cursor-route 0.1.14 → 0.1.16

package/CHANGELOG.md

@@ -4,6 +4,18 @@
 
 _(none)_
 
+## 0.1.16 — 2026-09-16
+
+- `--worker opencode --model free` now ranks the **strongest listed-free coding model** by capability tokens (ultra/pro/max > preview > generic > flash/lite), then coding-family, then `context_length`. No locked live winner id.
+- Ox Alpha (`opencode/x-preview-f-free`) is the offline / fetch-fail / empty-catalog **fallback only**, not a live pin. Pin `CURSOR_ROUTE_OPENCODE_MODEL` to freeze an id.
+- `hy3-free` is may-train (−20), not a coding-family boost. Contributor-free is penalized. Mid lane still `claude-ds`; no worker swap. Hero demo fixture regenerated to **0.1.16**.
+
+## 0.1.15 — 2026-09-11
+
+- Mid default is `deepseek-flash` (DeepSeek V4.1 Flash, native vision). `--model pro` and `--model vision` are legacy aliases to the same id. Pro is off rotation.
+- `--model flash|pro|vision` and legacy full ids (`deepseek-flash`, `deepseek-v4-flash`, `deepseek-v4.1-flash`, `deepseek-v4-pro`, `deepseek-v4-pro[1m]`, `deepseek-v4-flash-vision`, `deepseek-v4-flash-vision-exp`) all launch `deepseek-flash`. `job.model` still records the alias the operator passed.
+- Mid lane still `claude-ds`; no worker swap. Hero demo fixture regenerated to **0.1.15**.
+
 ## 0.1.14 — 2026-09-02
 
 - Easy-lane OpenRouter live pick now **tier-ranks** free models like the toolkit: Qwen 100, GLM/Kimi 95, DeepSeek 90, coding/chat families 70, **Nemotron 15**, default 40. Score adds a context bonus capped at 131072 (`tier + min(ctx, 131072)/131072 × 5`) so a huge Nemotron 550B free model can no longer outrank Qwen/GLM/Kimi on context alone.

package/README.md

@@ -29,7 +29,7 @@ If you already live in Cursor, X Premium (Grok CLI), and DeepSeek — stop payin
 | Grok CLI | X Premium | `--lane hard` implement |
 | DeepSeek via claude-ds | DeepSeek API / plan | `--lane mid` implement (**Flash** default; `--model vision` for screenshots; `--model pro` harder mid / hard backup only) |
 | OpenRouter free models | OpenRouter API (free tier) | `--lane easy` live free pick at start — non-secret prompts only (see Security) |
-| OpenCode (opt-in) | OpenCode Zen free models | `--worker opencode` implement on live Zen free pick (Ox Alpha while listed) |
+| OpenCode (opt-in) | OpenCode Zen free models | `--worker opencode` implement on live Zen free pick (strongest listed-free; no locked id) |
 | Codex / extra Claude | Optional | Not required for v0 |
 
 Exact dollars vary — the point is **reuse subscriptions you already have**.
@@ -116,17 +116,17 @@ docs/fixtures/generate-hero-demo.sh      # regenerate docs/fixtures/hero-demo.lo
 
 ```text
 $ cursor-route --version
-0.1.14
+0.1.16
 
 $ CURSOR_ROUTE_RELAXED=1 cursor-route health
-cursor-route v0.1.14
+cursor-route v0.1.16
 health: OK
 
 $ cursor-route start --lane mid --model flash --dry-run "Add a unit test for shellQuote"
 dry-run job a1b2c3d4
 worker: claude-ds
 model:  flash
-command: cd '~/Projects/cursor-route' && '~/.local/bin/claude-ds' -PromptFile '~/.local/share/cursor-route/jobs/a1b2c3d4.prompt' -Model 'deepseek-v4-flash' --dangerously-skip-permissions
+command: cd '~/Projects/cursor-route' && '~/.local/bin/claude-ds' -PromptFile '~/.local/share/cursor-route/jobs/a1b2c3d4.prompt' -Model 'deepseek-flash' --dangerously-skip-permissions
 
 $ cursor-route jobs --json
 []
@@ -145,26 +145,27 @@ A real hero GIF is still pending — recording steps live in [docs/DEMO_GIF.md](
 
 Always-approve is **on** by default for **coding worktrees only**. It does not authorize LIVE Discord, trading, or irreversible SaaS. Opt out: `--ask` or `CURSOR_ROUTE_ASK=1`.
 
-### Mid models (Flash vs Pro)
+### Mid models (Flash)
 
 | Flag | Model id | When |
 |------|----------|------|
-| `--model flash` (default) | `deepseek-v4-flash` | Cheap mid execute. Prefer this when Grok **usage** is out |
-| `--model vision` | `deepseek-v4-flash-vision-exp` | Screenshots / ui mocks / image prompts (or auto-pick) |
-| `--model pro` | `deepseek-v4-pro` | Harder mid / **hard backup** only — not the default Grok-out stand-in |
-| `--model deepseek-v4-pro[1m]` | `deepseek-v4-pro[1m]` | Large-context Pro (SKU preserved) |
+| `--model flash` (default) | `deepseek-flash` | Cheap mid execute. Prefer this when Grok **usage** is out |
+| `--model vision` | `deepseek-flash` | Screenshots / ui mocks / image prompts (or auto-pick). V4.1 Flash has native vision |
+| `--model pro` | `deepseek-flash` | Legacy alias — Pro is off rotation |
+
+This map matches DeepSeek's 2026-09-10 API id `deepseek-flash`. `--model pro` and `--model vision` are legacy aliases to the same id (including `deepseek-v4-pro[1m]`).
 
 ```bash
 cursor-route start --lane mid "…"                    # Flash
-cursor-route start --lane mid --model vision "…"     # Vision Flash
-cursor-route start --lane mid --model pro "…"        # Pro (harder mid / hard backup)
+cursor-route start --lane mid --model vision "…"     # legacy alias → deepseek-flash
+cursor-route start --lane mid --model pro "…"        # legacy alias → deepseek-flash
 # Or set default without a flag:
 export CURSOR_ROUTE_DS_MODEL=flash   # also honors ANTHROPIC_MODEL; --model overrides
 ```
 
-If `--model` and `CURSOR_ROUTE_DS_MODEL` / `ANTHROPIC_MODEL` are unset, a prompt that looks like a screenshot/image/png/jpg/jpeg/webp/ui mock/multimodal/vision auto-picks vision Flash. Explicit `--model flash|pro|vision` always wins.
+If `--model` and `CURSOR_ROUTE_DS_MODEL` / `ANTHROPIC_MODEL` are unset, a prompt that looks like a screenshot/image/png/jpg/jpeg/webp/ui mock/multimodal/vision auto-picks the vision alias (`job.model` is `vision`; launch id is still `deepseek-flash`). Explicit `--model flash|pro|vision` always wins.
 
-**Grok auth ≠ usage-out:** if `cursor-route health` shows `worker:grok` ✗, run `grok login` (or set `XAI_API_KEY`). That is auth, not the Pro case. When Grok **usage** is exhausted, stay on `--lane mid --model flash` (cheap default). `--model pro` is harder mid / hard backup only.
+**Grok auth ≠ usage-out:** if `cursor-route health` shows `worker:grok` ✗, run `grok login` (or set `XAI_API_KEY`). That is auth, not a model switch. When Grok **usage** is exhausted, stay on `--lane mid --model flash` (cheap default). `--model pro` is a legacy alias to `deepseek-flash`.
 
 `CURSOR_ROUTE_ALLOW_ANTHROPIC=1` is an expensive escape hatch: it does **not** pass DeepSeek `--model` ids (Anthropic would reject them).
 
@@ -180,18 +181,18 @@ npm i -g @anthropic-ai/claude-code
 export ANTHROPIC_BASE_URL=https://api.deepseek.com/anthropic
 export ANTHROPIC_AUTH_TOKEN=YOUR_DEEPSEEK_API_KEY   # from platform.deepseek.com
 # Optional shell defaults (CLI --model overrides ANTHROPIC_MODEL for the job):
-export ANTHROPIC_DEFAULT_HAIKU_MODEL=deepseek-v4-flash
-export CLAUDE_CODE_SUBAGENT_MODEL=deepseek-v4-flash
+export ANTHROPIC_DEFAULT_HAIKU_MODEL=deepseek-flash
+export CLAUDE_CODE_SUBAGENT_MODEL=deepseek-flash
 
 cursor-route health          # worker:claude-ds should be ✓; `lane:mid` is ✓ only when DeepSeek is proven
 cursor-route start --lane mid "…"                 # Flash (default; also when Grok usage is out)
-cursor-route start --lane mid --model vision "…"  # screenshots / ui mocks
-cursor-route start --lane mid --model pro "…"     # harder mid / hard backup only
+cursor-route start --lane mid --model vision "…"  # screenshots / ui mocks (same launch id)
+cursor-route start --lane mid --model pro "…"     # legacy alias → deepseek-flash
 ```
 
 Persist the same vars under `~/.claude/settings.json` → `"env": { … }` if you want them every shell.
 
-**Also accepted:** `claude-ds` or `deepseek-claude` on PATH (Cemini shims). The adapter passes `-Model deepseek-v4-flash|deepseek-v4-pro`.
+**Also accepted:** `claude-ds` or `deepseek-claude` on PATH (Cemini shims). The adapter passes `-Model deepseek-flash`.
 
 **Experimental:** `--worker deepseek` runs the official DeepSeek Harness (`dsh`, npm `@deepseek-ai/dsh`) as an opt-in worker — **mid stays on `claude-ds`**; don't default lanes here.
 
