oh-my-opencode 4.16.1 → 4.16.3

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/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/dist/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/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-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/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 +20899,16 @@ 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-sol",
+          variant: "high"
+        },
         {
           providers: ["openai", "github-copilot", "opencode", "vercel"],
           model: "gpt-5.5",
@@ -20905,7 +20925,7 @@ 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 +20942,7 @@ 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: {
@@ -20980,7 +21000,7 @@ 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 +21348,22 @@ 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-5.5": {
       id: "gpt-5.5",
       family: "gpt",
@@ -22064,11 +22100,15 @@ 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;
@@ -22187,13 +22227,13 @@ var init_openai_categories = __esm(() => {
   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-sol", variant: "high" },
       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
@@ -75205,6 +75245,66 @@ 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 +75357,13 @@ 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 +75383,10 @@ 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 +75424,11 @@ 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();

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode",
-  "version": "4.16.1",
+  "version": "4.16.3",
   "description": "The Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools",
   "main": "./dist/index.js",
   "types": "dist/index.d.ts",
@@ -210,18 +210,18 @@
     "typescript": "^6.0.3"
   },
   "optionalDependencies": {
-    "oh-my-opencode-darwin-arm64": "4.16.1",
-    "oh-my-opencode-darwin-x64": "4.16.1",
-    "oh-my-opencode-darwin-x64-baseline": "4.16.1",
-    "oh-my-opencode-linux-arm64": "4.16.1",
-    "oh-my-opencode-linux-arm64-musl": "4.16.1",
-    "oh-my-opencode-linux-x64": "4.16.1",
-    "oh-my-opencode-linux-x64-baseline": "4.16.1",
-    "oh-my-opencode-linux-x64-musl": "4.16.1",
-    "oh-my-opencode-linux-x64-musl-baseline": "4.16.1",
-    "oh-my-opencode-windows-arm64": "4.16.1",
-    "oh-my-opencode-windows-x64": "4.16.1",
-    "oh-my-opencode-windows-x64-baseline": "4.16.1"
+    "oh-my-opencode-darwin-arm64": "4.16.3",
+    "oh-my-opencode-darwin-x64": "4.16.3",
+    "oh-my-opencode-darwin-x64-baseline": "4.16.3",
+    "oh-my-opencode-linux-arm64": "4.16.3",
+    "oh-my-opencode-linux-arm64-musl": "4.16.3",
+    "oh-my-opencode-linux-x64": "4.16.3",
+    "oh-my-opencode-linux-x64-baseline": "4.16.3",
+    "oh-my-opencode-linux-x64-musl": "4.16.3",
+    "oh-my-opencode-linux-x64-musl-baseline": "4.16.3",
+    "oh-my-opencode-windows-arm64": "4.16.3",
+    "oh-my-opencode-windows-x64": "4.16.3",
+    "oh-my-opencode-windows-x64-baseline": "4.16.3"
   },
   "overrides": {
     "@earendil-works/pi-agent-core": "0.80.3",

package/packages/omo-codex/plugin/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "omo",
-  "version": "4.16.1",
+  "version": "4.16.3",
   "description": "One Codex plugin namespace for Yeongyu's local Codex components.",
   "author": {
     "name": "Yeongyu Kim",