match(config, /\[agents\][\s\S]*?max_threads = 1000/);
+	assert.doesNotMatch(config, /max_threads = 16/);
+});
+
+test("#given explicit v2 model_catalog_json and stale models_cache v1 #when generated bundle updates config #then explicit catalog clears managed disable and cap", async () => {
+	// given
+	const root = await mkdtemp(join(tmpdir(), "omo-codex-generated-catalog-v2-"));
+	const configPath = join(root, "config.toml");
+	const catalogPath = join(root, "custom-catalog.json");
+	await writeFile(
+		configPath,
+		[
+			'model = "gpt-5.6-sol"',
+			`model_catalog_json = "${catalogPath}"`,
+			"",
+			"[features]",
+			"multi_agent_v2 = false",
+			"",
+			"[agents]",
+			"max_threads = 16",
+			"",
+		].join("\n"),
+	);
+	await writeFile(catalogPath, JSON.stringify({ models: [{ slug: "gpt-5.6-sol", multi_agent_version: "v2" }] }));
+	await writeFile(join(root, "models_cache.json"), JSON.stringify({ models: [{ slug: "gpt-5.6-sol", multi_agent_version: "v1" }] }));
+
+	// when
+	await updateCodexConfig({
+		configPath,
+		repoRoot: "/repo/packages/omo-codex",
+		marketplaceName: "debug",
+		marketplaceSource: { sourceType: "local", source: "/repo/packages/omo-codex" },
+		pluginNames: ["omo"],
+	});
+
+	// then
+	const config = await readFile(configPath, "utf8");
+	const v2Section = sectionText(config, "[features.multi_agent_v2]");
+	assert.doesNotMatch(v2Section, /^enabled\s*=/m);
+	assert.doesNotMatch(config, /^\s*max_threads\s*=/m);
+	assert.match(v2Section, /max_concurrent_threads_per_session = 1000/);
+});
+
+function sectionText(config, header) {
+	const start = config.indexOf(header);
+	if (start === -1) return "";
+	const afterStart = config.slice(start + header.length);
+	const nextSectionOffset = afterStart.search(/\n\[/);
+	return nextSectionOffset === -1 ? config.slice(start) : config.slice(start, start + header.length + nextSectionOffset);
+}

package/packages/shared-skills/skills/review-work/SKILL.md

@@ -14,9 +14,11 @@ This skill may include examples copied from the OpenCode harness. In Codex, do n
 | `task(subagent_type="oracle", ...)` for final verification | `multi_agent_v1.spawn_agent({"message":"TASK: act as a rigorous reviewer. ...","agent_type":"lazycodex-gate-reviewer","fork_context":false})` |
 | `task(category="...", ...)` for implementation or QA | `multi_agent_v1.spawn_agent({"message":"TASK: act as an implementation or QA worker. ...","fork_context":false})` |
 | `background_output(task_id="...")` | `multi_agent_v1.wait_agent(...)` for mailbox signals |
-| `team_*(...)` | Use Codex native subagents via `multi_agent_v1.spawn_agent`, `multi_agent_v1.send_input`, `multi_agent_v1.wait_agent`, and `multi_agent_v1.close_agent` |
+| `team_*(...)` | Use Codex native subagents via `multi_agent_v1.spawn_agent` and `multi_agent_v1.wait_agent`; use `multi_agent_v1.send_input` and `multi_agent_v1.close_agent` only when exposed in the active tools list |
 