@@ -201,10 +202,10 @@ export DEEPSEEK_API_KEY=YOUR_DEEPSEEK_API_KEY   # from platform.deepseek.com
 
 cursor-route health                              # worker:deepseek should be ✓
 cursor-route start --worker deepseek "…"         # Flash (default)
-cursor-route start --worker deepseek --model pro "…"   # harder mid / hard backup only
+cursor-route start --worker deepseek --model pro "…"   # legacy alias → deepseek-flash
 ```
 
-The adapter launches `dsh --profile headless` with a **per-job Cordis patch** (`jobs/<id>.dsh-patch.yml`, mode 0600) that pins `--model flash|pro|vision` (`deepseek-v4-pro[1m]` preserved) — it never rewrites `~/.dsh/settings.yaml`, so parallel jobs don't race. Always-approve maps to `DSH_PERMISSION_MODE=danger-full-access`; `--ask` drops to `workspace-write`. Your `DEEPSEEK_API_KEY` travels via env only — never in the launch command or patch. Override the binary with `CURSOR_ROUTE_DSH_BIN`.
+The adapter launches `dsh --profile headless` with a **per-job Cordis patch** (`jobs/<id>.dsh-patch.yml`, mode 0600) that pins `--model flash|pro|vision` to `deepseek-flash` — it never rewrites `~/.dsh/settings.yaml`, so parallel jobs don't race. Always-approve maps to `DSH_PERMISSION_MODE=danger-full-access`; `--ask` drops to `workspace-write`. Your `DEEPSEEK_API_KEY` travels via env only — never in the launch command or patch. Override the binary with `CURSOR_ROUTE_DSH_BIN`.
 
 **Not the default:** bare `claude` still talking to Anthropic. Health refuses that so a misconfigured install cannot silently burn frontier $ rates. Escape hatch only: `CURSOR_ROUTE_ALLOW_ANTHROPIC=1`.
 
@@ -242,9 +243,10 @@ key-shaped material in `start` / `send`, and the runner re-checks the prompt fil
 ## OpenCode setup (opt-in free coding worker)
 
 `--worker opencode` runs [OpenCode](https://opencode.ai) as a **coding agent** on
-live OpenCode Zen free models (`--model free` fetches the catalog and ranks,
-same idea as the OpenRouter free picker). Ox Alpha (`opencode/x-preview-f-free`)
-wins while it is listed and free. This is **not** a lane default — mid stays
+live OpenCode Zen free models (`--model free` fetches the catalog and ranks the
+strongest listed-free coding model, same idea as the OpenRouter free picker).
+There is no locked live id. Offline / empty-catalog fallback is
+`opencode/x-preview-f-free`. This is **not** a lane default — mid stays
 `claude-ds`; easy stays OpenRouter chat (no tools). Use it to burn fewer Grok /
 DeepSeek tokens on implement work.
 
@@ -270,7 +272,7 @@ for ~15 minutes (`CURSOR_ROUTE_ZEN_CACHE_MINUTES`).
 **Non-secret prompts:** several Zen free models may log or train on prompts during
 their free period (see [OpenCode Zen](https://opencode.ai/docs/zen/) privacy notes).
 The same refuse gate as every lane still applies. `opencode/x-preview-f-free`
-(Ox Alpha) is the zero-retention free option if you need it.
+(Ox Alpha) is the zero-retention **fallback** option if you need it.
 
 ## Jobs directory
 

package/SECURITY.md

@@ -15,7 +15,7 @@ Do **not** open a public issue for credential leaks or RCE-class bugs.
 
 1. **No secrets in prompts or job files.** Do not paste API keys, SSH private keys, Discord tokens, or `.env` contents into `cursor-route start` / `send` prompts.
 2. **Free OpenRouter easy-lane models may log prompts.** `--lane easy` / `--worker openrouter` is for **non-secret** wording/drafts only. The refuse gate (`start` / `send`, plus the runner's re-check) applies to every lane — never send key-shaped material to the easy lane.
-3. **OpenCode Zen free models may log or train during their free period.** `--worker opencode --model free` picks from the live Zen catalog (Ox Alpha / `x-preview-f-free` currently ranks first and is zero-retention). Treat other free Zen models like the easy lane for secrets. Pin `CURSOR_ROUTE_OPENCODE_MODEL` when you need a specific id.
+3. **OpenCode Zen free models may log or train during their free period.** `--worker opencode --model free` ranks the strongest listed-free coding model. Treat free Zen models like the easy lane for secrets. Pin `CURSOR_ROUTE_OPENCODE_MODEL` for a frozen id. Ox Alpha (`opencode/x-preview-f-free`) remains the zero-retention **fallback** option.
 4. **Always-approve is powerful.** Default headless workers skip interactive permission prompts (`--always-approve` / `--dangerously-skip-permissions` / OpenCode `--auto`). Opt out with `--ask` / `CURSOR_ROUTE_ASK=1` when you need HITL.
 5. **Install from known channels only.** Prefer `npm i -g cursor-route` or a git clone of this repo. Do not pipe unknown `curl | bash` installers as the primary path.
 6. **Workers inherit your auth.** Grok CLI, Claude Code / claude-ds, and OpenCode use *your* local login. Treat worker panes like you would treat your own shell.

package/dist/adapters/claude-ds.js

@@ -128,8 +128,16 @@ export function midDeepSeekProofDetail() {
 }
 function pickModel(requested, modelId) {
     if (modelId) {
-        const alias = requested ?? resolveDsModel(modelId).alias;
-        return { alias, id: modelId };
+        try {
+            const resolved = resolveDsModel(modelId);
+            return { alias: requested ?? resolved.alias, id: resolved.id };
+        }
+        catch (e) {
+            // Unknown id with an explicit alias: keep the raw id so dsh YAML checks can still reject it.
+            if (requested)
+                return { alias: requested, id: modelId };
+            throw e;
+        }
     }
     if (requested) {
         return { alias: requested, id: DS_MODEL_IDS[requested] };

package/dist/adapters/deepseek.js

@@ -32,8 +32,16 @@ function findDsh() {
 /** Same resolution as claude-ds: passed model/modelId wins, else env, else Flash. */
 function pickModel(requested, modelId) {
     if (modelId) {
-        const alias = requested ?? resolveDsModel(modelId).alias;
-        return { alias, id: modelId };
+        try {
+            const resolved = resolveDsModel(modelId);
+            return { alias: requested ?? resolved.alias, id: resolved.id };
+        }
+        catch (e) {
+            // Unknown id with an explicit alias: keep the raw id so YAML checks can still reject it.
+            if (requested)
+                return { alias: requested, id: modelId };
+            throw e;
+        }
     }
     if (requested) {
         return { alias: requested, id: DS_MODEL_IDS[requested] };

package/dist/adapters/opencode.js

@@ -4,9 +4,9 @@ import { shellQuote } from "../util.js";
 import { openCodeModel, OPENCODE_DEFAULT_MODEL, cachedZenFreePick } from "../config.js";
 /**
  * Opt-in OpenCode worker (`opencode run`) — a coding agent on live OpenCode
- * Zen free models (`--model free` ranks the catalog; Ox Alpha wins while
- * listed). Not a lane default: mid stays claude-ds; easy stays OpenRouter
- * chat (no tools).
+ * Zen free models (`--model free` ranks the strongest listed-free coding
+ * model). Not a lane default: mid stays claude-ds; easy stays OpenRouter
+ * chat (no tools). Pin `CURSOR_ROUTE_OPENCODE_MODEL` to freeze an id.
  *
  * We never rewrite ~/.config/opencode/opencode.json (parallel jobs would
  * race). Always-approve maps to `opencode run --auto` (still honors explicit
@@ -42,7 +42,7 @@ export const opencodeAdapter = {
                 detail: "opencode not found — install: npm i -g opencode-ai (or brew install opencode). Then: opencode auth login. Mid default remains claude-ds.",
             };
         }
-        // Health stays offline: show a fresh cache hit, else the Ox Alpha fallback.
+        // Health stays offline: show a fresh cache hit, else the fallback id.
         const pick = cachedZenFreePick() || OPENCODE_DEFAULT_MODEL;
         return {
             worker: "opencode",

package/dist/cli.js

@@ -31,7 +31,7 @@ Usage:
 Start options:
   --worker <grok|claude-ds|openrouter|deepseek|opencode>  Worker adapter (default: grok; deepseek/opencode = opt-in)
   --lane <easy|mid|hard>                Lane → worker (easy=openrouter, mid=claude-ds, hard=grok)
-  --model <flash|pro|vision|free|provider/model>  claude-ds/deepseek: flash|pro|vision. opencode/openrouter: free (live catalog pick) or provider/model
+  --model <flash|pro|vision|free|provider/model>  claude-ds/deepseek: flash|pro|vision (aliases map to deepseek-flash). opencode/openrouter: free (live catalog pick) or provider/model
   --dir <path>                          Working directory (default: cwd)
   --ask                                 Disable always-approve for this job
   --dry-run                             Print launch command; do not start
@@ -44,7 +44,7 @@ Env:
   CURSOR_ROUTE_MAX_JOBS              Max active jobs (default: 50)
   CURSOR_ROUTE_RELAXED=1             health OK without tmux/workers (CI / infra smoke)
   CURSOR_ROUTE_ALLOW_ANTHROPIC=1     Allow mid-lane on Anthropic Claude (expensive; not default; --model ignored)
-  CURSOR_ROUTE_DS_MODEL              Default mid model flash|pro|vision (or full ids / deepseek-v4-pro[1m]); overridden by --model
+  CURSOR_ROUTE_DS_MODEL              Default mid model flash|pro|vision (aliases map to deepseek-flash); overridden by --model
   CURSOR_ROUTE_GROK_BIN              Override the grok binary path (tests / power users)
   CURSOR_ROUTE_CLAUDE_DS_BIN         Override the claude-ds binary path (tests / power users)
   CURSOR_ROUTE_DSH_BIN               Override the dsh binary path (tests / power users)

package/dist/config.js

@@ -4,10 +4,12 @@ import { defaultJobsDir } from "./runtime.js";
 export const WORKERS = ["grok", "claude-ds", "openrouter", "deepseek", "opencode"];
 export const LANES = ["easy", "mid", "hard"];
 export const DS_MODELS = ["flash", "pro", "vision"];
+/** DeepSeek V4.1 Flash (native vision). Matches the 2026-09-10 API id. */
+export const DS_FLASH_ID = "deepseek-flash";
 export const DS_MODEL_IDS = {
-    flash: "deepseek-v4-flash",
-    pro: "deepseek-v4-pro",
-    vision: "deepseek-v4-flash-vision-exp",
+    flash: DS_FLASH_ID,
+    pro: DS_FLASH_ID,
+    vision: DS_FLASH_ID,
 };
 /** Prompt looks like a screenshot / image / ui mock — vision auto-pick. */
 const VISION_PROMPT_RE = /screenshot|\bimage\b|\.png|\.jpe?g|\.webp|ui mock|multimodal|\bvision\b/i;
