@alexeiled/claude-router 0.4.2 → 0.5.0

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "router",
-  "displayName": "Router",
-  "version": "0.4.2",
+  "displayName": "jev-router",
+  "version": "0.5.0",
   "description": "Auto-picks the right Claude model for each turn — small models for quick edits, mid-tier for code, frontier for hard problems. Uses Jev to classify each request.",
   "author": { "name": "Alexei Ledenev", "url": "https://github.com/alexei-led" },
   "repository": "https://github.com/alexei-led/claude-router",

package/docs/configuration.md

@@ -20,15 +20,14 @@ starts it again.
 
 ```json
 {
-  "model": "jev-router",
+  "model": "jev-router[1m]",
   "env": {
-    "ANTHROPIC_BASE_URL": "http://127.0.0.1:43170",
-    "CLAUDE_CODE_MAX_CONTEXT_TOKENS": "1000000"
+    "ANTHROPIC_BASE_URL": "http://127.0.0.1:43170"
   },
   "modelPicker": {
     "options": [
       {
-        "model": "jev-router",
+        "model": "jev-router[1m]",
         "label": "Jev Router (auto)",
         "description": "Auto-selects the model and effort for each turn",
         "behavesAs": "claude-opus-5-5"
@@ -47,11 +46,14 @@ routes it, and setup replaces that row.
 
 Setup writes the file as its last step. Restart Claude Code after it. Until
 the restart, the session sends `jev-router` to Anthropic and shows "There's an
-issue with the selected model (jev-router)".
+issue with the selected model (jev-router[1m])".
 
 Claude Code does not know the model `jev-router`, so it assumes a 200K window.
-`CLAUDE_CODE_MAX_CONTEXT_TOKENS` declares the real window: the largest
-`contextWindow` of the routed models, 1M by default. The gateway sends a turn
+The `[1m]` suffix declares 1M, the largest `contextWindow` of the default
+routes; Claude Code strips it before the request. `CLAUDE_CODE_MAX_CONTEXT_TOKENS`
+does not work here: Claude Code ignores it for this model. With the suffix,
+Claude Code sends the 1M context beta header on every request; the gateway
+drops it for a model with a smaller window (Haiku answers it with 400). The gateway sends a turn
 only to a model whose window holds the context with room to spare (80%). A
 large session skips Haiku (200K) and goes to Sonnet or Opus. The
 `/router:status` reason for such a turn is `context-fit`.
@@ -138,15 +140,17 @@ frontmatter of `skills/<tier>/SKILL.md`. A test makes sure that they agree.
 
 ### models
 
-| Alias    | ID                 | Input | Cache Read | Window | Billing | Efforts       |
-| -------- | ------------------ | ----- | ---------- | ------ | ------- | ------------- |
-| `opus`   | `claude-opus-5-5`  | $4    | $0.2       | 1M     | plan    | all           |
-| `sonnet` | `claude-sonnet-5`  | $2    | $0.2       | 1M     | plan    | low–xhigh–max |
-| `haiku`  | `claude-haiku-4-5` | $1    | $0.1       | 200k   | plan    | none          |
+| Alias    | ID                 | Input | Cache Read | Window | Max output | Billing | Efforts       |
+| -------- | ------------------ | ----- | ---------- | ------ | ---------- | ------- | ------------- |
+| `opus`   | `claude-opus-5-5`  | $4    | $0.2       | 1M     | as sent    | plan    | all           |
+| `sonnet` | `claude-sonnet-5`  | $2    | $0.2       | 1M     | as sent    | plan    | low–xhigh–max |
+| `haiku`  | `claude-haiku-4-5` | $1    | $0.1       | 200k   | 64k        | plan    | none          |
 
 `id` is the model id that the gateway sends to Anthropic. `input` and
 `cacheRead` are list prices in USD per million tokens. `contextWindow` is the
-size of the context window in tokens. `billing` is `plan` for models that use
+size of the context window in tokens. `maxOutput`, when set, caps the
+`max_tokens` that Claude Code sends; the API rejects a request above the
+model's output limit. `billing` is `plan` for models that use
 the subscription limits, or `credits` for models that bill usage credits.
 `policy.cashCapUsd` applies to `credits` models only. `efforts` lists the
 levels that the model accepts. An empty list means that the gateway removes

package/lib/config.mjs

@@ -39,7 +39,16 @@ export const DEFAULTS = {
       billing: 'plan',
       efforts: EFFORTS,
     },
-    haiku: { id: 'claude-haiku-4-5', input: 1, cacheRead: 0.1, contextWindow: 200_000, billing: 'plan', efforts: [] },
+    // `maxOutput` caps `max_tokens`: Claude Code asks for 128K, Haiku 4.5 answers more than 64K with 400.
