@bman654/clodex 2.15.0 → 2.16.0

package/README.md

@@ -276,6 +276,16 @@ Two things worth knowing about the numbers:
   number first only costs usable context. A provider that declares a share of its own
   is still honoured; clodex just never invents one. Use `--context` if you want a
   smaller window than the provider offers.
+- **A window nobody published is not a ceiling.** Some servers list their models
+  without saying how much context each one takes. Clodex reports the 200,000 Claude
+  Code assumes anyway, but that number is a guess, not a measurement — so
+  `clodex models --context <model>=1m --save` raises it instead of being clamped back
+  down to the guess. Clamping still applies in full wherever a window *is* published,
+  by the provider or by clodex's own catalog. If the model is already baked into a
+  patched binary, re-run `clodex patch` so it picks the new window up. Set this model up
+  before this version? Run `clodex providers refresh-models <provider>` once — an older
+  clodex stored the guess as if the server had published it, and until you refresh it is
+  indistinguishable from a real limit and still clamps.
 - **The account ceiling moves.** It is server-side and per-account, and it has
   changed by more than 2x within a single day in the past. `max` reads whatever the
   catalog reports now and clamps to it, so a stale ceiling shrinks the stop rather
@@ -292,7 +302,7 @@ Two things worth knowing about the numbers:
 | `remove <id>` | Remove a provider by id |
 | `refresh-models [id]` | Update cached model lists |
 
-Providers supported: `openai` (API key, platform.openai.com), `openai-oauth` (ChatGPT/Codex plan), and `opencode-go` (OpenCode Go API key). OpenCode Go exposes its Anthropic Messages and Chat Completions models; Responses-only entries are intentionally excluded. See [OpenCode Go provider](docs/opencode-go.md).
+Providers supported: `openai` (API key, platform.openai.com), `openai-oauth` (ChatGPT/Codex plan), and `opencode-go` (OpenCode Go API key). OpenCode Go exposes its Anthropic Messages, Chat Completions, and Responses models; entries whose transport has not been verified against the live endpoint are left out. See [OpenCode Go provider](docs/opencode-go.md).
 
 A **custom OpenAI-compatible server** is any OpenAI-style API, given by its base URL (the part before `/chat/completions`), such as `https://openrouter.ai/api/v1`. `providers add` asks for a name, the base URL and an API key (leave it empty for a local server without auth), lists the server's models to check the connection, and saves the provider as `custom-<name>`. Its models then appear in `clodex models`; once saved as favorites they are addressed as `clodex:custom-<name>:<model>` and can be given a short alias with `clodex models --alias`. The base URL is checked before anything is saved: plain `http://` is accepted only after you confirm it, and only for loopback or private-network addresses, and an `https://` URL whose host is, or resolves to, a loopback (`127.0.0.0/8`, `::1`), private, link-local, unique-local, carrier-grade-NAT or well-known cloud-metadata address is refused. A model's id and name are stored with surrounding whitespace trimmed, and a model whose trimmed id or name still contains a control character is skipped, whether the list is fetched by `providers add` or by `providers refresh-models`, and error text from the server is shown with control characters replaced by spaces. Only the OpenAI-compatible kind is offered in the menu.