@@ -15,26 +17,31 @@ export function promptLooksLikeVision(prompt) {
     return VISION_PROMPT_RE.test(prompt);
 }
 /**
- * Resolve --model / env to alias + concrete model id.
- * Preserves `deepseek-v4-pro[1m]` (does not silently strip the SKU).
+ * Resolve --model / env to alias + launch id.
+ * V4.1 Flash is native vision; Pro is a legacy alias, not a rotation step.
+ * All known aliases launch `deepseek-flash`.
  * Empty → Flash.
  */
 export function resolveDsModel(raw) {
     if (!raw || !raw.trim()) {
-        return { alias: "flash", id: DS_MODEL_IDS.flash };
+        return { alias: "flash", id: DS_FLASH_ID };
     }
-    const v = raw.trim().toLowerCase();
-    if (v === "flash" || v === "deepseek-v4-flash") {
-        return { alias: "flash", id: DS_MODEL_IDS.flash };
+    // Trim, lower-case, strip a trailing `[…]` SKU (`deepseek-v4-pro[1m]` → `deepseek-v4-pro`).
+    const v = raw.trim().toLowerCase().replace(/\[[^\]]*\]\s*$/, "");
+    if (v === "flash" ||
+        v === "deepseek-flash" ||
+        v === "deepseek-v4-flash" ||
+        v === "deepseek-v4.1-flash") {
+        return { alias: "flash", id: DS_FLASH_ID };
     }
     if (v === "pro" || v === "deepseek-v4-pro") {
-        return { alias: "pro", id: DS_MODEL_IDS.pro };
+        return { alias: "pro", id: DS_FLASH_ID };
     }
-    if (v === "vision" || v === "deepseek-v4-flash-vision-exp") {
-        return { alias: "vision", id: DS_MODEL_IDS.vision };
-    }
-    if (v === "deepseek-v4-pro[1m]") {
-        return { alias: "pro", id: "deepseek-v4-pro[1m]" };
+    if (v === "vision" ||
+        v === "flash-vision" ||
+        v === "deepseek-v4-flash-vision" ||
+        v === "deepseek-v4-flash-vision-exp") {
+        return { alias: "vision", id: DS_FLASH_ID };
     }
     throw new Error(`Invalid DeepSeek model ${raw}; expected flash|pro|vision`);
 }
@@ -72,7 +79,7 @@ function maxConcurrentJobsFromEnv() {
  */
 export const config = {
     product: "cursor-route",
-    version: "0.1.14",
+    version: "0.1.16",
     get jobsDir() {
         return defaultJobsDir();
     },

package/dist/zen-free.js

@@ -11,12 +11,15 @@ import { join } from "node:path";
  * `big-pickle` / `x-preview-f-free`; the CLI wants `opencode/<id>`.
  */
 export const ZEN_MODELS_URL_DEFAULT = "https://opencode.ai/zen/v1/models";
-/** Offline / fetch-fail fallback — Ox Alpha (zero-retention, currently top-tier free). */
+/** Offline / fetch-fail fallback only — not a live pin. */
 export const OPENCODE_DEFAULT_MODEL = "opencode/x-preview-f-free";
 const EXCLUDE_RE = /lyria|whisper|tts|embed|embedding|image|vision-only|audio|diffusion|flux|stable-diffusion|moderation/i;
-const CODING_RE = /coder|instruct|chat|laguna|nemotron|glm|qwen|kimi|deepseek|mimo|hy3|gpt-oss|north|gemma/i;
-const OX_ALPHA_RE = /x-preview|ox-alpha|oxalpha/i;
-const CONTRIBUTOR_RE = /contributor-free/i;
+const POWER_ULTRA_RE = /ultra|(^|[-/])opus($|[-/])|(^|[-/_])pro($|[-/])|(^|[-/])max($|[-/])|plus|(^|[-/])large($|[-/])/;
+const POWER_PREVIEW_RE = /x-preview|ox-alpha|oxalpha|(^|[-/])alpha($|[-/])|preview/;
+const POWER_FLASH_RE = /flash|lightning|lite|mini|nano|small|haiku|fin-/;
+const CODING_FAMILY_RE = /coder|code|instruct|laguna|glm|qwen|kimi|deepseek|gpt-oss|north|gemma|nemotron|mimo|muse/;
+const CONTRIBUTOR_RE = /contributor-free/;
+const MAY_TRAIN_RE = /(^|\/)big-pickle$|(^|\/)hy3-free$/;
 function zenModelsUrl() {
     return (process.env.CURSOR_ROUTE_ZEN_MODELS_URL || ZEN_MODELS_URL_DEFAULT).trim();
 }
@@ -65,20 +68,32 @@ export function isZenFreeModel(m) {
         /(^|\/)big-pickle$/i.test(id);
     return tagged || pricedFree;
 }
-/** Higher boost wins. Ox Alpha first while it is in the free catalog. */
+/**
+ * Higher boost wins. Generic capability tokens only — never a locked model id.
+ * Coding-family matches the model slug so the provider `opencode/` does not
+ * trip `code`.
+ */
 export function zenFreeBoost(id) {
     const s = id.toLowerCase();
-    if (OX_ALPHA_RE.test(s))
-        return 40;
+    const slug = s.includes("/") ? s.slice(s.lastIndexOf("/") + 1) : s;
+    let score = 0;
+    if (POWER_ULTRA_RE.test(s))
+        score += 50;
+    else if (POWER_PREVIEW_RE.test(s))
+        score += 42;
+    else if (POWER_FLASH_RE.test(s))
+        score += 15;
+    else
+        score += 30;
+    if (CODING_FAMILY_RE.test(slug))
+        score += 20;
+    else if (s.endsWith("-free") || s.endsWith(":free"))
+        score += 10;
     if (CONTRIBUTOR_RE.test(s))
-        return 1;
-    if (CODING_RE.test(s))
-        return 20;
-    if (s.endsWith("-free") || s.endsWith(":free"))
-        return 10;
-    if (/(^|\/)big-pickle$/.test(s))
-        return 5;
-    return 0;
+        score -= 25;
+    if (MAY_TRAIN_RE.test(s))
+        score -= 20;
+    return score;
 }
 export function rankZenFreeModels(models) {
     const out = [];

package/docs/briefs/WORKING.md

@@ -1,9 +1,9 @@
 ---
 title: cursor-route workspace — working brief (edit in place)
 repo: ~/Projects/cursor-route
-npm: cursor-route@0.1.14 (not yet published — Kimi audit next)
+npm: cursor-route@0.1.16
 created: 2026-08-12
-updated: 2026-09-02
+updated: 2026-09-16
 ---
 
 # cursor-route — living brief
@@ -19,13 +19,13 @@ Cursor Agent plans. Workers run in tmux via `cursor-route`:
 | Lane | Worker | Intent |
 |------|--------|--------|
 | `easy` | OpenRouter free (live pick) | Wording / drafts — non-secret prompts only |
-| `mid` | claude-ds (DeepSeek behind Claude Code) | Default implement (**Flash**; `--model vision` for screenshots; `--model pro` harder mid / hard backup only) |
+| `mid` | claude-ds (DeepSeek behind Claude Code) | Default implement (**Flash** `deepseek-flash`; `--model vision` / `--model pro` are legacy aliases to the same id) |
 | `hard` | Grok CLI | Hard implement |
-| opt-in | OpenCode | `--worker opencode` coding agent; `--model free` ranks live Zen catalog (Ox Alpha first while listed) |
+| opt-in | OpenCode | `--worker opencode` coding agent; `--model free` ranks strongest listed-free Zen coding model (no locked id; offline fallback `opencode/x-preview-f-free`) |
 
 Always-approve on for coding worktrees (`--ask` / `CURSOR_ROUTE_ASK=1` to opt out) — not LIVE Discord/trading. Jobs live in `~/.local/share/cursor-route/jobs`, not in this clone.
 
-Install: `npm i -g cursor-route` → **0.1.13**. Release notes: [CHANGELOG.md](../../CHANGELOG.md).
+Install: `npm i -g cursor-route` → **0.1.16** (parent publishes). Release notes: [CHANGELOG.md](../../CHANGELOG.md).
 
 ## Open (edit / check off)
 
@@ -44,7 +44,9 @@ Install: `npm i -g cursor-route` → **0.1.13**. Release notes: [CHANGELOG.md](.
 - [x] **Flash-first + vision + live OpenRouter pick** — 0.1.12: `--model flash` stays the cheap Grok-out default; `--model vision` + screenshot auto-pick; easy lane live-picks free OpenRouter text models (`openrouter/free` is fetch-fail fallback only). Health never fetches `/models`. `route-orch` ProgRouter + MoRe one-liners. Hero fixture regenerated to 0.1.12. No npm publish in this slice.
 - [x] **Kimi 0.1.13 follow-up** — do not cache OpenRouter fallback; health labels uncached fallback; no Authorization on GET /models; env-invalid model error names the env vars; `\bimage\b` vision trigger.
 - [x] **Super-audit OR ranker parity (0.1.14)** — tier-rank Qwen/GLM/Kimi above Nemotron 550B in `or-free.ts` (match agent-toolkit `select-openrouter-free-model.ps1`); brief `docs/briefs/2026-09-02_super-audit-or-ranker-parity.md`
+- [x] **V4.1 Flash wire (0.1.15)** — mid default `deepseek-flash` (native vision). `--model pro` / `--model vision` are legacy aliases to the same id. Pro is off rotation. Mid still `claude-ds`. Hero fixture regenerated. Brief `docs/briefs/2026-09-11_v41-flash-not-pro.md`
 - [ ] **Hero GIF** — still outstanding; dry-run fixture ships as the substitute for now (`docs/fixtures/hero-demo.log` — see `docs/DEMO_GIF.md`)
+- [x] **Zen strongest-free ranker (0.1.16)** — `zenFreeBoost` ports capability tokens (ultra/pro/max > preview > generic > flash/lite), then coding-family, then `context_length`. No locked live id. Ox Alpha is offline fallback only. SIP: `docs/briefs/2026-09-16_zen-strongest-free.md`. Mid still `claude-ds`.
 - [x] **Do not** paste private `ROUTE_KIT`, SIP, prod paths, or hang-watchdog env into this public repo
 
 ## Repo map
@@ -81,4 +83,8 @@ Install: `npm i -g cursor-route` → **0.1.13**. Release notes: [CHANGELOG.md](.
 | 2026-08-21 | Live Zen free pick (Ox Alpha first while listed; OpenRouter-style catalog rank) → 0.1.11 LIVE. |
 | 2026-08-29 | Flash-first docs, `--model vision` + auto-pick, live OpenRouter free pick, route-orch K318/K322, hero fixture 0.1.12. No npm publish. |
 | 2026-08-29 | Kimi audit follow-up → 0.1.13 LIVE on npm: no fallback cache, health labels, unauth GET /models, env error wording. |
-| 2026-09-02 | Tier-rank OpenRouter free picks in `or-free.ts` (Qwen 100 / GLM-Kimi 95 / DeepSeek 90 / coding 70 / Nemotron 15 / default 40; ctx bonus capped at 131072) → 0.1.14. Commit + tag `v0.1.14`. **No npm publish** — parent Kimi-audits then publishes. Mid stays claude-ds. |
+| 2026-09-02 | Tier-rank OpenRouter free picks in `or-free.ts` (Qwen 100 / GLM-Kimi 95 / DeepSeek 90 / coding 70 / Nemotron 15 / default 40; ctx bonus capped at 131072) → 0.1.14. Commit + tag `v0.1.14`. Mid stays claude-ds. |
+| 2026-09-02 | Kimi audit follow-up → ranker tests (seven tiers, score/id ties, 131072 cap, cache round-trip) then **0.1.14 LIVE** on npm. |
+| 2026-09-11 | Map mid models to `deepseek-flash` (V4.1 Flash, native vision). `--model pro` / `--model vision` are legacy aliases. Pro is off rotation. Mid still `claude-ds` → **0.1.15 LIVE** on npm. |
+| 2026-09-16 | Pickup brief: `docs/briefs/2026-09-16_zen-strongest-free.md`. Port private `/route` Zen capability-token ranker so `--model free` picks strongest listed-free coding model. Target npm `0.1.16`. Open checkbox added. |
+| 2026-09-16 | Ship Zen strongest-free ranker → **0.1.16** (commit + tag; parent publishes npm). Ox Alpha is offline fallback only, not a live pin. Mid still `claude-ds`. |

package/docs/demo-notes.md

@@ -6,10 +6,10 @@ Simulated capture output for README / tweet assets — replace with a real GIF o
 
