opencode-zen-freex 0.2.1 → 0.2.3

package/limits.mjs

@@ -0,0 +1,123 @@
+// Zen's catalogue is where a model's limits are declared from, and for some
+// free ids it under-reports them. A free id and its paid twin are the same
+// upstream model — x-opencode-upstream-model-id answers
+// "deepseek/deepseek-v4.1-flash" whichever of the two is asked for — and only
+// the paid one is declared at what that model can actually do.
+//
+// A limit the host believes is acted on. The window decides when a
+// conversation is compacted and whether a request is worth sending at all; the
+// output cap is sent as max_tokens on every request. So an under-reported limit
+// is not the conservative choice, it is a wrong one nobody can see: a window
+// that is too small is never refused, it is just quietly never used, and an
+// output cap that is too small cuts replies off with a finish reason that looks
+// like the model's own decision.
+//
+// Only evidence moves a value here, and evidence is sorted:
+//
+//   route       the route's own refusal, in its own words
+//   route-twin  what this route declares for the same upstream model
+//   vendor      the model vendor's published page
+//   witnessed   a generation somebody watched finish
+//
+// Being accepted is not evidence. Zen answers 200 to max_tokens 2000000 under a
+// short prompt, so a value that is accepted says something about the request
+// and nothing about what the model writes. A route or route-twin value may set
+// any number; a vendor or witnessed one may only raise, because lowering a
+// limit on weaker evidence invents a restriction nobody asked for.
+//
+// Every axis carries the catalogue value it was measured against. A catalogue
+// that moves voids that axis rather than leaving a stale number behind, and a
+// refusal that names a different window while the plugin is running corrects it
+// for the rest of the process (see observeRouteStatement).
+export const LIMITS = {
+  "deepseek-v4.1-flash-free": {
+    context: {
+      value: 1048576,
+      source: "route",
+      declaredAt: 200000,
+      measured: "2026-10-15",
+      samples: "1,048,507 tokens served; 1,048,707 and 1,060,000 refused 4/4",
+      how: "a prompt sized just over the window; Zen's own 400 answers \"This model's maximum context length is 1048576 tokens. However, you requested 1422278 tokens (1038278 in the messages, 384000 in the completion).\"",
+    },
+    output: {
+      value: 384000,
+      source: "route-twin",
+      declaredAt: 32000,
+      measured: "2026-10-15",
+      samples: "one reply of 306,880 completion tokens, finish=stop; nothing above it observed",
+      how: "deepseek-v4.1-flash, the paid id serving the same upstream model, is declared 384000 in this same catalogue; DeepSeek's own page says 384K, which is 393216 read as binary K",
+    },
+  },
+};
+
+// "This model's maximum context length is 1048576 tokens. However, you
+// requested 1422278 tokens (1038278 in the messages, 384000 in the
+// completion)." — the route's own words, and the only sentence seen on this
+// route that states a window. A generic 400 says nothing attributable and is
+// left alone; §7 of the measured notes has a context overflow and an invalid
+// parameter answering with byte-identical 400s on another Zen model.
+const NAMED_CONTEXT = /maximum context length is (\d+) tokens/i;
+
+// Windows named by a refusal while this process is running, by model id. Not
+// persisted: it is the same kind of fact as LIMITS, only newer, and a restart
+// falls back to what was measured last.
+const OBSERVED = new Map();
+
+// The window a refusal names, or undefined when the body says nothing
+// attributable. Exported for the tests and for anyone reading a capture.
+export function namedContextWindow(text) {
+  const match = NAMED_CONTEXT.exec(typeof text === "string" ? text : "");
+  if (!match) return undefined;
+  const tokens = Number.parseInt(match[1], 10);
+  return Number.isSafeInteger(tokens) && tokens > 0 ? tokens : undefined;
+}
+
+// Read a refusal for a window it names. Only non-2xx responses are read, and
+// only the first `limit` characters of one: this is an error path on the
+// request's way to a caller that is waiting, so it must never be able to fail a
+// request, change a response, or buffer a body that is not small.