-Role-specific behavior must be described in a self-contained `message`. Use `fork_context: false` to start the child with only the initial prompt (no parent history); use `fork_context: true` only when full parent history is truly required. Include any required conversation context, files, diffs, constraints, and requested skill names directly in the spawned agent's `message`. OMO installs these selectable agent roles into `~/.codex/agents/`: `explorer`, `librarian`, `plan`, `momus`, `metis`, `lazycodex-code-reviewer`, `lazycodex-qa-executor`, and `lazycodex-gate-reviewer` — pass the matching name as `agent_type` so the child gets that role's model and instructions. On `multi_agent_v2` sessions the same `agent_type` applies (the OMO installer exposes it) with `fork_turns` instead of `fork_context`. If the spawn tool exposes no `agent_type` parameter, omit it and describe the role inside `message`. If a code block below conflicts with this section, this section wins.
+Role-specific behavior must be described in a self-contained `message`. Use `fork_context: false` to start the child with only the initial prompt (no parent history); use `fork_context: true` only when full parent history is truly required. Include any required conversation context, files, diffs, constraints, and requested skill names directly in the spawned agent's `message`. OMO installs these selectable agent roles into `~/.codex/agents/`: `explorer`, `librarian`, `plan`, `momus`, `metis`, `lazycodex-code-reviewer`, `lazycodex-qa-executor`, and `lazycodex-gate-reviewer` — pass the matching name as `agent_type` so the child gets that role's model and instructions. If the spawn tool exposes no `agent_type` parameter, omit it and describe the role inside `message`. If a code block below conflicts with this section, this section wins.
+
+Codex exposes ONE of two subagent tool surfaces per session; check your own tool list and route accordingly. If `multi_agent_v1.*` tools exist, use the table above as written. If instead a flat `spawn_agent` with a required `task_name` exists (`multi_agent_v2`), rewrite every `multi_agent_v1.*` example: `multi_agent_v1.spawn_agent({...,"fork_context":false})` becomes `spawn_agent({"task_name":"<lowercase_digits_underscores>","message":...,"agent_type":...,"fork_turns":"none"})` (`"all"` only when full parent history is truly required); `send_input` becomes `send_message`; do not call `close_agent`/`resume_agent` (finished agents end on their own; `followup_task` re-tasks one, `interrupt_agent` stops one); `wait_agent` takes only `timeout_ms` and returns on any child mailbox activity. `agent_type` works the same on both surfaces. If a code block below conflicts with this section, this section wins.
 
 For work likely to exceed one wait cycle, require the child to send `WORKING: <task> - <current phase>` before long passes and `BLOCKED: <reason>` only when progress stops. A `multi_agent_v1.wait_agent` timeout only means no new mailbox update arrived. Treat a running child as alive. Fallback only when the child is completed without the deliverable, ack-only after followup, explicitly `BLOCKED:`, or no longer running.
 

package/packages/shared-skills/skills/start-work/SKILL.md

@@ -20,6 +20,8 @@ Translate any OpenCode-only tool name in an inherited example to its Codex equiv
 
 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.
 
+Codex exposes ONE of two subagent tool surfaces per session; check your own tool list and route accordingly. If `multi_agent_v1.*` tools exist, use the table above as written. If instead a flat `spawn_agent` with a required `task_name` exists (`multi_agent_v2`), rewrite every `multi_agent_v1.*` example: `multi_agent_v1.spawn_agent({...,"fork_context":false})` becomes `spawn_agent({"task_name":"<lowercase_digits_underscores>","message":...,"agent_type":...,"fork_turns":"none"})` (`"all"` only when full parent history is truly required); `send_input` becomes `send_message`; do not call `close_agent`/`resume_agent` (finished agents end on their own; `followup_task` re-tasks one, `interrupt_agent` stops one); `wait_agent` takes only `timeout_ms` and returns on any child mailbox activity. `agent_type` works the same on both surfaces. If a code block below conflicts with this section, this section wins.
+
 ## Codex Subagent Reliability
 
 Every `multi_agent_v1.spawn_agent` message is a self-contained executable assignment: `TASK: <imperative assignment>`, then `DELIVERABLE`, `SCOPE`, and `VERIFY`, with role instructions inside `message`. Use `fork_context: false` unless full history is truly required; paste only the context the child needs.

package/packages/shared-skills/skills/ulw-plan/references/full-workflow.md

@@ -85,7 +85,7 @@ Runs in parallel; ALL must APPROVE; surface results and wait for the user's expl
 - UNCLEAR: run the high-accuracy review AUTOMATICALLY before presenting (unless Classify=Trivial), then present a brief that LEADS with the derived approach and the adopted defaults; still wait for the user's explicit okay.
 