 ```
 $ cursor-route --version
-0.1.14
+0.1.16
 
 $ cursor-route health
-cursor-route v0.1.14
+cursor-route v0.1.16
 health: OK
   ✓ tmux
   ✓ runtime          bun ok
@@ -32,7 +32,7 @@ $ cursor-route jobs --json
 
 Verified locally (2026-08-10): headless `claude-ds` smoke returned `CURSOR_ROUTE_SMOKE_OK`.
 Grok smoke hit 402 (Build usage balance exhausted) — auth/PATH wiring works; top up Grok Build for live demos.
-Use `--model flash` when Grok **usage** is out (cheap default). `--model pro` is harder mid / hard backup only — not the default Grok-out stand-in. A missing `grok login` is auth, not the Pro case.
+Use `--model flash` when Grok **usage** is out (cheap default). `--model pro` and `--model vision` are legacy aliases to `deepseek-flash`. A missing `grok login` is auth, not a model switch.
 
 Current commands: `health`, `start`, `jobs`, `status`, `capture`, `send`, `attach`, `kill`, `sessions`, `clean`.
 Headless demos (no tmux) use `--no-tmux` and `capture`/`status` instead of `attach`/`send`.

package/docs/fixtures/hero-demo.log

@@ -1,15 +1,15 @@
 $ cursor-route --version
-0.1.14
+0.1.16
 
 $ CURSOR_ROUTE_RELAXED=1 cursor-route health
-cursor-route v0.1.14
+cursor-route v0.1.16
 health: OK
 
   ✓ tmux             ok
   ✓ runtime          bun ok
   ✓ script(1)        ok (tty log capture)
   ✓ worker:grok      ok (auth checked at first start — run grok login if jobs fail) @ ~/.grok/bin/grok
-  ✓ worker:claude-ds ok (claude-ds (DeepSeek shim); default model deepseek-v4-flash) @ ~/.local/bin/claude-ds
+  ✓ worker:claude-ds ok (claude-ds (DeepSeek shim); default model deepseek-flash) @ ~/.local/bin/claude-ds
   ✗ worker:openrouter OPENROUTER_API_KEY not set — export your OpenRouter key (easy lane live-picks a free model at start; pin with CURSOR_ROUTE_OPENROUTER_MODEL) @ node '~/Projects/cursor-route/dist/openrouter-run.js'
   ✗ worker:deepseek  dsh (@deepseek-ai/dsh) not found — install: npm i -g @deepseek-ai/dsh. Mid default remains claude-ds.
   ✓ worker:opencode  ok (opencode run; --model free = live Zen pick, now opencode/x-preview-f-free; auth at first start — opencode auth login if jobs fail; mid default remains claude-ds) @ ~/.local/bin/opencode
@@ -22,7 +22,7 @@ $ cursor-route start --lane mid --model flash --dry-run "Add a unit test for she
 dry-run job a1b2c3d4
 worker: claude-ds
 model:  flash
-command: cd '~/Projects/cursor-route' && '~/.local/bin/claude-ds' -PromptFile '~/.local/share/cursor-route/jobs/a1b2c3d4.prompt' -Model 'deepseek-v4-flash' --dangerously-skip-permissions
+command: cd '~/Projects/cursor-route' && '~/.local/bin/claude-ds' -PromptFile '~/.local/share/cursor-route/jobs/a1b2c3d4.prompt' -Model 'deepseek-flash' --dangerously-skip-permissions
 
 $ cursor-route start --lane easy --dry-run "Rewrite this FAQ answer in 3 sentences"
 dry-run job b2c3d4e5
@@ -48,7 +48,7 @@ $ cursor-route start --lane mid --dry-run --json "Add a failing test then make i
   "alwaysApprove": true,
   "tmuxSession": "cursor-route-d4e5f6a7",
   "createdAt": "2026-08-13T00:00:00.000Z",
-  "command": "cd '~/Projects/cursor-route' && '~/.local/bin/claude-ds' -PromptFile '~/.local/share/cursor-route/jobs/d4e5f6a7.prompt' -Model 'deepseek-v4-flash' --dangerously-skip-permissions"
+  "command": "cd '~/Projects/cursor-route' && '~/.local/bin/claude-ds' -PromptFile '~/.local/share/cursor-route/jobs/d4e5f6a7.prompt' -Model 'deepseek-flash' --dangerously-skip-permissions"
 }
 
 $ cursor-route jobs --json

package/llms.txt

@@ -2,30 +2,31 @@
 
 > Cursor stays the planner. DeepSeek (mid), Grok CLI (hard), and OpenRouter free models (easy) run parallel coding workers in tmux. `--worker opencode` is an opt-in coding agent on OpenCode Zen free models.
 
-MIT CLI + Cursor skill. npm: https://www.npmjs.com/package/cursor-route (latest **0.1.14**)
+MIT CLI + Cursor skill. npm: https://www.npmjs.com/package/cursor-route (latest **0.1.16**)
 GitHub: https://github.com/cemini23/cursor-route
 
 ## FAQ
 
 ### What is cursor-route?
-cursor-route is a public MIT CLI and Cursor skill that runs parallel coding workers in tmux while Cursor remains the planner. DeepSeek handles the mid lane, Grok CLI handles the hard lane, and OpenRouter free models handle the easy lane (wording/drafts, non-secret prompts only). `--worker opencode` is an opt-in coding agent (`--model free` ranks the live Zen catalog; Ox Alpha wins while listed) — not a lane default.
+cursor-route is a public MIT CLI and Cursor skill that runs parallel coding workers in tmux while Cursor remains the planner. DeepSeek handles the mid lane, Grok CLI handles the hard lane, and OpenRouter free models handle the easy lane (wording/drafts, non-secret prompts only). `--worker opencode` is an opt-in coding agent (`--model free` ranks the strongest listed-free Zen coding model; pin to freeze) — not a lane default.
 
 ### How is this different from Codex orchestrator?
 It uses the familiar strategist and worker-pane shape, but it is not a Codex clone. cursor-route uses Cursor as the planner and DeepSeek plus Grok CLI as workers. Codex is not required.
 
 ### Does mid lane use Anthropic Claude?
-No. The mid worker is DeepSeek. Claude Code is the harness, configured with `ANTHROPIC_BASE_URL=https://api.deepseek.com/anthropic` and a DeepSeek key in `ANTHROPIC_AUTH_TOKEN`. Default model is Flash (`--model flash`) — keep Flash when Grok **usage** is out. `--model vision` is for screenshots / ui mocks. `--model pro` is harder mid / **hard backup only**, not the default Grok-out stand-in. A missing `grok login` is auth, not the Pro case.
+No. The mid worker is DeepSeek. Claude Code is the harness, configured with `ANTHROPIC_BASE_URL=https://api.deepseek.com/anthropic` and a DeepSeek key in `ANTHROPIC_AUTH_TOKEN`. Default model is Flash (`--model flash` → `deepseek-flash`) — keep Flash when Grok **usage** is out. `--model vision` and `--model pro` are legacy aliases to the same id. A missing `grok login` is auth, not a model switch.
 
