@jeffreycao/copilot-api 1.3.5 → 1.3.7

package/README.md

@@ -254,6 +254,7 @@ The following command line options are available for the `start` command:
         "enabled": true,
         "baseUrl": "your-base-url",
         "apiKey": "sk-your-provider-key",
+        "adjustInputTokens": false,
         "models": {
           "kimi-k2.5": {
             "temperature": 1,
@@ -275,7 +276,6 @@ The following command line options are available for the `start` command:
       "gpt-5.4": "xhigh"
     },
     "useFunctionApplyPatch": true,
-    "compactUseSmallModel": true,
     "useMessagesApi": true
   }
   ```
@@ -285,6 +285,7 @@ The following command line options are available for the `start` command:
   - `enabled` defaults to `true` if omitted.
   - `baseUrl` should be provider API base URL without trailing `/v1/messages`.
   - `apiKey` is used as upstream `x-api-key`.
+  - `adjustInputTokens` (optional): When `true`, the proxy will adjust the `input_tokens` in the usage response by subtracting `cache_read_input_tokens` and `cache_creation_input_tokens`. 
   - `models` (optional): Per-model configuration map. Each key is a model ID (matching the model name in requests), and the value is:
     - `temperature` (optional): Default temperature value used when the request does not specify one.
     - `topP` (optional): Default top_p value used when the request does not specify one.
@@ -293,7 +294,6 @@ The following command line options are available for the `start` command:
 - **responsesApiContextManagementModels:** List of model IDs that should receive Responses API `context_management` compaction instructions. Use this when a model supports server-side context management and you want the proxy to keep only the latest compaction carrier on follow-up turns.
 - **modelReasoningEfforts:** Per-model `reasoning.effort` sent to the Copilot Responses API. Allowed values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`. If a model isn’t listed, `high` is used by default.
 - **useFunctionApplyPatch:** When `true`, the server will convert any custom tool named `apply_patch` in Responses payloads into an OpenAI-style function tool (`type: "function"`) with a parameter schema so assistants can call it using function-calling semantics to edit files. Set to `false` to leave tools unchanged. Defaults to `true`.
-- **compactUseSmallModel:** When `true`, detected "compact" requests (e.g., from Claude Code or Opencode compact mode) will automatically use the configured `smallModel` to avoid consuming premium model usage for short/background tasks. Defaults to `true`.
 - **useMessagesApi:** When `true`, Claude-family models that support Copilot's native `/v1/messages` endpoint will use the Messages API; otherwise they fall back to `/chat/completions`. Set to `false` to disable Messages API routing and always use `/chat/completions`. Defaults to `true`.
 
 Edit this file to customize prompts or swap in your own fast model. Restart the server (or rerun the command) after changes so the cached config is refreshed.