 

package/dist/cli.js

@@ -346,7 +346,7 @@ import { join } from "path";
 // package.json
 var package_default = {
   name: "@bman654/clodex",
-  version: "2.15.0",
+  version: "2.16.0",
   publishConfig: {
     access: "public"
   },
@@ -694,20 +694,22 @@ function getCacheIndex() {
   }
   return cacheIndex;
 }
-function contextWindowFromHeuristics(modelId) {
-  const cached = heuristicCache.get(modelId);
-  if (cached !== void 0) return cached;
+function matchHeuristicWindow(modelId) {
+  if (heuristicCache.has(modelId)) return heuristicCache.get(modelId);
   for (const [pattern, size] of HEURISTIC_RULES) {
     if (pattern.test(modelId)) {
       heuristicCache.set(modelId, size);
       return size;
     }
   }
-  heuristicCache.set(modelId, DEFAULT_CONTEXT_WINDOW);
-  return DEFAULT_CONTEXT_WINDOW;
+  heuristicCache.set(modelId, void 0);
+  return void 0;
+}
+function lookupKnownContextWindow(modelId) {
+  return getCacheIndex().get(modelId) ?? matchHeuristicWindow(modelId);
 }
 function lookupContextWindow(modelId) {
-  return getCacheIndex().get(modelId) ?? contextWindowFromHeuristics(modelId);
+  return lookupKnownContextWindow(modelId) ?? DEFAULT_CONTEXT_WINDOW;
 }
 function resolveContextWindow(modelId, explicit) {
   if (typeof explicit === "number" && explicit > 0) return explicit;
@@ -3160,17 +3162,19 @@ function parseContextStop(value) {
   return parsed;
 }
 function resolveContextStop(limits, stop = "standard") {
-  const standardRaw = positiveInteger(limits.contextWindow) ?? 0;
-  const ceiling = positiveInteger(limits.maxContextWindow) ?? standardRaw;
-  const requested = stop === "standard" ? standardRaw : stop === "max" ? ceiling : positiveInteger(stop) ?? standardRaw;
-  const raw = Math.min(requested, ceiling);
+  const declaredWindow = positiveInteger(limits.contextWindow);
+  const declaredCeiling = positiveInteger(limits.maxContextWindow);
+  const standardRaw = declaredWindow ?? DEFAULT_CONTEXT_WINDOW;
+  const ceiling = declaredCeiling ?? declaredWindow;
+  const requested = stop === "standard" ? standardRaw : stop === "max" ? declaredCeiling ?? standardRaw : positiveInteger(stop) ?? standardRaw;
+  const raw = ceiling === void 0 ? requested : Math.min(requested, ceiling);
   const effective = effectiveContextWindow(raw, limits.effectiveContextPercent);
   const boundary = positiveInteger(limits.pricingBoundary);
   return {
     stop,
     raw,
     effective,
-    ...requested > ceiling ? { clampedFrom: requested } : {},
+    ...ceiling !== void 0 && requested > ceiling ? { clampedFrom: requested } : {},
     crossesPricingBoundary: boundary !== void 0 && effective > boundary
   };
 }
@@ -5208,6 +5212,52 @@ var opencode_go_models_default = [
     upstreamModelId: "minimax-m3",
     family: "minimax"
   },
+  {
+    id: "muse-spark-1.2-contributor",
+    name: "Muse Spark 1.2 Contributor",
+    contextWindow: 1048576,
+    cost: {
+      input: 0.1,
+      output: 0.2,
+      cache_read: 2e-3
+    },
+    modelFormat: "openai",
+    npm: "@ai-sdk/openai",
+    apiUrl: "https://opencode.ai/zen/go/v1",
+    reasoning: true,
+    modalities: [
+      "text",
+      "image"
+    ],
+    compatibility: {
+      supportsReasoningEffort: false
+    },
+    upstreamModelId: "muse-spark-1.2-contributor",
+    family: "muse"
+  },
+  {
+    id: "muse-spark-1.3-contributor",
+    name: "Muse Spark 1.3 Contributor",
+    contextWindow: 1048576,
+    cost: {
+      input: 0.1,
+      output: 0.2,
+      cache_read: 2e-3
+    },
+    modelFormat: "openai",
+    npm: "@ai-sdk/openai",
+    apiUrl: "https://opencode.ai/zen/go/v1",
+    reasoning: true,
+    modalities: [
+      "text",