 ### Flash vs Pro?
 | Flag | Model | When |
 |------|-------|------|
-| `--model flash` (default) | `deepseek-v4-flash` | Cheap mid execute. Prefer this when Grok **usage** is out |
-| `--model vision` | `deepseek-v4-flash-vision-exp` | Screenshots / ui mocks / image prompts (or auto-pick) |
-| `--model pro` | `deepseek-v4-pro` | Harder mid / **hard backup** only — not the default Grok-out stand-in |
-| `--model deepseek-v4-pro[1m]` | preserved SKU | Large-context Pro |
+| `--model flash` (default) | `deepseek-flash` | Cheap mid execute. Prefer this when Grok **usage** is out |
+| `--model vision` | `deepseek-flash` | Screenshots / ui mocks / image prompts (or auto-pick). V4.1 Flash has native vision |
+| `--model pro` | `deepseek-flash` | Legacy alias — Pro is off rotation |
+
+This map matches DeepSeek's 2026-09-10 API id `deepseek-flash`.
 
 ### How do I use OpenCode free models?
-Install OpenCode (`npm i -g opencode-ai`), run `opencode auth login`, then `cursor-route start --worker opencode "…"`. `--model free` ranks live Zen free models (Ox Alpha first while listed). Mid stays `claude-ds`.
+Install OpenCode (`npm i -g opencode-ai`), run `opencode auth login`, then `cursor-route start --worker opencode "…"`. `--model free` ranks the strongest listed-free Zen coding model (offline fallback `opencode/x-preview-f-free`). Mid stays `claude-ds`.
 
 ### How do I install?
 Run `npm i -g cursor-route`, install tmux if needed, then run `cursor-route health`. Copy the Cursor skill from `$(npm root -g)/cursor-route/skills/route-orch`. Source: https://github.com/cemini23/cursor-route
@@ -37,6 +38,6 @@ The cursor-route code is open source under MIT. It does not make the worker serv
 
 - npm: `npm i -g cursor-route`
 - Health: `cursor-route health`
-- Mid: `cursor-route start --lane mid "…"` (Flash; keep Flash when Grok usage is out) · `--model vision` for screenshots · `--model pro` harder mid / hard backup only
+- Mid: `cursor-route start --lane mid "…"` (Flash `deepseek-flash`; keep Flash when Grok usage is out) · `--model vision` / `--model pro` are legacy aliases to the same id
 - OpenCode (opt-in): `cursor-route start --worker opencode "…"`
 - Skill: `/route-orch` (Cursor)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "cursor-route",
-  "version": "0.1.14",
+  "version": "0.1.16",
   "description": "Cursor stays the brain. Grok CLI + DeepSeek (claude-ds) + OpenRouter easy lane + OpenCode (opt-in free) are the parallel army \u2014 lane-aware /route orchestration in tmux.",
   "type": "module",
   "license": "MIT",

package/skills/route-orch/SKILL.md

@@ -36,10 +36,11 @@ One harness. Do not install a second coding loop.
 
 | Flag | Model id | When |
 |------|----------|------|
-| `--model flash` (default) | `deepseek-v4-flash` | Cheap mid execute. Prefer this when Grok **usage** is out |
-| `--model vision` | `deepseek-v4-flash-vision-exp` | Screenshots / ui mocks / image prompts (or auto-pick) |
-| `--model pro` | `deepseek-v4-pro` | Harder mid / **hard backup** only — not the default Grok-out stand-in |
-| `--model deepseek-v4-pro[1m]` | preserved SKU | Large-context Pro |
+| `--model flash` (default) | `deepseek-flash` | Cheap mid execute. Prefer this when Grok **usage** is out |
+| `--model vision` | `deepseek-flash` | Screenshots / ui mocks / image prompts (or auto-pick) |
+| `--model pro` | `deepseek-flash` | Legacy alias — Pro is off rotation |
+
+V4.1 Flash has native vision; `--model pro` is a legacy alias (off rotation).
 
 ```bash
 cursor-route start --lane mid --dir "$PWD" "…"
@@ -47,7 +48,7 @@ cursor-route start --lane mid --model vision --dir "$PWD" "…"
 cursor-route start --lane mid --model pro --dir "$PWD" "…"
 ```
 
-If `worker:grok` is ✗ on health, that is usually **auth** (`grok login` / `XAI_API_KEY`) — not the Pro case. When Grok **usage** is out, stay on Flash.
+If `worker:grok` is ✗ on health, that is usually **auth** (`grok login` / `XAI_API_KEY`) — not a model switch. When Grok **usage** is out, stay on Flash.
 