+export async function observeRouteStatement(id, response, limit = 4096) {
+  try {
+    if (typeof id !== "string" || !id || response?.ok !== false) return undefined;
+    const text = await response
+      .clone()
+      .text()
+      .catch(() => "");
+    const tokens = namedContextWindow(text.slice(0, limit));
+    if (tokens !== undefined) OBSERVED.set(id, tokens);
+    return tokens;
+  } catch {
+    return undefined;
+  }
+}
+
+const ROUTE_TIERS = new Set(["route", "route-twin"]);
+
+// What this plugin declares for a model instead of what the catalogue says, as
+// a plain object to spread over the catalogue's own limit. Empty when there is
+// no evidence, when the evidence was measured against a different catalogue, or
+// when it would change nothing.
+export function limitOverrides(id, declared = {}, table = LIMITS, observed = OBSERVED) {
+  const overrides = {};
+  const record = table?.[id];
+  const live = observed?.get(id);
+  for (const axis of ["context", "output"]) {
+    const declaredValue = declared?.[axis];
+    const entry = record?.[axis];
+    // A route statement made while this process was running is the same tier as
+    // the table and newer than it, so it is taken as it stands. Everything else
+    // has to have been measured against the catalogue in front of us now.
+    const value =
+      axis === "context" && live !== undefined
+        ? live
+        : entry && entry.declaredAt === declaredValue
+          ? entry.value
+          : undefined;
+    if (value === undefined || !Number.isSafeInteger(value) || value <= 0) continue;
+    if (value === declaredValue) continue;
+    if (entry && !ROUTE_TIERS.has(entry.source) && Number.isSafeInteger(declaredValue) && value < declaredValue)
+      continue;
+    overrides[axis] = value;
+  }
+  return overrides;
+}

package/models.mjs

@@ -1,148 +1,213 @@
-export const PROVIDER = "opencode-zen-free";
-export const SDK = {
-  chat: "@ai-sdk/openai-compatible",
-  responses: "@ai-sdk/openai",
-  anthropic: "@ai-sdk/anthropic",
-};
-
-export function parseProtocolDocs(text) {
-  const protocols = {};
-  const pattern =
-    /\|[^|]+\|\s*`?([^|`\s]+)`?\s*\|\s*`[^`]+\/v1\/(chat\/completions|responses|messages|systemone)`/g;
-  for (const match of text.matchAll(pattern)) {
-    protocols[match[1]] = {
-      "chat/completions": "chat",
-      responses: "responses",
-      messages: "anthropic",
-      systemone: "systemone",
-    }[match[2]];
-  }
-  return protocols;
-}
-
-function sdkProtocol(npm) {
-  if (npm?.includes("anthropic")) return "anthropic";
-  if (npm === SDK.responses) return "responses";
-  if (npm?.includes("openai-compatible")) return "chat";
-}
-
-function isRetired(model) {
-  return (
-    model.deprecated === true ||
-    ["deprecated", "retired", "disabled"].includes(model.status ?? model.lifecycle) ||
-    model.deprecated_at != null ||
-    model.retirement_date != null
-  );
-}
-
-export function isFree(id, model = {}) {
-  return (
-    !isRetired(model) && (/free/i.test(id) || (model.cost?.input === 0 && model.cost?.output === 0))
-  );
-}
-
-export function buildModels(ids, provider, protocols, baseURL) {
-  const result = {};
-  for (const id of ids) {
-    if (typeof id !== "string" || !id || id === "__proto__") continue;
-    const raw = provider.models?.[id];
-    const model = raw ?? {};
-    const protocol = protocols[id] ?? (raw && sdkProtocol(model.provider?.npm ?? provider.npm));
-    if (!isFree(id, model) || !Object.hasOwn(SDK, protocol)) continue;
-    const input = model.modalities?.input ?? ["text"];
-    const output = model.modalities?.output ?? ["text"];
-    const modalities = (values) =>
-      Object.fromEntries(
-        ["text", "image", "audio", "video", "pdf"].map((name) => [name, values.includes(name)]),
-      );
-    const efforts = (model.reasoning_options ?? [])
-      .filter((option) => option.type === "effort")
-      .flatMap((option) => option.values ?? []);
-    result[id] = {
-      id,
-      providerID: PROVIDER,
-      name: model.name ?? id,
-      api: { id, url: baseURL, npm: SDK[protocol] },
-      limit: { context: 32768, output: 4096, ...model.limit },
-      capabilities: {
-        temperature: model.temperature ?? true,
-        reasoning: model.reasoning ?? false,
-        attachment: model.attachment ?? input.some((name) => name !== "text"),
-        toolcall: model.tool_call ?? true,
-        input: modalities(input),
-        output: modalities(output),
-        interleaved: model.interleaved ?? false,
-      },
-      cost: { input: 0, output: 0, cache: { read: 0, write: 0 } },
-      variants: Object.fromEntries(efforts.map((effort) => [effort, { reasoningEffort: effort }])),
-      options: {},
-      headers: {},
-      status: model.status ?? "active",
-      release_date: model.release_date ?? "",
-      free: true,
-    };
-  }
-  return result;
-}
-
-// Offline bootstrap metadata from the OpenCode catalog, 2026-10-06.