+      "image"
+    ],
+    compatibility: {
+      supportsReasoningEffort: false
+    },
+    upstreamModelId: "muse-spark-1.3-contributor",
+    family: "muse"
+  },
   {
     id: "qwen3.6-plus",
     name: "Qwen3.6 Plus",
@@ -5471,6 +5521,10 @@ function openCodeGoPinnedApiUrl(npm) {
   if (npm === "@ai-sdk/anthropic") return OPENCODE_GO_ANTHROPIC_BASE_URL;
   return null;
 }
+function openCodeGoPinnedModelApiUrl(npm) {
+  if (npm === "@ai-sdk/openai") return OPENCODE_GO_COMPLETIONS_BASE_URL;
+  return openCodeGoPinnedApiUrl(npm);
+}
 function isProviderConfiguredForTemplate(provider, templateId) {
   if (provider.id === templateId) return true;
   return templateId === OPENCODE_GO_PROVIDER_ID && isRetainedOpenCodeGoProvider(provider);
@@ -5957,10 +6011,10 @@ var OPENAI_OAUTH_MODEL_SEEDS = [
   { id: "gpt-5", name: "GPT-5", contextWindow: 272e3, reasoning: true },
   // o-series reasoning (Plus+)
   { id: "o4-mini", name: "o4 Mini", reasoning: true },
-  { id: "o3", name: "o3", reasoning: true },
+  { id: "o3", name: "o3", contextWindow: 2e5, reasoning: true },
   { id: "o3-mini", name: "o3 Mini", reasoning: true },
-  { id: "o1", name: "o1", reasoning: true },
-  { id: "o1-mini", name: "o1 Mini", reasoning: true }
+  { id: "o1", name: "o1", contextWindow: 2e5, reasoning: true },
+  { id: "o1-mini", name: "o1 Mini", contextWindow: 128e3, reasoning: true }
 ];
 function hasPricingBoundary(id) {
   const version = /^gpt-(\d+)(?:\.(\d+))?(?:-|$)/i.exec(id);
@@ -6008,7 +6062,7 @@ function buildOpenAiOAuthModels() {
       upstreamModelId: seed.id,
       family: prefix,
       brand: deriveBrand(prefix),
-      contextWindow: resolveContextWindow(seed.id, seed.contextWindow),
+      contextWindow: seed.contextWindow ?? lookupKnownContextWindow(seed.id),
       maxContextWindow: seed.maxContextWindow,
       effectiveContextPercent: seed.effectiveContextPercent,
       pricingBoundary: seed.pricingBoundary ?? pricing.pricingBoundary,
@@ -6524,7 +6578,9 @@ function parseModelList(body, npm, allowBareArray) {
     const freeStatus = classifyFreeStatus({
       model: { cost, isFree: row.isFree }
     });
-    const contextWindow = row.context_length ?? row.contextWindow ?? row.context_window ?? row.max_model_len ?? resolveContextWindow(id);
+    const contextWindow = row.context_length ?? row.contextWindow ?? row.context_window ?? row.max_model_len ?? // Left undefined when nothing is known: persisting the invented 200,000
+    // would make it this model's permanent ceiling.
+    lookupKnownContextWindow(id);
     models.push({
       id,
       name: normalizeGoogleDisplayName(row.name, id),
@@ -6556,7 +6612,7 @@ function materializeTemplateModel(template, model, baseUrl) {
     upstreamModelId: model.upstreamModelId ?? normalizedUpstream,
     family,
     brand: model.brand ?? deriveBrand(family),
-    contextWindow: model.contextWindow ?? resolveContextWindow(id),
+    contextWindow: model.contextWindow ?? lookupKnownContextWindow(id),
     isFree: model.isFree ?? isFreeStatus(freeStatus),
     freeStatus,
     modelFormat: model.modelFormat ?? modelFormatForNpm(npm),
@@ -6758,10 +6814,10 @@ function resolveMaterializedApiUrl(cached, provider, npm) {
   if (!isRetainedOpenCodeGoProvider(provider)) {
     return cached.apiUrl ?? provider.api.url ?? "";
   }
-  return openCodeGoPinnedApiUrl(npm);
+  return openCodeGoPinnedModelApiUrl(npm);
 }
 function projectContextStop(cached, providerId, modelId) {
-  const limits = contextLimitsFrom(cached, resolveContextWindow(modelId));
+  const limits = contextLimitsFrom(cached, lookupKnownContextWindow(modelId));
   const stop = selectContextStop(providerId, modelId);