 ## Experimental: --worker deepseek (dsh)
 
@@ -74,7 +75,7 @@ cursor-route start --worker opencode --model free --dir "$PWD" "…"
 cursor-route start --worker opencode --model opencode/hy3-free --dir "$PWD" "…"
 ```
 
-Health ✓ needs `opencode` on PATH (override `CURSOR_ROUTE_OPENCODE_BIN`). `--model free` / unset ranks the live OpenCode Zen catalog (Ox Alpha first while listed; pin with `CURSOR_ROUTE_OPENCODE_MODEL` or `--model provider/model`). Always-approve → `opencode run --auto`; `--ask` omits `--auto`. Never rewrites `~/.config/opencode/opencode.json`. Free Zen models may log/train — keep secrets off this worker (same refuse gate as easy). Ox Alpha (`opencode/x-preview-f-free`) is the zero-retention free option.
+Health ✓ needs `opencode` on PATH (override `CURSOR_ROUTE_OPENCODE_BIN`). `--model free` / unset ranks the strongest listed-free OpenCode Zen coding model (pin with `CURSOR_ROUTE_OPENCODE_MODEL` or `--model provider/model` to freeze). Always-approve → `opencode run --auto`; `--ask` omits `--auto`. Never rewrites `~/.config/opencode/opencode.json`. Free Zen models may log/train — keep secrets off this worker (same refuse gate as easy). Ox Alpha (`opencode/x-preview-f-free`) is the zero-retention fallback option.
 
 ## Workflow
 

package/src/adapters/claude-ds.ts

@@ -145,8 +145,14 @@ export function midDeepSeekProofDetail(): string {
 
 function pickModel(requested?: DsModelAlias, modelId?: string): { alias: DsModelAlias; id: string } {
   if (modelId) {
-    const alias = requested ?? resolveDsModel(modelId).alias;
-    return { alias, id: modelId };
+    try {
+      const resolved = resolveDsModel(modelId);
+      return { alias: requested ?? resolved.alias, id: resolved.id };
+    } catch (e) {
+      // Unknown id with an explicit alias: keep the raw id so dsh YAML checks can still reject it.
+      if (requested) return { alias: requested, id: modelId };
+      throw e;
+    }
   }
   if (requested) {
     return { alias: requested, id: DS_MODEL_IDS[requested] };

package/src/adapters/deepseek.ts

@@ -43,8 +43,14 @@ function pickModel(
   modelId?: string,
 ): { alias: DsModelAlias; id: string } {
   if (modelId) {
-    const alias = requested ?? resolveDsModel(modelId).alias;
-    return { alias, id: modelId };
+    try {
+      const resolved = resolveDsModel(modelId);
+      return { alias: requested ?? resolved.alias, id: resolved.id };
+    } catch (e) {
+      // Unknown id with an explicit alias: keep the raw id so YAML checks can still reject it.
+      if (requested) return { alias: requested, id: modelId };
+      throw e;
+    }
   }
   if (requested) {
     return { alias: requested, id: DS_MODEL_IDS[requested] };

package/src/adapters/opencode.test.ts

@@ -11,7 +11,7 @@ import {
 } from "../config.ts";
 
 describe("openCodeModel", () => {
-  test("defaults to live Zen pick (Ox Alpha fallback when offline)", () => {
+  test("defaults to live Zen pick (fallback id when offline)", () => {
     const prev = {
       model: process.env.CURSOR_ROUTE_OPENCODE_MODEL,
       offline: process.env.CURSOR_ROUTE_ZEN_OFFLINE,

package/src/adapters/opencode.ts

@@ -6,9 +6,9 @@ import { openCodeModel, OPENCODE_DEFAULT_MODEL, cachedZenFreePick } from "../con
 
 /**
  * Opt-in OpenCode worker (`opencode run`) — a coding agent on live OpenCode
- * Zen free models (`--model free` ranks the catalog; Ox Alpha wins while
- * listed). Not a lane default: mid stays claude-ds; easy stays OpenRouter
- * chat (no tools).
+ * Zen free models (`--model free` ranks the strongest listed-free coding
+ * model). Not a lane default: mid stays claude-ds; easy stays OpenRouter
+ * chat (no tools). Pin `CURSOR_ROUTE_OPENCODE_MODEL` to freeze an id.
  *
  * We never rewrite ~/.config/opencode/opencode.json (parallel jobs would
  * race). Always-approve maps to `opencode run --auto` (still honors explicit
@@ -47,7 +47,7 @@ export const opencodeAdapter: Adapter = {
           "opencode not found — install: npm i -g opencode-ai (or brew install opencode). Then: opencode auth login. Mid default remains claude-ds.",
       };
     }
-    // Health stays offline: show a fresh cache hit, else the Ox Alpha fallback.
+    // Health stays offline: show a fresh cache hit, else the fallback id.
     const pick = cachedZenFreePick() || OPENCODE_DEFAULT_MODEL;
     return {
       worker: "opencode",

package/src/cli.test.ts

@@ -52,24 +52,32 @@ describe("resolveWorker", () => {
 
 describe("resolveDsModel", () => {
   test("defaults to flash", () => {
-    expect(resolveDsModel()).toEqual({ alias: "flash", id: "deepseek-v4-flash" });
+    expect(resolveDsModel()).toEqual({ alias: "flash", id: "deepseek-flash" });
+    expect(resolveDsModel("  ")).toEqual({ alias: "flash", id: "deepseek-flash" });
     expect(resolveDsModelAlias("")).toBe("flash");
   });
   test("accepts aliases and full ids", () => {
-    expect(resolveDsModel("flash").id).toBe("deepseek-v4-flash");
-    expect(resolveDsModel("pro").id).toBe("deepseek-v4-pro");
-    expect(resolveDsModel("vision").id).toBe("deepseek-v4-flash-vision-exp");
-    expect(resolveDsModel("deepseek-v4-flash-vision-exp")).toEqual({
+    expect(resolveDsModel("flash")).toEqual({ alias: "flash", id: "deepseek-flash" });
+    expect(resolveDsModel("deepseek-flash")).toEqual({ alias: "flash", id: "deepseek-flash" });
+    expect(resolveDsModel("deepseek-v4-flash")).toEqual({ alias: "flash", id: "deepseek-flash" });
+    expect(resolveDsModel("deepseek-v4.1-flash")).toEqual({ alias: "flash", id: "deepseek-flash" });
+    expect(resolveDsModel("pro")).toEqual({ alias: "pro", id: "deepseek-flash" });
+    expect(resolveDsModel("deepseek-v4-pro")).toEqual({ alias: "pro", id: "deepseek-flash" });
+    expect(resolveDsModel("deepseek-v4-pro[1m]")).toEqual({ alias: "pro", id: "deepseek-flash" });
+    expect(resolveDsModel("vision")).toEqual({ alias: "vision", id: "deepseek-flash" });
+    expect(resolveDsModel("flash-vision")).toEqual({ alias: "vision", id: "deepseek-flash" });
+    expect(resolveDsModel("deepseek-v4-flash-vision")).toEqual({
       alias: "vision",
-      id: "deepseek-v4-flash-vision-exp",
+      id: "deepseek-flash",
     });
-    expect(resolveDsModel("deepseek-v4-pro[1m]")).toEqual({
-      alias: "pro",
-      id: "deepseek-v4-pro[1m]",
+    expect(resolveDsModel("deepseek-v4-flash-vision-exp")).toEqual({
+      alias: "vision",
+      id: "deepseek-flash",
     });
   });
   test("rejects unknown", () => {
     expect(() => resolveDsModel("opus")).toThrow(/flash\|pro\|vision/);
+    expect(() => resolveDsModel("deepseek-chat")).toThrow(/flash\|pro\|vision/);
   });
 });
 
@@ -93,7 +101,7 @@ describe("promptLooksLikeVision", () => {
 });
 
 describe("claude-ds -Model", () => {
-  test("shim path passes -Model deepseek-v4-flash by default", () => {
+  test("shim path passes -Model deepseek-flash by default", () => {
     const prev = process.env.CURSOR_ROUTE_CLAUDE_DS_BIN;
     const prevDs = process.env.CURSOR_ROUTE_DS_MODEL;
     const prevAm = process.env.ANTHROPIC_MODEL;
@@ -107,7 +115,9 @@ describe("claude-ds -Model", () => {
         alwaysApprove: true,
       });
       expect(plan.command).toContain("-Model");
-      expect(plan.command).toContain("deepseek-v4-flash");
+      expect(plan.command).toContain("deepseek-flash");
+      expect(plan.command).not.toContain("deepseek-v4-flash");
+      expect(plan.command).not.toContain("deepseek-v4-pro");
     } finally {
       if (prev === undefined) delete process.env.CURSOR_ROUTE_CLAUDE_DS_BIN;
       else process.env.CURSOR_ROUTE_CLAUDE_DS_BIN = prev;
@@ -117,7 +127,7 @@ describe("claude-ds -Model", () => {
       else process.env.ANTHROPIC_MODEL = prevAm;
     }
   });
-  test("vision alias maps to deepseek-v4-flash-vision-exp", () => {
+  test("vision alias maps to deepseek-flash", () => {
     const prev = process.env.CURSOR_ROUTE_CLAUDE_DS_BIN;
     process.env.CURSOR_ROUTE_CLAUDE_DS_BIN = "/tmp/fake-claude-ds";
     try {
@@ -127,14 +137,14 @@ describe("claude-ds -Model", () => {
         alwaysApprove: true,
         model: "vision",
       });
-      expect(plan.command).toContain("deepseek-v4-flash-vision-exp");
-      expect(plan.command).not.toContain("deepseek-v4-flash'");
+      expect(plan.command).toContain("deepseek-flash");
+      expect(plan.command).not.toContain("deepseek-v4-flash-vision-exp");
     } finally {
       if (prev === undefined) delete process.env.CURSOR_ROUTE_CLAUDE_DS_BIN;
       else process.env.CURSOR_ROUTE_CLAUDE_DS_BIN = prev;
     }
   });
-  test("pro alias maps to deepseek-v4-pro", () => {
+  test("pro alias maps to deepseek-flash", () => {
     const prev = process.env.CURSOR_ROUTE_CLAUDE_DS_BIN;
     process.env.CURSOR_ROUTE_CLAUDE_DS_BIN = "/tmp/fake-claude-ds";
     try {
@@ -144,14 +154,14 @@ describe("claude-ds -Model", () => {
         alwaysApprove: true,
         model: "pro",
       });
-      expect(plan.command).toContain("deepseek-v4-pro");
-      expect(plan.command).not.toContain("deepseek-v4-flash");
+      expect(plan.command).toContain("deepseek-flash");
+      expect(plan.command).not.toContain("deepseek-v4-pro");
     } finally {
       if (prev === undefined) delete process.env.CURSOR_ROUTE_CLAUDE_DS_BIN;
       else process.env.CURSOR_ROUTE_CLAUDE_DS_BIN = prev;
     }
   });
-  test("preserves deepseek-v4-pro[1m] via modelId", () => {
+  test("legacy deepseek-v4-pro[1m] modelId maps to deepseek-flash", () => {
     const prev = process.env.CURSOR_ROUTE_CLAUDE_DS_BIN;
     process.env.CURSOR_ROUTE_CLAUDE_DS_BIN = "/tmp/fake-claude-ds";
     try {
@@ -162,7 +172,8 @@ describe("claude-ds -Model", () => {
         model: "pro",
         modelId: "deepseek-v4-pro[1m]",
       });
-      expect(plan.command).toContain("deepseek-v4-pro[1m]");
+      expect(plan.command).toContain("deepseek-flash");
+      expect(plan.command).not.toContain("deepseek-v4-pro");
     } finally {
       if (prev === undefined) delete process.env.CURSOR_ROUTE_CLAUDE_DS_BIN;
