oh-my-opencode 4.16.2 → 4.17.0

package/dist/plugin/chat-message/types.d.ts

@@ -49,6 +49,9 @@ type RalphLoopHook = {
     resumeLoop?: (sessionID: string) => boolean;
     cancelLoop: (sessionID: string) => boolean | void;
 };
+type TodoContinuationEnforcerHook = {
+    cancelAllCountdowns: () => void;
+};
 export type ChatMessageHooks = {
     modelFallback?: ChatMessageHook | null;
     stopContinuationGuard?: StopContinuationGuard | null;
@@ -63,5 +66,6 @@ export type ChatMessageHooks = {
     hephaestusAgentsMdInjector?: ChatMessageHook | null;
     startWork?: ChatMessageHook | null;
     ralphLoop?: RalphLoopHook | null;
+    todoContinuationEnforcer?: TodoContinuationEnforcerHook | null;
 };
 export {};

package/dist/plugin/command-execute-before.d.ts

@@ -14,6 +14,7 @@ type CommandExecuteBeforeOutput = {
 };
 declare const NATIVE_LOOP_TRIGGERED_FLAG = "__omoNativeLoopTriggered";
 export declare function createCommandExecuteBeforeHandler(args: {
+    directory: string;
     hooks: CreatedHooks;
 }): (input: CommandExecuteBeforeInput, output: CommandExecuteBeforeOutput) => Promise<void>;
 export { NATIVE_LOOP_TRIGGERED_FLAG };

package/dist/plugin/stop-continuation.d.ts

@@ -0,0 +1,17 @@
+type StopContinuationHooks = {
+    readonly stopContinuationGuard?: {
+        readonly stop?: (sessionID: string) => void;
+    } | null;
+    readonly todoContinuationEnforcer?: {
+        readonly cancelAllCountdowns: () => void;
+    } | null;
+    readonly ralphLoop?: {
+        readonly cancelLoop: (sessionID: string) => boolean | void;
+    } | null;
+};
+export declare function stopContinuation(args: {
+    readonly directory: string;
+    readonly hooks: StopContinuationHooks;
+    readonly sessionID: string;
+}): void;
+export {};

package/dist/shared/live-server-route.d.ts

@@ -3,7 +3,7 @@ export declare const LIVE_ROUTE_UNAVAILABLE_LOG = "[live-server-route] route una
 type RouteResult = {
     client: unknown;
     route: "live" | "in-process";
-    reason: "identity" | "flag" | "child" | "unavailable" | "live";
+    reason: "identity" | "flag" | "child" | "unavailable" | "live" | "affinity";
 };
 type FetchImpl = typeof fetch;
 export declare function _setFetchImplementationForTesting(impl: FetchImpl | undefined): void;

package/dist/skills/remove-ai-slops/SKILL.md

@@ -62,7 +62,7 @@ The agent looks for these nine categories. The first three are stylistic, the ne
    **Hard rule**: only apply when behavior equivalence is obvious. Do NOT change algorithms with subtle correctness implications. Do NOT micro-optimize hot paths without a benchmark. If in doubt, SKIP.
 
 ### Behavior coverage
-9. **Missing tests** — behavior present in changed files that is not locked by any regression test. The fix is not to remove code but to ADD the narrowest test that pins the behavior.
+9. **Missing tests** — behavior present in changed files that is not locked by any regression test. The fix is not to remove code but to ADD the narrowest test that pins the behavior. EXCEPTION: a PROSE file (prompt, `SKILL.md`, rule, markdown) has no behavioral seam — do NOT add a text/word-count/phrase pin for it; that guards a diff, not behavior. Cover only a machine-consumed value (parsed field, sentinel a runtime greps, a doc JSON sample through its real validator) or leave it to review.
 
 ### Structural
 10. **Oversized modules** — any source file exceeding **250 pure LOC** (non-blank, non-comment lines). This is an architectural defect, not a style preference. Measure: `awk '!/^[[:space:]]*$/ && !/^[[:space:]]*(#|\/\/)/' <file> | wc -l`.
@@ -122,7 +122,7 @@ For each in-scope source file:
 
 1. Identify the public/observable behavior the file exposes (exported functions, HTTP handlers, CLI commands, classes used elsewhere).
 2. Check whether existing tests cover that behavior. Use `git grep` / project test conventions to find related test files.
-3. **If behavior is uncovered or weakly covered, write the narrowest regression test that pins current behavior BEFORE editing the file.** Tests should pin observable outputs, not implementation details.
+3. **If behavior is uncovered or weakly covered, write the narrowest regression test that pins current behavior BEFORE editing the file.** Tests should pin observable outputs, not implementation details. A PROSE file (prompt/`SKILL.md`/rule/markdown) is exempt — its wording is not behavior; skip the test and rely on review, or assert only a machine-consumed value.
 4. Run the test suite (or at minimum the relevant tests). They must be **green** before any cleanup begins.
 