-export const bootstrapProvider = {
-  npm: SDK.chat,
-  models: {
-    "big-pickle": {
-      name: "Big Pickle",
-      cost: { input: 0, output: 0 },
-      limit: { context: 200000, input: 160000, output: 32000 },
-      reasoning: true,
-      tool_call: true,
-      interleaved: { field: "reasoning_content" },
-    },
-    "space-bunny-free": {
-      name: "Space Bunny Free",
-      cost: { input: 0, output: 0 },
-      limit: { context: 1048576, input: 524288, output: 524288 },
-      reasoning: true,
-      tool_call: true,
-    },
-    "muse-spark-1.3-contributor-free": {
-      name: "Muse Spark 1.3 Free",
-      cost: { input: 0, output: 0 },
-      provider: { npm: SDK.responses },
-      limit: { context: 1048576, output: 131072 },
-      reasoning: true,
-      tool_call: true,
-      modalities: { input: ["text", "image", "video", "pdf", "audio"], output: ["text"] },
-      reasoning_options: [
-        { type: "effort", values: ["minimal", "low", "medium", "high", "xhigh"] },
-      ],
-    },
-  },
-};
-
-export function configModels(models) {
-  return Object.fromEntries(
-    Object.entries(models).map(([id, model]) => [
-      id,
-      {
-        id,
-        name: model.name,
-        provider: { npm: model.api.npm, api: model.api.url },
-        limit: model.limit,
-        reasoning: model.capabilities.reasoning,
-        tool_call: model.capabilities.toolcall,
-        attachment: model.capabilities.attachment,
-        modalities: {
-          input: Object.keys(model.capabilities.input).filter(
-            (key) => model.capabilities.input[key],
-          ),
-          output: Object.keys(model.capabilities.output).filter(
-            (key) => model.capabilities.output[key],
-          ),
-        },
-        cost: { input: 0, output: 0 },
-        variants: model.variants,
-        free: true,
-      },
-    ]),
-  );
-}
+import { limitOverrides } from "./limits.mjs";
+
+export const PROVIDER = "opencode-zen-free";
+export const SDK = {
+  chat: "@ai-sdk/openai-compatible",
+  responses: "@ai-sdk/openai",
+  anthropic: "@ai-sdk/anthropic",
+};
+
+export function parseProtocolDocs(text) {
+  const protocols = {};
+  const pattern =
+    /\|[^|]+\|\s*`?([^|`\s]+)`?\s*\|\s*`[^`]+\/v1\/(chat\/completions|responses|messages|systemone)`/g;
+  for (const match of text.matchAll(pattern)) {
+    protocols[match[1]] = {
+      "chat/completions": "chat",
+      responses: "responses",
+      messages: "anthropic",
+      systemone: "systemone",
+    }[match[2]];
+  }
+  return protocols;
+}
+
+function sdkProtocol(npm) {
+  if (npm?.includes("anthropic")) return "anthropic";
+  if (npm === SDK.responses) return "responses";
+  if (npm?.includes("openai-compatible")) return "chat";
+}
+
+function isRetired(model) {
+  return (
+    model.deprecated === true ||
+    ["deprecated", "retired", "disabled"].includes(model.status ?? model.lifecycle) ||