 ### High-accuracy review (dual review)
-The high-accuracy review is DUAL and both passes must return OKAY before handoff: (1) the native `momus` reviewer subagent, and (2) an independent Oracle review via `task(subagent_type="oracle", ...)` on the strongest available reasoning model, in a fully isolated sub-session with normal approval and sandbox policy. Do not add flags that disable approvals or sandboxing. One round = exactly ONE `momus` + ONE independent review, dispatched together against the COMPLETE plan file (todos + TL;DR filled) - never a second `momus` while a round is in flight. After both verdicts return, fix every cited issue and resubmit both fresh until each approves. CLEAR: runs when the user opts in or `review_required: true`. UNCLEAR: runs automatically unless Classify=Trivial.
+The high-accuracy review is DUAL and both passes must return OKAY before handoff: (1) the native `momus` reviewer subagent, and (2) an independent Oracle review via `task(subagent_type="oracle", ...)` on the strongest available reasoning model, in a fully isolated sub-session with normal approval and sandbox policy. Do not add flags that disable approvals or sandboxing. Momus runs at Ultra and may take substantially longer than other agents. One round = exactly ONE `momus` + ONE independent review, dispatched together against the COMPLETE plan file (todos + TL;DR filled). Keep Momus in flight and wait for its terminal result: elapsed time alone never justifies cancelling, duplicating, replacing, or treating it as failed. After both verdicts return, fix every cited issue and resubmit both fresh until each approves. CLEAR: runs when the user opts in or `review_required: true`. UNCLEAR: runs automatically unless Classify=Trivial.
 
 The draft must record the native Momus session/result, the independent review session/result, and the fix/retry summary. Do not say "high-accuracy review completed" unless both receipts exist and both final verdicts are unconditional approval.
 

package/packages/shared-skills/skills/ulw-research/SKILL.md

@@ -15,9 +15,11 @@ This skill may include examples copied from the OpenCode harness. In Codex, do n
 | `task(subagent_type="oracle", ...)` for final verification | `multi_agent_v1.spawn_agent({"message":"TASK: act as a rigorous reviewer. ...","agent_type":"lazycodex-gate-reviewer","fork_context":false})` |
 | `task(category="...", ...)` for implementation or QA | `multi_agent_v1.spawn_agent({"message":"TASK: act as an implementation or QA worker. ...","fork_context":false})` |
 | `background_output(task_id="...")` | `multi_agent_v1.wait_agent(...)` for mailbox signals |
-| `team_*(...)` | Use Codex native subagents via `multi_agent_v1.spawn_agent`, `multi_agent_v1.send_input`, `multi_agent_v1.wait_agent`, and `multi_agent_v1.close_agent` |
+| `team_*(...)` | Use Codex native subagents via `multi_agent_v1.spawn_agent` and `multi_agent_v1.wait_agent`; use `multi_agent_v1.send_input` and `multi_agent_v1.close_agent` only when exposed in the active tools list |
 
-Role-specific behavior must be described in a self-contained `message`. Use `fork_context: false` to start the child with only the initial prompt (no parent history); use `fork_context: true` only when full parent history is truly required. Include any required conversation context, files, diffs, constraints, and requested skill names directly in the spawned agent's `message`. OMO installs these selectable agent roles into `~/.codex/agents/`: `explorer`, `librarian`, `plan`, `momus`, `metis`, `lazycodex-code-reviewer`, `lazycodex-qa-executor`, and `lazycodex-gate-reviewer` — pass the matching name as `agent_type` so the child gets that role's model and instructions. On `multi_agent_v2` sessions the same `agent_type` applies (the OMO installer exposes it) with `fork_turns` instead of `fork_context`. If the spawn tool exposes no `agent_type` parameter, omit it and describe the role inside `message`. If a code block below conflicts with this section, this section wins.
+Role-specific behavior must be described in a self-contained `message`. Use `fork_context: false` to start the child with only the initial prompt (no parent history); use `fork_context: true` only when full parent history is truly required. Include any required conversation context, files, diffs, constraints, and requested skill names directly in the spawned agent's `message`. OMO installs these selectable agent roles into `~/.codex/agents/`: `explorer`, `librarian`, `plan`, `momus`, `metis`, `lazycodex-code-reviewer`, `lazycodex-qa-executor`, and `lazycodex-gate-reviewer` — pass the matching name as `agent_type` so the child gets that role's model and instructions. If the spawn tool exposes no `agent_type` parameter, omit it and describe the role inside `message`. If a code block below conflicts with this section, this section wins.
+
+Codex exposes ONE of two subagent tool surfaces per session; check your own tool list and route accordingly. If `multi_agent_v1.*` tools exist, use the table above as written. If instead a flat `spawn_agent` with a required `task_name` exists (`multi_agent_v2`), rewrite every `multi_agent_v1.*` example: `multi_agent_v1.spawn_agent({...,"fork_context":false})` becomes `spawn_agent({"task_name":"<lowercase_digits_underscores>","message":...,"agent_type":...,"fork_turns":"none"})` (`"all"` only when full parent history is truly required); `send_input` becomes `send_message`; do not call `close_agent`/`resume_agent` (finished agents end on their own; `followup_task` re-tasks one, `interrupt_agent` stops one); `wait_agent` takes only `timeout_ms` and returns on any child mailbox activity. `agent_type` works the same on both surfaces. If a code block below conflicts with this section, this section wins.
 