 If you cannot establish a green baseline (e.g., test runner is broken), STOP and report. Do not proceed with cleanup on unverified ground.

package/dist/skills/review-work/SKILL.md

@@ -14,7 +14,7 @@ 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. 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.
 

package/dist/skills/start-work/SKILL.md

@@ -14,13 +14,16 @@ Translate any OpenCode-only tool name in an inherited example to its Codex equiv
 | OpenCode example | Codex tool to use |
 | --- | --- |
 | final-review `task(...)` | `multi_agent_v1.spawn_agent({"message":"TASK: act as a rigorous reviewer. ...","agent_type":"lazycodex-gate-reviewer","fork_context":false})` |
-| worker `task(...)` | `multi_agent_v1.spawn_agent({"message":"TASK: act as <role>. ...","fork_context":false})` |
+| worker `task(...)` | `multi_agent_v1.spawn_agent({"message":"TASK: act as <role>. ...","fork_context":false})` — for implementation workers add `agent_type: "lazycodex-worker-<low|medium|high>"` when the spawn schema exposes `agent_type` |
 | `background_output(task_id="...")` | `multi_agent_v1.wait_agent(...)` for mailbox signals |
 | `team_*(...)` | `multi_agent_v1.spawn_agent` + `multi_agent_v1.send_input` + `multi_agent_v1.wait_agent` + `multi_agent_v1.close_agent` |
 
 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 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. On the v2 surface `agent_type` may be absent from the spawn schema — when absent, omit it and describe the role inside `message`. If a code block below conflicts with this section, this section wins.
+
+### Delegation by difficulty (Codex tier workers)
+When tier worker agents are installed (Codex), size each implementation lane by difficulty and pass the matching `agent_type` where the spawn schema exposes it: LOW (one-file fix, boilerplate, config/copy) -> `lazycodex-worker-low`; MEDIUM (standard feature, few files, known patterns) -> `lazycodex-worker-medium`; HIGH (new module, cross-module refactor, concurrency/security/migration) -> `lazycodex-worker-high`. Explorer/librarian research lanes keep their own roles. Difficulty (model power) is orthogonal to the LIGHT/HEAVY rigor tier in step 4 — judge each on its own facts. On spawn surfaces without `agent_type` (deployed v2), state the tier inside `message`.
 
 ## Codex Subagent Reliability
 

package/dist/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/dist/skills/ulw-plan/scripts/scaffold-plan.mjs

@@ -221,7 +221,7 @@ Your next move: <fill - e.g. approve, or run a high-accuracy review>. Full execu
 ## Verification strategy
 > Zero human intervention - all verification is agent-executed.
 - Test decision: <TDD | tests-after | none> + framework
-- Evidence: .omo/evidence/task-<N>-${slug}.<ext>
+- Evidence: <attemptDir>/task-<N>-${slug}.<ext> (attemptDir = currentAttemptDir from 'omo ulw-loop status --json', .omo/evidence/ulw/<session>/<goalId>/a<attempt>; outside ulw-loop use .omo/evidence/)
 
 ## Execution strategy
 ### Parallel execution waves
@@ -239,7 +239,7 @@ Your next move: <fill - e.g. approve, or run a high-accuracy review>. Full execu
   Parallelization: Wave <N> | Blocked by: <...> | Blocks: <...>
   References (executor has NO interview context - be exhaustive): <src/path:lines>
   Acceptance criteria (agent-executable): <exact command or assertion>
-  QA scenarios (name the exact tool + invocation): happy + failure, Evidence .omo/evidence/task-1-${slug}.<ext>
+  QA scenarios (name the exact tool + invocation): happy + failure, Evidence <attemptDir>/task-1-${slug}.<ext>
   Commit: <Y/N> | <type>(<scope>): <summary>
 
 ## Final verification wave

package/dist/skills/ulw-research/SKILL.md

@@ -15,7 +15,7 @@ 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. 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.
 