+    haiku: {
+      id: 'claude-haiku-4-5',
+      input: 1,
+      cacheRead: 0.1,
+      contextWindow: 200_000,
+      maxOutput: 64_000,
+      billing: 'plan',
+      efforts: [],
+    },
   },
   cache: {
     writeMultiplier: { '5m': 1.25, '1h': 2 },
@@ -108,6 +117,8 @@ function validate(config) {
         throw new Error(`models.${alias}.${field} must be a non-negative number`);
     }
     if (typeof model.id !== 'string' || !model.id) throw new Error(`models.${alias}.id is required`);
+    if (model.maxOutput !== undefined && !(Number.isInteger(model.maxOutput) && model.maxOutput > 0))
+      throw new Error(`models.${alias}.maxOutput must be a positive integer`);
     if (!['plan', 'credits'].includes(model.billing))
       throw new Error(`models.${alias}.billing must be plan or credits`);
     if (!Array.isArray(model.efforts) || model.efforts.some((e) => !EFFORTS.includes(e)))

package/lib/gateway.mjs

@@ -11,6 +11,19 @@ import { ROUTER_DISPLAY_NAME, STATUS_PATH, statusSnapshot } from './status.mjs';
 const HOP_BY_HOP = new Set(['host', 'connection', 'content-length', 'accept-encoding', 'transfer-encoding']);
 const LOOPBACK = new Set(['127.0.0.1', 'localhost', '[::1]']);
 const MESSAGES_PATH = '/v1/messages';
+const LONG_CONTEXT_BETA = /^context-1m-/;
+const LONG_CONTEXT_WINDOW = 1_000_000;
+
+// `jev-router[1m]` makes Claude Code send the 1M context beta on every request; a model with a smaller
+// window answers it with 400 ("The long context beta is not yet available"), so drop it for those.
+function withoutLongContextBeta(headers, modelId, config) {
+  const model = Object.values(config.models).find((m) => m.id === modelId);
+  const beta = headers['anthropic-beta'];
+  if (!model || model.contextWindow >= LONG_CONTEXT_WINDOW || typeof beta !== 'string') return;
+  const kept = beta.split(',').filter((flag) => !LONG_CONTEXT_BETA.test(flag.trim()));
+  if (kept.length) headers['anthropic-beta'] = kept.join(',');
+  else delete headers['anthropic-beta'];
+}
 
 export function createGateway({
   router,
@@ -66,6 +79,7 @@ export function createGateway({
         for (const [name, value] of Object.entries(req.headers)) if (!HOP_BY_HOP.has(name)) headers[name] = value;
         headers.host = target.host;
         headers['content-length'] = String(body.length);
+        if (routed) withoutLongContextBeta(headers, routed.body.model, router.config);
         up = send(
           { host: target.hostname, port: target.port || undefined, path: req.url, method: req.method, headers },
           (upRes) => relay(upRes, res, { routed, session, turn, clientLeft: () => closedEarly }),

package/lib/rewrite.mjs

@@ -1,4 +1,4 @@
-// Turn a request for the router alias into a request for a concrete model. Only `model`,
+// Turn a request for the router alias into a request for a concrete model. Only `model`, `max_tokens`,
 // `output_config.effort`, `thinking` and thinking edits in `context_management` change;
 // system, tools and messages are never touched.
 import { EFFORTS } from './config.mjs';
@@ -7,6 +7,7 @@ export function rewriteRequest(body, tier, config) {
   const route = config.routes[tier];
   const model = config.models[route.model];
   const out = { ...body, model: model.id };
+  if (model.maxOutput && out.max_tokens > model.maxOutput) out.max_tokens = model.maxOutput;
   if (model.efforts.length === 0) return withoutThinking(out, body.output_config);
   const effort = clampEffort(route.effort ?? body.output_config?.effort, model.efforts);
   if (effort) out.output_config = { ...(body.output_config ?? {}), effort };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@alexeiled/claude-router",
-  "version": "0.4.2",
+  "version": "0.5.0",
   "description": "Claude Code plugin: auto-picks the right model and effort for each turn using Jev routing.",
   "license": "MIT",
   "author": "Alexei Ledenev",

package/scripts/statusline.mjs

@@ -17,7 +17,10 @@ try {
 } catch {}
 
 const names = [config.gateway.alias, LEGACY_ALIAS, ROUTER_DISPLAY_NAME];
-const routed = [payload.model?.id, payload.model?.display_name].some((name) => names.includes(name));
+// `jev-router[1m]`: the suffix only tells Claude Code the window size.
+const routed = [payload.model?.id, payload.model?.display_name].some((name) =>
+  names.includes(name?.replace(/\[1m\]$/, '')),
+);
 const [status] = await Promise.all([
   routed ? fetchStatus(config.gateway.port, payload.session_id) : null,
   command ? runWrapped(command, args, input) : null,

package/skills/setup/SKILL.md

@@ -1,29 +1,29 @@
 ---
 name: setup
-description: Point Claude Code at the router gateway. Adds `model`, `ANTHROPIC_BASE_URL`, the context window and the `/model` picker row to the user settings, and offers the status line.