package/dist/{auth-PjO-EXxs.js → auth-DteTbqnM.js}

@@ -1,6 +1,6 @@
 import { PATHS, ensurePaths } from "./paths-Cla6y5eD.js";
-import { state } from "./utils-artyYmCm.js";
-import { setupGitHubToken } from "./token-G21yvpKv.js";
+import { state } from "./utils-DKqD66k9.js";
+import { setupGitHubToken } from "./token-8AyBHdsS.js";
 import { defineCommand } from "citty";
 import consola from "consola";
 
@@ -43,4 +43,4 @@ const auth = defineCommand({
 
 //#endregion
 export { auth };
-//# sourceMappingURL=auth-PjO-EXxs.js.map
+//# sourceMappingURL=auth-DteTbqnM.js.map

package/dist/{auth-PjO-EXxs.js.map → auth-DteTbqnM.js.map}

@@ -1 +1 @@
-{"version":3,"file":"auth-PjO-EXxs.js","names":[],"sources":["../src/auth.ts"],"sourcesContent":["#!/usr/bin/env node\n\nimport { defineCommand } from \"citty\"\nimport consola from \"consola\"\n\nimport { PATHS, ensurePaths } from \"./lib/paths\"\nimport { state } from \"./lib/state\"\nimport { setupGitHubToken } from \"./lib/token\"\n\ninterface RunAuthOptions {\n  verbose: boolean\n  showToken: boolean\n}\n\nexport async function runAuth(options: RunAuthOptions): Promise<void> {\n  if (options.verbose) {\n    consola.level = 5\n    consola.info(\"Verbose logging enabled\")\n  }\n\n  state.showToken = options.showToken\n\n  await ensurePaths()\n  await setupGitHubToken({ force: true })\n  consola.success(\"GitHub token written to\", PATHS.GITHUB_TOKEN_PATH)\n}\n\nexport const auth = defineCommand({\n  meta: {\n    name: \"auth\",\n    description: \"Run GitHub auth flow without running the server\",\n  },\n  args: {\n    verbose: {\n      alias: \"v\",\n      type: \"boolean\",\n      default: false,\n      description: \"Enable verbose logging\",\n    },\n    \"show-token\": {\n      type: \"boolean\",\n      default: false,\n      description: \"Show GitHub token on auth\",\n    },\n  },\n  run({ args }) {\n    return runAuth({\n      verbose: args.verbose,\n      showToken: args[\"show-token\"],\n    })\n  },\n})\n"],"mappings":";;;;;;;AAcA,eAAsB,QAAQ,SAAwC;AACpE,KAAI,QAAQ,SAAS;AACnB,UAAQ,QAAQ;AAChB,UAAQ,KAAK,0BAA0B;;AAGzC,OAAM,YAAY,QAAQ;AAE1B,OAAM,aAAa;AACnB,OAAM,iBAAiB,EAAE,OAAO,MAAM,CAAC;AACvC,SAAQ,QAAQ,2BAA2B,MAAM,kBAAkB;;AAGrE,MAAa,OAAO,cAAc;CAChC,MAAM;EACJ,MAAM;EACN,aAAa;EACd;CACD,MAAM;EACJ,SAAS;GACP,OAAO;GACP,MAAM;GACN,SAAS;GACT,aAAa;GACd;EACD,cAAc;GACZ,MAAM;GACN,SAAS;GACT,aAAa;GACd;EACF;CACD,IAAI,EAAE,QAAQ;AACZ,SAAO,QAAQ;GACb,SAAS,KAAK;GACd,WAAW,KAAK;GACjB,CAAC;;CAEL,CAAC"}
+{"version":3,"file":"auth-DteTbqnM.js","names":[],"sources":["../src/auth.ts"],"sourcesContent":["#!