@@ -69,7 +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/dist/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>

package/dist/tui.js

@@ -20694,6 +20694,11 @@ var init_agent_model_requirements = __esm(() => {
     },
     hephaestus: {
       fallbackChain: [
+        {
+          providers: ["openai", "vercel"],
+          model: "gpt-5.6-sol",
+          variant: "medium"
+        },
         {
           providers: ["openai", "github-copilot", "opencode", "vercel"],
           model: "gpt-5.5",
@@ -20720,7 +20725,7 @@ var init_agent_model_requirements = __esm(() => {
           model: "claude-opus-4-7",
           variant: "max"
         },
-        { providers: ["opencode-go", "vercel"], model: "glm-5.1" }
+        { providers: ["opencode-go", "vercel"], model: "glm-5.2" }
       ]
     },
     librarian: {
@@ -20767,7 +20772,7 @@ var init_agent_model_requirements = __esm(() => {
           model: "gpt-5.5",
           variant: "high"
         },
-        { providers: ["opencode-go", "vercel"], model: "glm-5.1" },
+        { providers: ["opencode-go", "vercel"], model: "glm-5.2" },
         {
           providers: ["google", "github-copilot", "opencode", "vercel"],
           model: "gemini-3.1-pro"
@@ -20790,12 +20795,17 @@ var init_agent_model_requirements = __esm(() => {
           model: "gpt-5.5",
           variant: "high"
         },
-        { providers: ["opencode-go", "vercel"], model: "glm-5.1" },
+        { providers: ["opencode-go", "vercel"], model: "glm-5.2" },
         { providers: ["kimi-for-coding"], model: "k2p5" }
       ]
     },
     momus: {
       fallbackChain: [
+        {
+          providers: ["openai", "vercel"],
+          model: "gpt-5.6-sol",
+          variant: "xhigh"
+        },
         {
           providers: ["openai", "github-copilot", "opencode", "vercel"],
           model: "gpt-5.5",
@@ -20811,7 +20821,7 @@ var init_agent_model_requirements = __esm(() => {
           model: "gemini-3.1-pro",
           variant: "high"
         },
-        { providers: ["opencode-go", "vercel"], model: "glm-5.1" }
+        { providers: ["opencode-go", "vercel"], model: "glm-5.2" }
       ]
     },
     atlas: {
@@ -20863,12 +20873,17 @@ var init_category_model_requirements = __esm(() => {
           model: "claude-opus-4-7",
           variant: "max"
         },
-        { providers: ["opencode-go", "vercel"], model: "glm-5.1" },
+        { providers: ["opencode-go", "vercel"], model: "glm-5.2" },
         { providers: ["kimi-for-coding"], model: "k2p5" }
       ]
     },
     ultrabrain: {
       fallbackChain: [
+        {
+          providers: ["openai", "vercel"],
+          model: "gpt-5.6-sol",
+          variant: "xhigh"
+        },
         {
           providers: ["openai", "opencode", "vercel"],
           model: "gpt-5.5",
@@ -20884,11 +20899,21 @@ var init_category_model_requirements = __esm(() => {
           model: "claude-opus-4-7",
           variant: "max"
         },
-        { providers: ["opencode-go", "vercel"], model: "glm-5.1" }
+        { providers: ["opencode-go", "vercel"], model: "glm-5.2" }
       ]
     },
     deep: {
       fallbackChain: [
+        {
+          providers: ["openai", "vercel"],
+          model: "gpt-5.6-terra",
+          variant: "xhigh"
+        },
+        {
+          providers: ["openai", "vercel"],
+          model: "gpt-5.6-sol",
+          variant: "high"
+        },
         {
           providers: ["openai", "github-copilot", "opencode", "vercel"],
           model: "gpt-5.5",
@@ -20905,7 +20930,7 @@ var init_category_model_requirements = __esm(() => {
           variant: "high"
         },
         { providers: ["opencode-go", "vercel"], model: "kimi-k2.6" },
-        { providers: ["opencode-go", "vercel"], model: "glm-5.1" }
+        { providers: ["opencode-go", "vercel"], model: "glm-5.2" }
       ]
     },
     artistry: {
@@ -20922,7 +20947,7 @@ var init_category_model_requirements = __esm(() => {