       else process.env.CURSOR_ROUTE_CLAUDE_DS_BIN = prev;
@@ -232,8 +243,8 @@ describe("startJob product path", () => {
       expect(result.ok).toBe(true);
       if (!result.ok) return;
       expect(result.job.model).toBe("pro");
-      expect(result.command).toContain("deepseek-v4-pro");
-      expect(result.command).not.toContain("deepseek-v4-flash");
+      expect(result.command).toContain("deepseek-flash");
+      expect(result.command).not.toContain("deepseek-v4-pro");
     } finally {
       if (prev.bin === undefined) delete process.env.CURSOR_ROUTE_CLAUDE_DS_BIN;
       else process.env.CURSOR_ROUTE_CLAUDE_DS_BIN = prev.bin;
@@ -306,7 +317,8 @@ describe("startJob product path", () => {
       expect(result.ok).toBe(true);
       if (!result.ok) return;
       expect(result.job.model).toBe("vision");
-      expect(result.command).toContain("deepseek-v4-flash-vision-exp");
+      expect(result.command).toContain("deepseek-flash");
+      expect(result.command).not.toContain("deepseek-v4-flash-vision-exp");
     } finally {
       if (prev.bin === undefined) delete process.env.CURSOR_ROUTE_CLAUDE_DS_BIN;
       else process.env.CURSOR_ROUTE_CLAUDE_DS_BIN = prev.bin;
@@ -342,7 +354,7 @@ describe("startJob product path", () => {
       expect(result.ok).toBe(true);
       if (!result.ok) return;
       expect(result.job.model).toBe("flash");
-      expect(result.command).toContain("deepseek-v4-flash");
+      expect(result.command).toContain("deepseek-flash");
       expect(result.command).not.toContain("deepseek-v4-flash-vision-exp");
     } finally {
       if (prev.bin === undefined) delete process.env.CURSOR_ROUTE_CLAUDE_DS_BIN;
@@ -380,6 +392,45 @@ describe("startJob product path", () => {
       expect(result.ok).toBe(true);
       if (!result.ok) return;
       expect(result.job.model).toBe("flash");
+      expect(result.command).toContain("deepseek-flash");
+      expect(result.command).not.toContain("deepseek-v4-flash-vision-exp");
+    } finally {
+      if (prev.bin === undefined) delete process.env.CURSOR_ROUTE_CLAUDE_DS_BIN;
+      else process.env.CURSOR_ROUTE_CLAUDE_DS_BIN = prev.bin;
+      if (prev.ds === undefined) delete process.env.CURSOR_ROUTE_DS_MODEL;
+      else process.env.CURSOR_ROUTE_DS_MODEL = prev.ds;
+      if (prev.am === undefined) delete process.env.ANTHROPIC_MODEL;
+      else process.env.ANTHROPIC_MODEL = prev.am;
+      if (prev.jobs === undefined) delete process.env.CURSOR_ROUTE_JOBS_DIR;
+      else process.env.CURSOR_ROUTE_JOBS_DIR = prev.jobs;
+      rmSync(jobsDir, { recursive: true, force: true });
+    }
+  });
+
+  test("--model vision records alias vision and launches deepseek-flash", () => {
+    const prev = {
+      bin: process.env.CURSOR_ROUTE_CLAUDE_DS_BIN,
+      ds: process.env.CURSOR_ROUTE_DS_MODEL,
+      am: process.env.ANTHROPIC_MODEL,
+      jobs: process.env.CURSOR_ROUTE_JOBS_DIR,
+    };
+    const jobsDir = join(tmpdir(), `cr-jobs-vision-flag-${process.pid}`);
+    mkdirSync(jobsDir, { recursive: true });
+    process.env.CURSOR_ROUTE_CLAUDE_DS_BIN = "/tmp/fake-claude-ds";
+    delete process.env.CURSOR_ROUTE_DS_MODEL;
+    delete process.env.ANTHROPIC_MODEL;
+    process.env.CURSOR_ROUTE_JOBS_DIR = jobsDir;
+    try {
+      const result = startJob({
+        prompt: "ping",
+        lane: "mid",
+        model: "vision",
+        dryRun: true,
+      });
+      expect(result.ok).toBe(true);
+      if (!result.ok) return;
+      expect(result.job.model).toBe("vision");
+      expect(result.command).toContain("deepseek-flash");
       expect(result.command).not.toContain("deepseek-v4-flash-vision-exp");
     } finally {
       if (prev.bin === undefined) delete process.env.CURSOR_ROUTE_CLAUDE_DS_BIN;
@@ -605,15 +656,16 @@ describe("deepseek adapter (dsh)", () => {
         const patch = readFileSync(join(dir, "job.dsh-patch.yml"), "utf8");
         expect(patch).toContain("agent-default-model");
         expect(patch).toContain("provider: deepseek-official");
-        expect(patch).toContain("deepseek-v4-flash");
+        expect(patch).toContain("deepseek-flash");
         expect(patch).not.toContain("deepseek-v4-pro");
+        expect(patch).not.toContain("deepseek-v4-flash-vision-exp");
         expect(patch).not.toContain("test-key");
       },
     );
     rmSync(dir, { recursive: true, force: true });
   });
 
-  test("buildLaunch: vision model → deepseek-v4-flash-vision-exp in patch", () => {
+  test("buildLaunch: vision model → deepseek-flash in patch", () => {
     const { dir, bin } = makeFakeDsh("vision");
     const promptFile = join(dir, "job.prompt");
     writeFileSync(promptFile, "ping");
@@ -632,13 +684,15 @@ describe("deepseek adapter (dsh)", () => {
           model: "vision",
         });
         const patch = readFileSync(join(dir, "job.dsh-patch.yml"), "utf8");
-        expect(patch).toContain("deepseek-v4-flash-vision-exp");
+        expect(patch).toContain("deepseek-flash");
+        expect(patch).not.toContain("deepseek-v4-flash-vision-exp");
+        expect(patch).not.toContain("deepseek-v4-pro");
       },
     );
     rmSync(dir, { recursive: true, force: true });
   });
 
-  test("buildLaunch: pro model → deepseek-v4-pro in patch", () => {
+  test("buildLaunch: pro model → deepseek-flash in patch", () => {
     const { dir, bin } = makeFakeDsh("pro");
     const promptFile = join(dir, "job.prompt");
     writeFileSync(promptFile, "ping");
@@ -657,14 +711,15 @@ describe("deepseek adapter (dsh)", () => {
           model: "pro",
         });
         const patch = readFileSync(join(dir, "job.dsh-patch.yml"), "utf8");
-        expect(patch).toContain("deepseek-v4-pro");
-        expect(patch).not.toContain("deepseek-v4-flash");
+        expect(patch).toContain("deepseek-flash");
+        expect(patch).not.toContain("deepseek-v4-pro");
+        expect(patch).not.toContain("deepseek-v4-flash-vision-exp");
       },
     );
     rmSync(dir, { recursive: true, force: true });
   });
 
-  test("buildLaunch: preserves deepseek-v4-pro[1m] in patch via modelId", () => {
+  test("buildLaunch: legacy deepseek-v4-pro[1m] modelId maps to deepseek-flash in patch", () => {
     const { dir, bin } = makeFakeDsh("pro1m");
     const promptFile = join(dir, "job.prompt");
     writeFileSync(promptFile, "ping");
@@ -684,7 +739,8 @@ describe("deepseek adapter (dsh)", () => {
           modelId: "deepseek-v4-pro[1m]",
         });
         const patch = readFileSync(join(dir, "job.dsh-patch.yml"), "utf8");
-        expect(patch).toContain("deepseek-v4-pro[1m]");
+        expect(patch).toContain("deepseek-flash");
+        expect(patch).not.toContain("deepseek-v4-pro");
       },
     );
     rmSync(dir, { recursive: true, force: true });
@@ -879,7 +935,7 @@ describe("health", () => {
   test("returns structured report", () => {
     const r = runHealth();
     expect(r.product).toBe("cursor-route");
-    expect(r.version).toBe("0.1.14");
+    expect(r.version).toBe("0.1.16");
     expect(r.checks.length).toBeGreaterThan(3);
     expect(r.checks.some((c) => c.name === "tmux")).toBe(true);
     expect(r.checks.some((c) => c.name === "cursor_cli")).toBe(true);
@@ -891,8 +947,8 @@ describe("health", () => {
     expect(r.checks.some((c) => c.name === "worker:deepseek")).toBe(true);
   });
 
-  test("config version is 0.1.14", () => {
-    expect(config.version).toBe("0.1.14");
+  test("config version is 0.1.16", () => {
+    expect(config.version).toBe("0.1.16");
   });
 
   test("OR-gate: ok can be true while worker:opencode is false", () => {

package/src/cli.ts

@@ -57,7 +57,7 @@ Usage:
 Start options:
   --worker <grok|claude-ds|openrouter|deepseek|opencode>  Worker adapter (default: grok; deepseek/opencode = opt-in)
   --lane <easy|mid|hard>                Lane → worker (easy=openrouter, mid=claude-ds, hard=grok)
-  --model <flash|pro|vision|free|provider/model>  claude-ds/deepseek: flash|pro|vision. opencode/openrouter: free (live catalog pick) or provider/model
+  --model <flash|pro|vision|free|provider/model>  claude-ds/deepseek: flash|pro|vision (aliases map to deepseek-flash). opencode/openrouter: free (live catalog pick) or provider/model
   --dir <path>                          Working directory (default: cwd)
   --ask                                 Disable always-approve for this job
   --dry-run                             Print launch command; do not start
@@ -70,7 +70,7 @@ Env:
   CURSOR_ROUTE_MAX_JOBS              Max active jobs (default: 50)
   CURSOR_ROUTE_RELAXED=1             health OK without tmux/workers (CI / infra smoke)
   CURSOR_ROUTE_ALLOW_ANTHROPIC=1     Allow mid-lane on Anthropic Claude (expensive; not default; --model ignored)
-  CURSOR_ROUTE_DS_MODEL              Default mid model flash|pro|vision (or full ids / deepseek-v4-pro[1m]); overridden by --model
+  CURSOR_ROUTE_DS_MODEL              Default mid model flash|pro|vision (aliases map to deepseek-flash); overridden by --model
   CURSOR_ROUTE_GROK_BIN              Override the grok binary path (tests / power users)
   CURSOR_ROUTE_CLAUDE_DS_BIN         Override the claude-ds binary path (tests / power users)
   CURSOR_ROUTE_DSH_BIN               Override the dsh binary path (tests / power users)

package/src/config.ts

@@ -23,10 +23,13 @@ export const WORKERS: WorkerKind[] = ["grok", "claude-ds", "openrouter", "deepse
 export const LANES: Lane[] = ["easy", "mid", "hard"];
 export const DS_MODELS: DsModelAlias[] = ["flash", "pro", "vision"];
 
+/** DeepSeek V4.1 Flash (native vision). Matches the 2026-09-10 API id. */
+export const DS_FLASH_ID = "deepseek-flash";
+
 export const DS_MODEL_IDS: Record<DsModelAlias, string> = {
-  flash: "deepseek-v4-flash",
-  pro: "deepseek-v4-pro",
-  vision: "deepseek-v4-flash-vision-exp",
+  flash: DS_FLASH_ID,
+  pro: DS_FLASH_ID,
+  vision: DS_FLASH_ID,
 };
 
 /** Prompt looks like a screenshot / image / ui mock — vision auto-pick. */
@@ -38,26 +41,35 @@ export function promptLooksLikeVision(prompt: string): boolean {