/usr/bin/env node\n\nimport { defineCommand } from \"citty\"\nimport consola from \"consola\"\n\nimport { PATHS, ensurePaths } from \"./lib/paths\"\nimport { state } from \"./lib/state\"\nimport { setupGitHubToken } from \"./lib/token\"\n\ninterface RunAuthOptions {\n  verbose: boolean\n  showToken: boolean\n}\n\nexport async function runAuth(options: RunAuthOptions): Promise<void> {\n  if (options.verbose) {\n    consola.level = 5\n    consola.info(\"Verbose logging enabled\")\n  }\n\n  state.showToken = options.showToken\n\n  await ensurePaths()\n  await setupGitHubToken({ force: true })\n  consola.success(\"GitHub token written to\", PATHS.GITHUB_TOKEN_PATH)\n}\n\nexport const auth = defineCommand({\n  meta: {\n    name: \"auth\",\n    description: \"Run GitHub auth flow without running the server\",\n  },\n  args: {\n    verbose: {\n      alias: \"v\",\n      type: \"boolean\",\n      default: false,\n      description: \"Enable verbose logging\",\n    },\n    \"show-token\": {\n      type: \"boolean\",\n      default: false,\n      description: \"Show GitHub token on auth\",\n    },\n  },\n  run({ args }) {\n    return runAuth({\n      verbose: args.verbose,\n      showToken: args[\"show-token\"],\n    })\n  },\n})\n"],"mappings":";;;;;;;AAcA,eAAsB,QAAQ,SAAwC;AACpE,KAAI,QAAQ,SAAS;AACnB,UAAQ,QAAQ;AAChB,UAAQ,KAAK,0BAA0B;;AAGzC,OAAM,YAAY,QAAQ;AAE1B,OAAM,aAAa;AACnB,OAAM,iBAAiB,EAAE,OAAO,MAAM,CAAC;AACvC,SAAQ,QAAQ,2BAA2B,MAAM,kBAAkB;;AAGrE,MAAa,OAAO,cAAc;CAChC,MAAM;EACJ,MAAM;EACN,aAAa;EACd;CACD,MAAM;EACJ,SAAS;GACP,OAAO;GACP,MAAM;GACN,SAAS;GACT,aAAa;GACd;EACD,cAAc;GACZ,MAAM;GACN,SAAS;GACT,aAAa;GACd;EACF;CACD,IAAI,EAAE,QAAQ;AACZ,SAAO,QAAQ;GACb,SAAS,KAAK;GACd,WAAW,KAAK;GACjB,CAAC;;CAEL,CAAC"}

package/dist/{check-usage-C9abXGdq.js → check-usage-Z8fnzZQt.js}

@@ -1,7 +1,7 @@
 import { ensurePaths } from "./paths-Cla6y5eD.js";
-import "./utils-artyYmCm.js";
-import { setupGitHubToken } from "./token-G21yvpKv.js";
-import { getCopilotUsage } from "./get-copilot-usage-xj7WA78o.js";
+import "./utils-DKqD66k9.js";
+import { setupGitHubToken } from "./token-8AyBHdsS.js";
+import { getCopilotUsage } from "./get-copilot-usage-CuVET98U.js";
 import { defineCommand } from "citty";
 import consola from "consola";
 
@@ -42,4 +42,4 @@ const checkUsage = defineCommand({
 
 //#endregion
 export { checkUsage };
-//# sourceMappingURL=check-usage-C9abXGdq.js.map
+//# sourceMappingURL=check-usage-Z8fnzZQt.js.map

package/dist/{check-usage-C9abXGdq.js.map → check-usage-Z8fnzZQt.js.map}

@@ -1 +1 @@
-{"version":3,"file":"check-usage-C9abXGdq.js","names":[],"sources":["../src/check-usage.ts"],"sourcesContent":["import { defineCommand } from \"citty\"\nimport consola from \"consola\"\n\nimport { ensurePaths } from \"./lib/paths\"\nimport { setupGitHubToken } from \"./lib/token\"\nimport {\n  getCopilotUsage,\n  type QuotaDetail,\n} from \"./services/github/get-copilot-usage\"\n\nexport const checkUsage = defineCommand({\n  meta: {\n    name: \"check-usage\",\n    description: \"Show current GitHub Copilot usage/quota information\",\n  },\n  async run() {\n    await ensurePaths()\n    await setupGitHubToken()\n    try {\n      const usage = await getCopilotUsage()\n      const premium = usage.quota_snapshots.premium_interactions\n      const premiumTotal = premium.entitlement\n      const premiumUsed = premiumTotal - premium.remaining\n      const premiumPercentUsed =\n        premiumTotal > 0 ? (premiumUsed / premiumTotal) * 100 : 0\n      const premiumPercentRemaining = premium.percent_remaining\n\n      // Helper to summarize a quota snapshot\n      function summarizeQuota(name: string, snap: QuotaDetail | undefined) {\n        if (!snap) return `${name}: N/A`\n        const total = snap.entitlement\n        const used = total - snap.remaining\n        const percentUsed = total > 0 ? (used / total) * 100 : 0\n        const percentRemaining = snap.percent_remaining\n        return `${name}: ${used}/${total} used (${percentUsed.toFixed(1)}% used, ${percentRemaining.toFixed(1)}% remaining)`\n      }\n\n      const premiumLine = `Premium: ${premiumUsed}/${premiumTotal} used (${premiumPercentUsed.toFixed(1)}% used, ${premiumPercentRemaining.toFixed(1)}% remaining)`\n      const chatLine = summarizeQuota(\"Chat\", usage.quota_snapshots.chat)\n      const completionsLine = summarizeQuota(\n        \"Completions\",\n        usage.quota_snapshots.completions,\n      )\n\n      consola.box(\n        `Copilot Usage (plan: ${usage.copilot_plan})\\n`\n          + `Quota resets: ${usage.quota_reset_date}\\n`\n          + `\\nQuotas:\\n`\n          + `  ${premiumLine}\\n`\n          + `  ${chatLine}\\n`\n          + `  ${completionsLine}`,\n      )\n    } catch (err) {\n      consola.error(\"Failed to fetch Copilot usage:\", err)\n      process.exit(1)\n    }\n  },\n})\n"],"mappings":";;;;;;;;AAUA,MAAa,aAAa,cAAc;CACtC,MAAM;EACJ,MAAM;EACN,aAAa;EACd;CACD,MAAM,MAAM;AACV,QAAM,aAAa;AACnB,QAAM,kBAAkB;AACxB,MAAI;GACF,MAAM,QAAQ,MAAM,iBAAiB;GACrC,MAAM,UAAU,MAAM,gBAAgB;GACtC,MAAM,eAAe,QAAQ;GAC7B,MAAM,cAAc,eAAe,QAAQ;GAC3C,MAAM,qBACJ,eAAe,IAAK,cAAc,eAAgB,MAAM;GAC1D,MAAM,0BAA0B,QAAQ;GAGxC,SAAS,eAAe,MAAc,MAA+B;AACnE,QAAI,CAAC,KAAM,QAAO,GAAG,KAAK;IAC1B,MAAM,QAAQ,KAAK;IACnB,MAAM,OAAO,QAAQ,KAAK;IAC1B,MAAM,cAAc,QAAQ,IAAK,OAAO,QAAS,MAAM;IACvD,MAAM,mBAAmB,KAAK;AAC9B,WAAO,GAAG,KAAK,IAAI,KAAK,GAAG,MAAM,SAAS,YAAY,QAAQ,EAAE,CAAC,UAAU,iBAAiB,QAAQ,EAAE,CAAC;;GAGzG,MAAM,cAAc,YAAY,YAAY,GAAG,aAAa,SAAS,mBAAmB,QAAQ,EAAE,CAAC,UAAU,wBAAwB,QAAQ,EAAE,CAAC;GAChJ,MAAM,WAAW,eAAe,QAAQ,MAAM,gBAAgB,KAAK;GACnE,MAAM,kBAAkB,eACtB,eACA,MAAM,gBAAgB,YACvB;AAED,WAAQ,IACN,wBAAwB,MAAM,aAAa,mBACtB,MAAM,iBAAiB,iBAEnC,YAAY,MACZ,SAAS,MACT,kBACV;WACM,KAAK;AACZ,WAAQ,MAAM,kCAAkC,IAAI;AACpD,WAAQ,KAAK,EAAE;;;CAGpB,CAAC"}
+{"version":3,"file":"check-usage-Z8fnzZQt.js","names":[],"sources":["../src/check-usage.ts"],"sourcesContent":["import { defineCommand } from \"citty\"\nimport consola from \"consola\"\n\nimport { ensurePaths } from \"./lib/paths\"\nimport { setupGitHubToken } from \"./lib/token\"\nimport {\n  getCopilotUsage,\n  type QuotaDetail,\n} from \"./services/github/get-copilot-usage\"\n\nexport const checkUsage = defineCommand({\n  meta: {\n    name: \"check-usage\",\n    description: \"Show current GitHub Copilot usage/quota information\",\n  },\n  async run() {\n    await ensurePaths()\n    await