         },
         { providers: ["openai", "github-copilot", "opencode", "vercel"], model: "gpt-5.5" },
         { providers: ["opencode-go", "vercel"], model: "kimi-k2.6" },
-        { providers: ["opencode-go", "vercel"], model: "glm-5.1" }
+        { providers: ["opencode-go", "vercel"], model: "glm-5.2" }
       ]
     },
     quick: {
@@ -20947,6 +20972,11 @@ var init_category_model_requirements = __esm(() => {
     },
     "unspecified-low": {
       fallbackChain: [
+        {
+          providers: ["openai", "vercel"],
+          model: "gpt-5.6-luna",
+          variant: "xhigh"
+        },
         {
           providers: ["anthropic", "github-copilot", "opencode", "vercel"],
           model: "claude-sonnet-4-6"
@@ -20980,7 +21010,7 @@ var init_category_model_requirements = __esm(() => {
         },
         { providers: ["zai-coding-plan", "opencode", "bailian-coding-plan", "vercel"], model: "glm-5" },
         { providers: ["kimi-for-coding"], model: "k2p5" },
-        { providers: ["opencode-go", "vercel"], model: "glm-5.1" },
+        { providers: ["opencode-go", "vercel"], model: "glm-5.2" },
         { providers: ["opencode", "bailian-coding-plan", "vercel"], model: "kimi-k2.5" },
         {
           providers: [
@@ -21328,6 +21358,54 @@ var init_supplemental_entries = __esm(() => {
         output: 262144
       }
     },
+    "gpt-5.6-sol": {
+      id: "gpt-5.6-sol",
+      family: "gpt",
+      reasoning: true,
+      temperature: false,
+      toolCall: true,
+      modalities: {
+        input: ["text", "image", "pdf"],
+        output: ["text"]
+      },
+      limit: {
+        context: 1050000,
+        input: 922000,
+        output: 128000
+      }
+    },
+    "gpt-5.6-terra": {
+      id: "gpt-5.6-terra",
+      family: "gpt-mini",
+      reasoning: true,
+      temperature: false,
+      toolCall: true,
+      modalities: {
+        input: ["text", "image", "pdf"],
+        output: ["text"]
+      },
+      limit: {
+        context: 1050000,
+        input: 922000,
+        output: 128000
+      }
+    },
+    "gpt-5.6-luna": {
+      id: "gpt-5.6-luna",
+      family: "gpt-nano",
+      reasoning: true,
+      temperature: false,
+      toolCall: true,
+      modalities: {
+        input: ["text", "image", "pdf"],
+        output: ["text"]
+      },
+      limit: {
+        context: 1050000,
+        input: 922000,
+        output: 128000
+      }
+    },
     "gpt-5.5": {
       id: "gpt-5.5",
       family: "gpt",
@@ -21846,28 +21924,7 @@ var init_agent_display_names = __esm(() => {
   REVERSE_DISPLAY_NAMES = Object.fromEntries(Object.entries(AGENT_DISPLAY_NAMES).map(([key, displayName]) => [displayName.toLowerCase(), key]));
 });
 // packages/omo-opencode/src/tools/delegate-task/anthropic-categories.ts
-var UNSPECIFIED_LOW_CATEGORY_PROMPT_APPEND = `<Category_Context>
-You are working on tasks that don't fit specific categories but require moderate effort.
-
-<Selection_Gate>
-BEFORE selecting this category, VERIFY ALL conditions:
-1. Task does NOT fit: quick (trivial), visual-engineering (UI), ultrabrain (deep logic), artistry (creative), writing (docs)
-2. Task requires more than trivial effort but is NOT system-wide
-3. Scope is contained within a few files/modules
-
-If task fits ANY other category, DO NOT select unspecified-low.
-This is NOT a default choice - it's for genuinely unclassifiable moderate-effort work.
-</Selection_Gate>
-</Category_Context>
-
-<Caller_Warning>
-THIS CATEGORY USES A MID-TIER MODEL (claude-sonnet-4-6).
-
-**PROVIDE CLEAR STRUCTURE:**
-1. MUST DO: Enumerate required actions explicitly
-2. MUST NOT DO: State forbidden actions to prevent scope creep
-3. EXPECTED OUTPUT: Define concrete success criteria
-</Caller_Warning>`, UNSPECIFIED_HIGH_CATEGORY_PROMPT_APPEND = `<Category_Context>
+var UNSPECIFIED_HIGH_CATEGORY_PROMPT_APPEND = `<Category_Context>
 You are working on tasks that don't fit specific categories but require substantial effort.
 