 }
 
 /**
- * Resolve --model / env to alias + concrete model id.
- * Preserves `deepseek-v4-pro[1m]` (does not silently strip the SKU).
+ * Resolve --model / env to alias + launch id.
+ * V4.1 Flash is native vision; Pro is a legacy alias, not a rotation step.
+ * All known aliases launch `deepseek-flash`.
  * Empty → Flash.
  */
 export function resolveDsModel(raw?: string | null): DsModelChoice {
   if (!raw || !raw.trim()) {
-    return { alias: "flash", id: DS_MODEL_IDS.flash };
+    return { alias: "flash", id: DS_FLASH_ID };
   }
-  const v = raw.trim().toLowerCase();
-  if (v === "flash" || v === "deepseek-v4-flash") {
-    return { alias: "flash", id: DS_MODEL_IDS.flash };
+  // Trim, lower-case, strip a trailing `[…]` SKU (`deepseek-v4-pro[1m]` → `deepseek-v4-pro`).
+  const v = raw.trim().toLowerCase().replace(/\[[^\]]*\]\s*$/, "");
+  if (
+    v === "flash" ||
+    v === "deepseek-flash" ||
+    v === "deepseek-v4-flash" ||
+    v === "deepseek-v4.1-flash"
+  ) {
+    return { alias: "flash", id: DS_FLASH_ID };
   }
   if (v === "pro" || v === "deepseek-v4-pro") {
-    return { alias: "pro", id: DS_MODEL_IDS.pro };
-  }
-  if (v === "vision" || v === "deepseek-v4-flash-vision-exp") {
-    return { alias: "vision", id: DS_MODEL_IDS.vision };
+    return { alias: "pro", id: DS_FLASH_ID };
   }
-  if (v === "deepseek-v4-pro[1m]") {
-    return { alias: "pro", id: "deepseek-v4-pro[1m]" };
+  if (
+    v === "vision" ||
+    v === "flash-vision" ||
+    v === "deepseek-v4-flash-vision" ||
+    v === "deepseek-v4-flash-vision-exp"
+  ) {
+    return { alias: "vision", id: DS_FLASH_ID };
   }
   throw new Error(`Invalid DeepSeek model ${raw}; expected flash|pro|vision`);
 }
@@ -111,7 +123,7 @@ function maxConcurrentJobsFromEnv(): number {
  */
 export const config = {
   product: "cursor-route",
-  version: "0.1.14",
+  version: "0.1.16",
   get jobsDir(): string {
     return defaultJobsDir();
   },

package/src/zen-free.test.ts

@@ -38,30 +38,91 @@ describe("zen free catalog", () => {
     ).toBe(true);
   });
 
-  test("Ox Alpha outranks coding free, which outranks big-pickle and contributor", () => {
-    expect(zenFreeBoost("opencode/x-preview-f-free")).toBe(40);
-    expect(zenFreeBoost("opencode/laguna-s-2.1-free")).toBe(20);
+  test("capability tokens: ultra > preview > generic coding > flash > may-train", () => {
+    expect(zenFreeBoost("opencode/nemotron-3-ultra-free")).toBe(70);
+    expect(zenFreeBoost("opencode/x-preview-f-free")).toBe(52);
+    expect(zenFreeBoost("opencode/laguna-s-2.1-free")).toBe(50);
+    expect(zenFreeBoost("opencode/deepseek-v4-flash-free")).toBe(35);
+    expect(zenFreeBoost("opencode/muse-spark-1.2-contributor-free")).toBe(25);
     expect(zenFreeBoost("opencode/hy3-free")).toBe(20);
-    expect(zenFreeBoost("opencode/big-pickle")).toBe(5);
-    expect(zenFreeBoost("opencode/muse-spark-1.2-contributor-free")).toBe(1);
+    expect(zenFreeBoost("opencode/big-pickle")).toBe(10);
   });
 
-  test("rank: Ox Alpha first while listed; paid/whisper dropped", () => {
+  test("relative boosts: ultra > preview > flash > big-pickle", () => {
+    expect(zenFreeBoost("opencode/nemotron-3-ultra-free")).toBeGreaterThan(
+      zenFreeBoost("opencode/x-preview-f-free"),
+    );
+    expect(zenFreeBoost("opencode/x-preview-f-free")).toBeGreaterThan(
+      zenFreeBoost("opencode/deepseek-v4-flash-free"),
+    );
+    expect(zenFreeBoost("opencode/deepseek-v4-flash-free")).toBeGreaterThan(
+      zenFreeBoost("opencode/big-pickle"),
+    );
+  });
+
+  test("hy3-free is may-train, not coding-family", () => {
+    // else 30 + -free 10 − 20 may-train = 20. Coding-family would be 30.
+    expect(zenFreeBoost("opencode/hy3-free")).toBe(20);
+    expect(zenFreeBoost("opencode/hy3-free")).toBeLessThan(
+      zenFreeBoost("opencode/laguna-s-2.1-free"),
+    );
+  });
+
+  test("rank: paid/whisper dropped; preview may beat laguna (52 > 50)", () => {
     const ranked = rankZenFreeModels(CATALOG);
     expect(ranked[0]?.id).toBe("opencode/x-preview-f-free");
     expect(ranked.map((r) => r.id)).not.toContain("opencode/claude-opus-4-6");
     expect(ranked.map((r) => r.id)).not.toContain("opencode/whisper-free");
-    expect(ranked.at(-1)?.id).toBe("opencode/muse-spark-1.2-contributor-free");
+    expect(ranked.at(-1)?.id).toBe("opencode/big-pickle");
   });
 
-  test("rank without Ox: coding free beats big-pickle", () => {
+  test("rank without preview: coding free beats big-pickle", () => {
     const ranked = rankZenFreeModels([
       { id: "big-pickle" },
       { id: "laguna-s-2.1-free" },
       { id: "muse-spark-1.2-contributor-free" },
     ]);
     expect(ranked[0]?.id).toBe("opencode/laguna-s-2.1-free");
-    expect(ranked[1]?.id).toBe("opencode/big-pickle");
+    expect(ranked[1]?.id).toBe("opencode/muse-spark-1.2-contributor-free");
+    expect(ranked[2]?.id).toBe("opencode/big-pickle");
+  });
+
+  test("hy3 + preview + big-pickle → preview", () => {
+    expect(
+      pickZenFreeModel({
+        catalog: [{ id: "hy3-free" }, { id: "x-preview-f-free" }, { id: "big-pickle" }],
+      }),
+    ).toBe("opencode/x-preview-f-free");
+  });
+
+  test("hy3 + big-pickle + flash → flash coding", () => {
+    expect(
+      pickZenFreeModel({
+        catalog: [
+          { id: "hy3-free" },
+          { id: "big-pickle" },
+          { id: "deepseek-v4-flash-free" },
+        ],
+      }),
+    ).toBe("opencode/deepseek-v4-flash-free");
+  });
+
+  test("flash + ultra + preview → ultra", () => {
+    expect(
+      pickZenFreeModel({
+        catalog: [
+          { id: "deepseek-v4-flash-free" },
+          { id: "nemotron-3-ultra-free" },
+          { id: "x-preview-f-free" },
+        ],
+      }),
+    ).toBe("opencode/nemotron-3-ultra-free");
+  });
+
+  test("only big-pickle → big-pickle", () => {
+    expect(pickZenFreeModel({ catalog: [{ id: "big-pickle" }] })).toBe(
+      "opencode/big-pickle",
+    );
   });
 
   test("asOpenCodeZenId prefixes bare Zen ids", () => {
@@ -73,8 +134,11 @@ describe("zen free catalog", () => {
     expect(pickZenFreeModel({ catalog: CATALOG })).toBe("opencode/x-preview-f-free");
   });
 
-  test("offline / empty catalog falls back to Ox Alpha", () => {
+  test("offline / empty / paid-only catalog falls back to Ox Alpha", () => {
     expect(pickZenFreeModel({ catalog: [] })).toBe(OPENCODE_DEFAULT_MODEL);
+    expect(pickZenFreeModel({ catalog: [{ id: "claude-opus-4-6" }] })).toBe(
+      OPENCODE_DEFAULT_MODEL,
+    );
     expect(OPENCODE_DEFAULT_MODEL).toBe("opencode/x-preview-f-free");
   });
 });
@@ -119,10 +183,16 @@ describe("openCodeModel live pick", () => {
     });
   });
 
-  test("free + injected catalog → Ox Alpha", () => {
+  test("free + injected catalog → strongest listed-free (ultra)", () => {
     isolate(() => {
-      process.env.CURSOR_ROUTE_ZEN_CATALOG_JSON = JSON.stringify({ data: CATALOG });
-      expect(openCodeModel("free")).toBe("opencode/x-preview-f-free");
+      process.env.CURSOR_ROUTE_ZEN_CATALOG_JSON = JSON.stringify({
+        data: [
+          { id: "deepseek-v4-flash-free" },
+          { id: "nemotron-3-ultra-free" },
+          { id: "x-preview-f-free" },
+        ],
+      });
+      expect(openCodeModel("free")).toBe("opencode/nemotron-3-ultra-free");
     });
   });
 

package/src/zen-free.ts

@@ -14,7 +14,7 @@ import { join } from "node:path";
 
 export const ZEN_MODELS_URL_DEFAULT = "https://opencode.ai/zen/v1/models";
 
-/** Offline / fetch-fail fallback — Ox Alpha (zero-retention, currently top-tier free). */
+/** Offline / fetch-fail fallback only — not a live pin. */
 export const OPENCODE_DEFAULT_MODEL = "opencode/x-preview-f-free";
 
 export interface ZenModel {
@@ -36,10 +36,14 @@ export interface ZenFreePick {
 
 const EXCLUDE_RE =
   /lyria|whisper|tts|embed|embedding|image|vision-only|audio|diffusion|flux|stable-diffusion|moderation/i;
-const CODING_RE =
-  /coder|instruct|chat|laguna|nemotron|glm|qwen|kimi|deepseek|mimo|hy3|gpt-oss|north|gemma/i;
-const OX_ALPHA_RE = /x-preview|ox-alpha|oxalpha/i;
-const CONTRIBUTOR_RE = /contributor-free/i;
+const POWER_ULTRA_RE =
+  /ultra|(^|[-/])opus($|[-/])|(^|[-/_])pro($|[-/])|(^|[-/])max($|[-/])|plus|(^|[-/])large($|[-/])/;
+const POWER_PREVIEW_RE = /x-preview|ox-alpha|oxalpha|(^|[-/])alpha($|[-/])|preview/;
+const POWER_FLASH_RE = /flash|lightning|lite|mini|nano|small|haiku|fin-/;
+const CODING_FAMILY_RE =
+  /coder|code|instruct|laguna|glm|qwen|kimi|deepseek|gpt-oss|north|gemma|nemotron|mimo|muse/;
+const CONTRIBUTOR_RE = /contributor-free/;
+const MAY_TRAIN_RE = /(^|\/)big-pickle$|(^|\/)hy3-free$/;
 
 function zenModelsUrl(): string {
   return (process.env.CURSOR_ROUTE_ZEN_MODELS_URL || ZEN_MODELS_URL_DEFAULT).trim();
@@ -94,15 +98,28 @@ export function isZenFreeModel(m: ZenModel): boolean {
   return tagged || pricedFree;
 }
 
-/** Higher boost wins. Ox Alpha first while it is in the free catalog. */
+/**
+ * Higher boost wins. Generic capability tokens only — never a locked model id.
+ * Coding-family matches the model slug so the provider `opencode/` does not
+ * trip `code`.
+ */
 export function zenFreeBoost(id: string): number {
   const s = id.toLowerCase();
-  if (OX_ALPHA_RE.test(s)) return 40;
-  if (CONTRIBUTOR_RE.test(s)) return 1;
-  if (CODING_RE.test(s)) return 20;
-  if (s.endsWith("-free") || s.endsWith(":free")) return 10;
-  if (/(^|\/)big-pickle$/.test(s)) return 5;
-  return 0;
+  const slug = s.includes("/") ? s.slice(s.lastIndexOf("/") + 1) : s;
+  let score = 0;
+
+  if (POWER_ULTRA_RE.test(s)) score += 50;
+  else if (POWER_PREVIEW_RE.test(s)) score += 42;
+  else if (POWER_FLASH_RE.test(s)) score += 15;
+  else score += 30;
+
+  if (CODING_FAMILY_RE.test(slug)) score += 20;
+  else if (s.endsWith("-free") || s.endsWith(":free")) score += 10;
+
+  if (CONTRIBUTOR_RE.test(s)) score -= 25;
+  if (MAY_TRAIN_RE.test(s)) score -= 20;
+
+  return score;
 }
 
 export function rankZenFreeModels(models: ZenModel[]): Array<{