+    model.deprecated_at != null ||
+    model.retirement_date != null
+  );
+}
+
+export function isFree(id, model = {}) {
+  return (
+    !isRetired(model) && (/free/i.test(id) || (model.cost?.input === 0 && model.cost?.output === 0))
+  );
+}
+
+export function buildModels(ids, provider, protocols, baseURL) {
+  const result = {};
+  for (const id of ids) {
+    if (typeof id !== "string" || !id || id === "__proto__") continue;
+    const raw = provider.models?.[id];
+    const model = raw ?? {};
+    const protocol = protocols[id] ?? (raw && sdkProtocol(model.provider?.npm ?? provider.npm));
+    if (!isFree(id, model) || !Object.hasOwn(SDK, protocol)) continue;
+    const input = model.modalities?.input ?? ["text"];
+    const output = model.modalities?.output ?? ["text"];
+    const modalities = (values) =>
+      Object.fromEntries(
+        ["text", "image", "audio", "video", "pdf"].map((name) => [name, values.includes(name)]),
+      );
+    const efforts = (model.reasoning_options ?? [])
+      .filter((option) => option.type === "effort")
+      .flatMap((option) => option.values ?? []);
+    result[id] = {
+      id,
+      providerID: PROVIDER,
+      name: model.name ?? id,
+      api: { id, url: baseURL, npm: SDK[protocol] },
+      limit: { context: 32768, output: 4096, ...model.limit, ...limitOverrides(id, model.limit) },
+      capabilities: {
+        temperature: model.temperature ?? true,
+        reasoning: model.reasoning ?? false,
+        attachment: model.attachment ?? input.some((name) => name !== "text"),
+        toolcall: model.tool_call ?? true,
+        input: modalities(input),
+        output: modalities(output),
+        interleaved: model.interleaved ?? false,
+      },
+      cost: { input: 0, output: 0, cache: { read: 0, write: 0 } },
+      variants: Object.fromEntries(efforts.map((effort) => [effort, { reasoningEffort: effort }])),
+      options: {},
+      headers: {},
+      status: model.status ?? "active",
+      release_date: model.release_date ?? "",
+      free: true,
+    };
+  }
+  return result;
+}
+
+// What each free model is asked at, from OpenCode's console docs
+// (services/www/src/docs/content/console/models.mdx) on 2026-10-15: used for
+// a listed model when the docs can't be read, so the catalog or the docs
+// being out of reach never leaves a listed free model out. Jev is a
+// SystemOne decision model, not one to chat with.
+export const bootstrapProtocols = {
+  "big-pickle": "chat",
+  "space-bunny-free": "chat",
+  "cat-jam-free": "chat",
+  "longcat-2.5-preview-free": "chat",
+  "step-5-preview-free": "chat",
+  "mimo-v2.6-flash-free": "chat",
+  "nemotron-3.5-lightning-free": "chat",
+  "muse-spark-1.3-contributor-free": "responses",
+  "jev-1.13-free": "systemone",
+};
+
+// Offline bootstrap metadata from the OpenCode catalog, 2026-10-06; the
+// free models listed since added on 2026-10-15.