 For work likely to exceed one wait cycle, require the child to send `WORKING: <task> - <current phase>` before long passes and `BLOCKED: <reason>` only when progress stops. A `multi_agent_v1.wait_agent` timeout only means no new mailbox update arrived. Treat a running child as alive. Fallback only when the child is completed without the deliverable, ack-only after followup, explicitly `BLOCKED:`, or no longer running.
 
@@ -67,7 +69,7 @@ Observation candidates and claim candidates travel back from workers as message
 
 ## Run the swarm as a cooperating team
 
-Saturation research defaults to teammode, not isolated fire-and-forget workers: a lead one worker surfaces almost always reshapes what another should search next. When your harness gives you real cooperating members — Codex: the `teammode` skill (`codex_app` threads); OpenCode: `team_mode` — run this swarm as a team. Fall back to the background-worker swarm below only when team mode is unavailable, or the axes are genuinely independent with no cross-pollination expected.
+Saturation research defaults to teammode, not isolated fire-and-forget workers: a lead one worker surfaces almost always reshapes what another should search next. When your harness gives you real cooperating members — Codex: the `teammode` skill (MultiAgentV2 agents, or `codex_app` threads as its fallback); OpenCode: `team_mode` — run this swarm as a team. Fall back to the background-worker swarm below only when team mode is unavailable, or the axes are genuinely independent with no cross-pollination expected.
 
 - **One member per axis — by part, ownership, or perspective, never a job title.** Each Phase 0 axis is one member owning one concrete slice: a codebase part, a source territory, or a question lens. No two members share an angle. "Backend researcher" or "the web person" gives no real boundary and invites overlap — name what the member owns.
 - **Many teammates by default.** Prefer a larger roster, usually 5-8 teammates, whenever the axes can be made distinct. Add at least one skeptic or red-team perspective for hyperdebate/ultradebate: cross-critique claims, evidence quality, synthesis structure, and visual-report choices before they reach the final deliverable.

package/packages/shared-skills/skills/visual-qa/SKILL.md

@@ -249,7 +249,7 @@ If any page fails, you are not done: fix it, re-capture the full set, re-dispatc
 
 Run this step IN ADDITION to Steps 1-4 when the original user task has a concrete visual target: "clone this site", "move this Figma design to code", "rebuild this screen", "make it look exactly like X", or "build this Imagen/Stitch/generated mockup and overview". For these tasks the normal dual-oracle is necessary but NOT sufficient. After it returns, run the following TWO additional MANDATORY verifications and LOOP until BOTH pass.
 
-1. Pixel-perfect design-compare subagent (visual oracle). Dispatch a focused, read-only design-compare reviewer (recommend `gpt-5.5` with medium reasoning). It must crop/zoom BOTH the reference (target / Figma export / source-site screenshot / generated page snapshot) and the ACTUAL screenshot into matching regions and read them **pixel-by-pixel** - header, nav, each card, spacing, type ramp, color tokens - not at a glance. It must also compare the overview text or annotations against the rendered content and DOM text. Anchor every claim with the bundled tool:
+1. Pixel-perfect design-compare subagent (visual oracle). Dispatch a focused, read-only design-compare reviewer (recommend `gpt-5.6-sol` with xhigh reasoning). It must crop/zoom BOTH the reference (target / Figma export / source-site screenshot / generated page snapshot) and the ACTUAL screenshot into matching regions and read them **pixel-by-pixel** - header, nav, each card, spacing, type ramp, color tokens - not at a glance. It must also compare the overview text or annotations against the rendered content and DOM text. Anchor every claim with the bundled tool:
 
 ```
 node "$SKILL_DIR/scripts/visual-qa.mjs" image-diff <reference.png> <actual.png>