 <Selection_Gate>
@@ -21883,12 +21940,6 @@ If task is unclassifiable but moderate-effort, use unspecified-low instead.
 </Category_Context>`, ANTHROPIC_CATEGORIES;
 var init_anthropic_categories = __esm(() => {
   ANTHROPIC_CATEGORIES = [
-    {
-      name: "unspecified-low",
-      config: { model: "anthropic/claude-sonnet-4-6" },
-      description: "Tasks that don't fit other categories, low effort required",
-      promptAppend: UNSPECIFIED_LOW_CATEGORY_PROMPT_APPEND
-    },
     {
       name: "unspecified-high",
       config: { model: "anthropic/claude-opus-4-7", variant: "max" },
@@ -22064,11 +22115,15 @@ function isGpt5_5Model(model) {
   const modelName = extractModelName(model).toLowerCase();
   return modelName.includes("gpt-5.5") || modelName.includes("gpt-5-5");
 }
+function isGpt5_6Model(model) {
+  const modelName = extractModelName(model).toLowerCase();
+  return modelName.includes("gpt-5.6") || modelName.includes("gpt-5-6");
+}
 var init_types3 = () => {};
 
 // packages/omo-opencode/src/tools/delegate-task/openai-categories.ts
 function resolveDeepCategoryPromptAppend(model) {
-  if (model && isGpt5_5Model(model)) {
+  if (model && (isGpt5_5Model(model) || isGpt5_6Model(model))) {
     return DEEP_CATEGORY_PROMPT_APPEND_GPT_5_5;
   }
   return DEEP_CATEGORY_PROMPT_APPEND;
@@ -22181,19 +22236,40 @@ EXPECTED OUTPUT:
 \`\`\`
 