+description: Point Claude Code at the router gateway. Adds `model` with the 1M window, `ANTHROPIC_BASE_URL` and the `/model` picker row to the user settings, and offers the status line.
 disable-model-invocation: true
 allowed-tools: Read, Edit, Write
 ---
 
-Configure Claude Code for the router gateway. This session does not use the gateway until Claude Code restarts. When the file has `model: "jev-router"`, this session can fail its next request. So ask all questions first, write the file once, and write it last.
+Configure Claude Code for the router gateway. This session does not use the gateway until Claude Code restarts. When the file has `model: "jev-router[1m]"`, this session can fail its next request. So ask all questions first, write the file once, and write it last.
 
 1. Read `~/.claude/settings.json`. If the file does not exist, start from `{}`. Read `~/.claude/router.json` if it exists.
 2. The status line can show the model and effort of the last routed turn. The command is `node ${CLAUDE_PLUGIN_ROOT}/scripts/statusline.mjs`, followed by the current status line command if there is one (for example `node ${CLAUDE_PLUGIN_ROOT}/scripts/statusline.mjs claude-powerline`). Show the user the current `statusLine` value and the new one, and ask. Change `statusLine.command` only if the user agrees. Keep the other `statusLine` keys.
 3. Prepare the new settings object in memory:
-   - `model`: `"jev-router"`.
+   - `model`: `"jev-router[1m]"`. Claude Code does not know the model `jev-router` and assumes a 200K window; the `[1m]` suffix declares 1M. Claude Code strips the suffix before it sends the request. If `router.json` routes no model with a 1M `contextWindow`, use `"jev-router"`.
    - `env.ANTHROPIC_BASE_URL`: `"http://127.0.0.1:43170"`. If `router.json` sets `gateway.port`, use that port.
-   - `env.CLAUDE_CODE_MAX_CONTEXT_TOKENS`: `"1000000"`. Claude Code does not know the model `jev-router` and assumes a 200K window without this key. If `router.json` changes `routes` or `models`, use the largest `contextWindow` of the models that the routes use. The gateway sends a turn only to a model whose window holds the context.
-   - The `/model` picker row. In `modelPicker.options`, replace the row whose `model` is `"jev-router"` or `"router"` (the name before 0.4.2), or append it if there is none:
-     `{ "model": "jev-router", "label": "Jev Router (auto)", "description": "Auto-selects the model and effort for each turn", "behavesAs": "claude-opus-5-5" }`.
+   - Remove `env.CLAUDE_CODE_MAX_CONTEXT_TOKENS`. Older versions of this setup wrote it; Claude Code ignores it for `jev-router`. The gateway sends a turn only to a model whose window holds the context, and drops the 1M beta header for a model with a smaller window.
+   - The `/model` picker row. In `modelPicker.options`, replace the row whose `model` is `"jev-router[1m]"`, `"jev-router"` or `"router"` (the name before 0.4.2), or append it if there is none:
+     `{ "model": "jev-router[1m]", "label": "Jev Router (auto)", "description": "Auto-selects the model and effort for each turn", "behavesAs": "claude-opus-5-5" }`.
      If `modelPicker` does not exist, set it to `{ "options": [<the row>] }`. Keep the other rows and `replaceBuiltInOptions`. `behavesAs` names a model that Claude Code knows; without it, Claude Code rejects `jev-router` as a model that is not in its catalog. If `router.json` changes the `high` route, use the `id` of its model.
    - Remove `env.ANTHROPIC_CUSTOM_MODEL_OPTION`, `env.ANTHROPIC_CUSTOM_MODEL_OPTION_NAME` and `env.ANTHROPIC_CUSTOM_MODEL_OPTION_DESCRIPTION`. Older versions of this setup wrote them; the `modelPicker` row replaces them.
    - The `statusLine` change from step 2, if the user agreed.
    - Keep every other key unchanged.
 4. Tell the user, before you write the file:
-   - Restart Claude Code now. Until the restart, this session can show "There's an issue with the selected model (jev-router)", because it still sends requests to Anthropic and not to the gateway.
+   - Restart Claude Code now. Until the restart, this session can show "There's an issue with the selected model (jev-router[1m])", because it still sends requests to Anthropic and not to the gateway.
    - After the restart, the router serves each turn, and `/router:status` shows the routes and the last turn.
    - The status line path contains the plugin version. After a plugin update, run `/router:setup` again.
-   - To stop the routing, remove `model`, `env.ANTHROPIC_BASE_URL`, `env.CLAUDE_CODE_MAX_CONTEXT_TOKENS` and the `jev-router` row of `modelPicker.options`, and restore the status line command.
+   - To stop the routing, remove `model`, `env.ANTHROPIC_BASE_URL` and the `jev-router[1m]` row of `modelPicker.options`, and restore the status line command.
 5. Write the whole object to `~/.claude/settings.json` with one Write call. Do not use a sequence of edits. Do nothing after this step.
 
 Do not change any other file.