+export const bootstrapProvider = {
+  npm: SDK.chat,
+  models: {
+    "cat-jam-free": {
+      name: "Cat Jam Free",
+      cost: { input: 0, output: 0 },
+      limit: { context: 262144, output: 131072 },
+      reasoning: true,
+      tool_call: true,
+      interleaved: { field: "reasoning_content" },
+      reasoning_options: [{ type: "effort", values: ["low", "medium", "high", "xhigh", "max"] }],
+    },
+    "step-5-preview-free": {
+      name: "Step 5 Preview Free",
+      cost: { input: 0, output: 0 },
+      limit: { context: 1000000, input: 1000000, output: 65536 },
+      reasoning: true,
+      tool_call: true,
+      interleaved: { field: "reasoning_content" },
+      modalities: { input: ["text", "image", "video"], output: ["text"] },
+      reasoning_options: [{ type: "effort", values: ["low", "medium", "high"] }],
+    },
+    "longcat-2.5-preview-free": {
+      name: "LongCat 2.5 Preview Free",
+      cost: { input: 0, output: 0 },
+      limit: { context: 1000000, output: 131072 },
+      reasoning: true,
+      tool_call: true,
+      interleaved: { field: "reasoning_content" },
+      modalities: { input: ["text", "image"], output: ["text"] },
+    },
+    "mimo-v2.6-flash-free": {
+      name: "MiMo-V2.6-Flash Free",
+      cost: { input: 0, output: 0 },
+      limit: { context: 200000, output: 32000 },
+      reasoning: true,
+      tool_call: true,
+      interleaved: { field: "reasoning_content" },
+      modalities: { input: ["text", "image", "audio", "video"], output: ["text"] },
+    },
+    "nemotron-3.5-lightning-free": {
+      name: "Nemotron 3.5 Lightning Free",
+      cost: { input: 0, output: 0 },
+      limit: { context: 262144, output: 262144 },
+      reasoning: true,
+      tool_call: true,
+      interleaved: { field: "reasoning_content" },
+    },
+    "big-pickle": {
+      name: "Big Pickle",
+      cost: { input: 0, output: 0 },
+      limit: { context: 200000, input: 160000, output: 32000 },
+      reasoning: true,
+      tool_call: true,
+      interleaved: { field: "reasoning_content" },
+    },
+    "space-bunny-free": {
+      name: "Space Bunny Free",
+      cost: { input: 0, output: 0 },
+      limit: { context: 1048576, input: 524288, output: 524288 },
+      reasoning: true,
+      tool_call: true,
+    },
+    "muse-spark-1.3-contributor-free": {
+      name: "Muse Spark 1.3 Free",
+      cost: { input: 0, output: 0 },
+      provider: { npm: SDK.responses },
+      limit: { context: 1048576, output: 131072 },
+      reasoning: true,
+      tool_call: true,
+      modalities: { input: ["text", "image", "video", "pdf", "audio"], output: ["text"] },
+      reasoning_options: [
+        { type: "effort", values: ["minimal", "low", "medium", "high", "xhigh"] },
+      ],
+    },
+  },
+};
+
+export function configModels(models) {
+  return Object.fromEntries(
+    Object.entries(models).map(([id, model]) => [
+      id,
+      {
+        id,
+        name: model.name,
+        provider: { npm: model.api.npm, api: model.api.url },
+        limit: model.limit,
+        reasoning: model.capabilities.reasoning,
+        tool_call: model.capabilities.toolcall,
+        attachment: model.capabilities.attachment,
+        modalities: {
+          input: Object.keys(model.capabilities.input).filter(
+            (key) => model.capabilities.input[key],
+          ),
+          output: Object.keys(model.capabilities.output).filter(
+            (key) => model.capabilities.output[key],
+          ),
+        },
+        cost: { input: 0, output: 0 },
+        variants: model.variants,
+        free: true,
+      },
+    ]),
+  );
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-zen-freex",
-  "version": "0.2.1",
+  "version": "0.2.3",
   "description": "OpenCode Zen's free models, for hosts that are not OpenCode: the public credential, automatic discovery and native streaming protocols",
   "type": "module",
   "main": "./index.mjs",
@@ -9,10 +9,14 @@
     "provider.mjs",
     "core-tools.mjs",
     "fingerprint.json",
+    "limits.mjs",
     "models.mjs",
     "stream.mjs",
     "tool-response.mjs",
+    "tools-smoke.mjs",
+    "capture.mjs",
     "README.md",
+    "MAINTAINING.md",
     "LICENSE"
   ],
   "keywords": ["opencode", "opencode-plugin", "zen", "free", "magpie"],