   const resolved = resolveContextStop(limits, stop);
   return {
@@ -7893,7 +7949,7 @@ function outboundHttpProxyAgent(targetUrl, env = process.env) {
     }
     return new HttpsProxyAgent(parsedProxy, { keepAlive: true });
   } catch (err) {
-    console.error(
+    emitParentNotice(
       `clodex: HTTP(S)_PROXY cannot be used for a CONNECT tunnel; using a direct connection (${err instanceof Error ? err.message : String(err)})`
     );
     return void 0;
@@ -10777,7 +10833,7 @@ async function createLanguageModel(spec) {
       apiKey: "",
       ...spec.headers ? { headers: spec.headers } : {},
       fetch: fetchWithoutCredentialHeaders
-    } : { apiKey, ...spec.headers ? { headers: spec.headers } : {} };
+    } : { apiKey, ...baseURL ? { baseURL } : {}, ...spec.headers ? { headers: spec.headers } : {} };
     const openai = createOpenAI(oauthOptions);
     return useResponsesEndpoint ? openai.responses(modelId) : openai.chat(modelId);
   }
@@ -14109,7 +14165,7 @@ function buildDesiredPatchConfig(options = {}) {
         compatibility: model.compatibility,
         upstreamModelId: upstreamModelId2
       });
-      const limits = contextLimitsFrom(model, resolveContextWindow(model.id));
+      const limits = contextLimitsFrom(model, lookupKnownContextWindow(model.id));
       const stop = resolveContextStop(
         limits,
         options.sessionStops ? selectContextStop(provider.id, model.id, prefs.modelContextModes) : readContextStop(prefs.modelContextModes, provider.id, model.id) ?? "standard"
@@ -14678,7 +14734,9 @@ async function runPatchCommand(opts = {}) {
     return 1;
   }
   for (const id of desired.unknownWindows) {
-    p2.log.warn(`No context window metadata for ${id} \u2014 Claude Code will assume the 200k default.`);
+    p2.log.warn(
+      `No context window metadata for ${id} \u2014 Claude Code will assume the 200k default. Refresh the provider's models, then set a window with \`clodex models --context <model=stop> --save\`, then re-run \`clodex patch\`.`
+    );
   }
   reportRejectedModelAliases(desired.rejectedAliasRejections);
   const localPatches = inspectLocalPatchSource(
@@ -15781,7 +15839,7 @@ async function fetchAnthropicModels(baseUrl, apiKey, extraHeaders) {
           upstreamModelId: id,
           family: id.split("-")[0] ?? id,
           brand: deriveBrand(id),
-          contextWindow: resolveContextWindow(id),
+          contextWindow: lookupKnownContextWindow(id),
           modelFormat: "anthropic",
           npm: "@ai-sdk/anthropic",
           apiUrl: root
@@ -16328,7 +16386,7 @@ function buildDynamicOAuthModel(entry, seedById, codexCatalog) {
     upstreamModelId: id,
     family: prefix,
     brand: deriveBrand(prefix),
-    contextWindow: entry.context_window ?? resolveContextWindow(id),
+    contextWindow: entry.context_window ?? lookupKnownContextWindow(id),
     maxContextWindow: entry.max_context_window,
     // Absent means no reduction. clodex reports the window the provider actually
     // gives; deciding how much of it to leave free is the client's job, and Claude
@@ -20433,6 +20491,14 @@ async function startHttpProxy(options) {
     );
   });
   const sockets = /* @__PURE__ */ new Set();
+  let warnedConnectSelfProxy = false;
+  const connectTunnelAgents = /* @__PURE__ */ new Map();
+  const connectTunnelAgent = (proxyUrl, targetUrl) => {
+    if (!connectTunnelAgents.has(proxyUrl)) {
+      connectTunnelAgents.set(proxyUrl, outboundHttpProxyAgent(targetUrl));
+    }
+    return connectTunnelAgents.get(proxyUrl);
+  };
   mitmServer.on("upgrade", (req, socket, head) => {
     forwardAnthropicUpgrade(
       req,