 If your prompt lacks this structure, REWRITE IT before delegating.
+</Caller_Warning>`, UNSPECIFIED_LOW_CATEGORY_PROMPT_APPEND = `<Category_Context>
+You are working on tasks that don't fit specific categories but require moderate effort.
+
+<Selection_Gate>
+BEFORE selecting this category, VERIFY ALL conditions:
+1. Task does NOT fit: quick (trivial), visual-engineering (UI), ultrabrain (deep logic), artistry (creative), writing (docs)
+2. Task requires more than trivial effort but is NOT system-wide
+3. Scope is contained within a few files/modules
+
+If task fits ANY other category, DO NOT select unspecified-low.
+This is NOT a default choice - it's for genuinely unclassifiable moderate-effort work.
+</Selection_Gate>
+</Category_Context>
+
+<Caller_Warning>
+THIS CATEGORY USES A LIGHTWEIGHT MODEL (gpt-5.6-luna).
+
+**PROVIDE CLEAR STRUCTURE:**
+1. MUST DO: Enumerate required actions explicitly
+2. MUST NOT DO: State forbidden actions to prevent scope creep
+3. EXPECTED OUTPUT: Define concrete success criteria
 </Caller_Warning>`, OPENAI_CATEGORIES;
 var init_openai_categories = __esm(() => {
   init_types3();
   OPENAI_CATEGORIES = [
     {
       name: "ultrabrain",
-      config: { model: "openai/gpt-5.5", variant: "xhigh" },
+      config: { model: "openai/gpt-5.6-sol", variant: "xhigh" },
       description: "Use ONLY for genuinely hard, logic-heavy tasks. Give clear goals only, not step-by-step instructions.",
       promptAppend: ULTRABRAIN_CATEGORY_PROMPT_APPEND
     },
     {
       name: "deep",
-      config: { model: "openai/gpt-5.5", variant: "medium" },
+      config: { model: "openai/gpt-5.6-terra", variant: "xhigh" },
       description: "Goal-oriented autonomous problem-solving on hairy problems requiring deep research. ONE goal + ONE deliverable per call \u2014 multiple goals must fan out as parallel `deep` calls, never bundled into one.",
       promptAppend: DEEP_CATEGORY_PROMPT_APPEND,
       resolvePromptAppend: resolveDeepCategoryPromptAppend
@@ -22203,6 +22279,12 @@ var init_openai_categories = __esm(() => {
       config: { model: "openai/gpt-5.4-mini" },
       description: "Trivial tasks - single file changes, typo fixes, simple modifications",
       promptAppend: QUICK_CATEGORY_PROMPT_APPEND
+    },
+    {
+      name: "unspecified-low",
+      config: { model: "openai/gpt-5.6-luna", variant: "xhigh" },
+      description: "Tasks that don't fit other categories, low effort required",
+      promptAppend: UNSPECIFIED_LOW_CATEGORY_PROMPT_APPEND
     }
   ];
 });
@@ -75205,6 +75287,66 @@ async function probe(registration) {
     return false;
   }
 }
+async function probeSessionAffinity(registration, sessionID) {
+  if (!registration.serverUrl) {
+    return;
+  }
+  const probeUrl = new URL(`/session/${sessionID}`, registration.serverUrl);
+  const authHeader = getServerBasicAuthHeader();
+  const headers = authHeader ? { Authorization: authHeader } : {};
+  try {
+    const controller = new AbortController;
+    const timeoutId = setTimeout(() => controller.abort(), PROBE_ABORT_MS);
+    let response;
+    try {
+      response = await getFetch()(probeUrl, { headers, signal: controller.signal });
+    } finally {
+      clearTimeout(timeoutId);
+    }
+    if (response.ok) {
+      setSessionAffinity(registration, sessionID, true);
+      return true;
+    }
+    if (response.status === 404) {
+      setSessionAffinity(registration, sessionID, false);
+      log2("[live-server-route] live listener does not own session; falling back to in-process client", { sessionID });
+      return false;
+    }
+    return;
+  } catch {
+    return;
+  }
+}
+function setSessionAffinity(registration, sessionID, owned) {
+  const now = Date.now();
+  for (const [key, entry] of registration.sessionAffinity) {
+    if (now - entry.timestamp >= AFFINITY_TTL_MS) {
+      registration.sessionAffinity.delete(key);
+    }
+  }
+  registration.sessionAffinity.set(sessionID, { owned, timestamp: now });
+}
+function getFreshSessionAffinity(registration, sessionID) {
+  const entry = registration.sessionAffinity.get(sessionID);
+  if (!entry || Date.now() - entry.timestamp >= AFFINITY_TTL_MS) {
+    return;
+  }
+  return entry.owned;
+}
+async function resolveSessionAffinity(registration, sessionID) {
+  const cached2 = getFreshSessionAffinity(registration, sessionID);
+  if (cached2 !== undefined) {
+    return cached2;
+  }
+  let inFlight = registration.inFlightAffinity.get(sessionID);
+  if (!inFlight) {
+    inFlight = probeSessionAffinity(registration, sessionID).finally(() => {
+      registration.inFlightAffinity.delete(sessionID);
+    });
+    registration.inFlightAffinity.set(sessionID, inFlight);
+  }
+  return inFlight;
+}
 function getFreshProbeAvailability(registration) {
   const available = registration.available;
   if (available === undefined || Date.now() - registration.probeTimestamp >= PROBE_TTL_MS) {
@@ -75257,6 +75399,13 @@ function tryResolveDispatchClientSync(client3, sessionID) {
   if (!freshAvailability) {
     return { client: client3, route: "in-process", reason: "unavailable" };
   }
+  const cachedAffinity = getFreshSessionAffinity(registration, sessionID);
+  if (cachedAffinity === undefined) {
+    return;
+  }
+  if (!cachedAffinity) {
+    return { client: client3, route: "in-process", reason: "affinity" };
+  }
   const resolvedLiveClient = getOrBuildLiveClient(registration);
   if (!resolvedLiveClient) {
     return { client: client3, route: "in-process", reason: "unavailable" };
@@ -75276,6 +75425,10 @@ async function resolveDispatchClient(client3, sessionID) {
   if (!isAvailable) {
     return { client: client3, route: "in-process", reason: "unavailable" };
   }
+  const affinity = await resolveSessionAffinity(registration, sessionID);
+  if (affinity === false) {
+    return { client: client3, route: "in-process", reason: "affinity" };
+  }
   const resolvedLiveClient = getOrBuildLiveClient(registration);
   if (!resolvedLiveClient) {
     return { client: client3, route: "in-process", reason: "unavailable" };
@@ -75313,10 +75466,11 @@ function markLiveRouteUnavailable(reason) {
   for (const registration of registrations.values()) {
     registration.available = false;
     registration.probeTimestamp = Date.now();
+    registration.sessionAffinity.clear();
   }
   log2(`[live-server-route] marked unavailable: ${reason}`);
 }
-var PROBE_TTL_MS = 60000, PROBE_ABORT_MS = 1500, registrations, liveParentWakeRoutingDisabled = false, fetchImplementationForTesting;
+var PROBE_TTL_MS = 60000, PROBE_ABORT_MS = 1500, AFFINITY_TTL_MS = 60000, registrations, liveParentWakeRoutingDisabled = false, fetchImplementationForTesting;
 var init_live_server_route = __esm(() => {
   init_dist();
   init_state();