@@ -20462,6 +20528,65 @@ async function startHttpProxy(options) {
       clientSocket.end("HTTP/1.1 400 Bad Request\r\n\r\n");
       return;
     }
+    const targetUrl = `https://${req.url}`;
+    const outboundProxyUrl = outboundProxyUrlForTarget(targetUrl);
+    const bound = proxyServer.address();
+    const selfTargeting = outboundProxyUrl !== void 0 && bound !== null && typeof bound !== "string" && proxyUrlTargetsListener(outboundProxyUrl, bound.address, bound.port);
+    if (selfTargeting && !warnedConnectSelfProxy) {
+      warnedConnectSelfProxy = true;
+      emitParentNotice(
+        "clodex: HTTP(S)_PROXY points at this proxy; tunneling CONNECT direct"
+      );
+    }
+    const outboundAgent = outboundProxyUrl !== void 0 && !selfTargeting ? connectTunnelAgent(outboundProxyUrl, targetUrl) : void 0;
+    if (outboundAgent) {
+      let upstream2;
+      let proxyConnectStatus;
+      req.once("proxyConnect", (response) => {
+        proxyConnectStatus = response.statusCode;
+      });
+      clientSocket.once("close", () => {
+        if (upstream2 && !upstream2.destroyed) upstream2.destroy();
+      });
+      void outboundAgent.connect(req, {
+        host: target.host,
+        port: target.port,
+        secureEndpoint: false
+      }).then((connected) => {
+        upstream2 = connected;
+        if (proxyConnectStatus !== 200 || clientSocket.destroyed) {
+          connected.destroy();
+          if (!clientSocket.destroyed) {
+            clientSocket.end("HTTP/1.1 502 Bad Gateway\r\n\r\n", () => clientSocket.destroy());
+          }
+          return;
+        }
+        let tunnelEstablished2 = false;
+        sockets.add(connected);
+        connected.once("close", () => {
+          sockets.delete(connected);
+          if (tunnelEstablished2 && !clientSocket.destroyed) clientSocket.destroy();
+        });
+        connected.once("error", () => {
+          if (clientSocket.destroyed) return;
+          if (tunnelEstablished2) {
+            clientSocket.destroy();
+            return;
+          }
+          clientSocket.end("HTTP/1.1 502 Bad Gateway\r\n\r\n", () => clientSocket.destroy());
+        });
+        tunnelEstablished2 = true;
+        clientSocket.write("HTTP/1.1 200 Connection Established\r\n\r\n");
+        if (head.length > 0) connected.write(head);
+        clientSocket.pipe(connected);
+        connected.pipe(clientSocket);
+      }).catch(() => {
+        if (!clientSocket.destroyed) {
+          clientSocket.end("HTTP/1.1 502 Bad Gateway\r\n\r\n", () => clientSocket.destroy());
+        }
+      });
+      return;
+    }
     const upstream = net.connect(target.port, target.host);
     let tunnelEstablished = false;
     sockets.add(upstream);
@@ -20527,6 +20652,8 @@ async function startHttpProxy(options) {
       for (const socket of sockets) socket.destroy();
       await new Promise((resolve4) => proxyServer.close(() => resolve4()));
       mitmServer.close();
+      for (const agent of connectTunnelAgents.values()) agent?.destroy();
+      connectTunnelAgents.clear();
       anthropicAgent?.destroy();
       adapter?.close();
     }
@@ -22242,7 +22369,7 @@ function applyContextStopAssignments(assignments, save, report, saveHint = "Add
       );
       return 1;
     }
-    const limits = contextLimitsFrom(cached, resolveContextWindow(assignment.modelId));
+    const limits = contextLimitsFrom(cached, lookupKnownContextWindow(assignment.modelId));
     const resolved = resolveContextStop(limits, assignment.stop ?? "standard");
     const target = modelAliasTarget(assignment);
     const label = assignment.label === target ? target : `${assignment.label} (${target})`;