setupGitHubToken()\n    try {\n      const usage = await getCopilotUsage()\n      const premium = usage.quota_snapshots.premium_interactions\n      const premiumTotal = premium.entitlement\n      const premiumUsed = premiumTotal - premium.remaining\n      const premiumPercentUsed =\n        premiumTotal > 0 ? (premiumUsed / premiumTotal) * 100 : 0\n      const premiumPercentRemaining = premium.percent_remaining\n\n      // Helper to summarize a quota snapshot\n      function summarizeQuota(name: string, snap: QuotaDetail | undefined) {\n        if (!snap) return `${name}: N/A`\n        const total = snap.entitlement\n        const used = total - snap.remaining\n        const percentUsed = total > 0 ? (used / total) * 100 : 0\n        const percentRemaining = snap.percent_remaining\n        return `${name}: ${used}/${total} used (${percentUsed.toFixed(1)}% used, ${percentRemaining.toFixed(1)}% remaining)`\n      }\n\n      const premiumLine = `Premium: ${premiumUsed}/${premiumTotal} used (${premiumPercentUsed.toFixed(1)}% used, ${premiumPercentRemaining.toFixed(1)}% remaining)`\n      const chatLine = summarizeQuota(\"Chat\", usage.quota_snapshots.chat)\n      const completionsLine = summarizeQuota(\n        \"Completions\",\n        usage.quota_snapshots.completions,\n      )\n\n      consola.box(\n        `Copilot Usage (plan: ${usage.copilot_plan})\\n`\n          + `Quota resets: ${usage.quota_reset_date}\\n`\n          + `\\nQuotas:\\n`\n          + `  ${premiumLine}\\n`\n          + `  ${chatLine}\\n`\n          + `  ${completionsLine}`,\n      )\n    } catch (err) {\n      consola.error(\"Failed to fetch Copilot usage:\", err)\n      process.exit(1)\n    }\n  },\n})\n"],"mappings":";;;;;;;;AAUA,MAAa,aAAa,cAAc;CACtC,MAAM;EACJ,MAAM;EACN,aAAa;EACd;CACD,MAAM,MAAM;AACV,QAAM,aAAa;AACnB,QAAM,kBAAkB;AACxB,MAAI;GACF,MAAM,QAAQ,MAAM,iBAAiB;GACrC,MAAM,UAAU,MAAM,gBAAgB;GACtC,MAAM,eAAe,QAAQ;GAC7B,MAAM,cAAc,eAAe,QAAQ;GAC3C,MAAM,qBACJ,eAAe,IAAK,cAAc,eAAgB,MAAM;GAC1D,MAAM,0BAA0B,QAAQ;GAGxC,SAAS,eAAe,MAAc,MAA+B;AACnE,QAAI,CAAC,KAAM,QAAO,GAAG,KAAK;IAC1B,MAAM,QAAQ,KAAK;IACnB,MAAM,OAAO,QAAQ,KAAK;IAC1B,MAAM,cAAc,QAAQ,IAAK,OAAO,QAAS,MAAM;IACvD,MAAM,mBAAmB,KAAK;AAC9B,WAAO,GAAG,KAAK,IAAI,KAAK,GAAG,MAAM,SAAS,YAAY,QAAQ,EAAE,CAAC,UAAU,iBAAiB,QAAQ,EAAE,CAAC;;GAGzG,MAAM,cAAc,YAAY,YAAY,GAAG,aAAa,SAAS,mBAAmB,QAAQ,EAAE,CAAC,UAAU,wBAAwB,QAAQ,EAAE,CAAC;GAChJ,MAAM,WAAW,eAAe,QAAQ,MAAM,gBAAgB,KAAK;GACnE,MAAM,kBAAkB,eACtB,eACA,MAAM,gBAAgB,YACvB;AAED,WAAQ,IACN,wBAAwB,MAAM,aAAa,mBACtB,MAAM,iBAAiB,iBAEnC,YAAY,MACZ,SAAS,MACT,kBACV;WACM,KAAK;AACZ,WAAQ,MAAM,kCAAkC,IAAI;AACpD,WAAQ,KAAK,EAAE;;;CAGpB,CAAC"}

package/dist/{config-D3COstcJ.js → config-DYOE_-p1.js}

@@ -44,7 +44,6 @@ const defaultConfig = {
 		"gpt-5.4": "xhigh"
 	},
 	useFunctionApplyPatch: true,
-	compactUseSmallModel: true,
 	useMessagesApi: true
 };
 let cachedConfig = null;
@@ -133,9 +132,6 @@ function isResponsesApiContextManagementModel(model) {
 function getReasoningEffortForModel(model) {
 	return getConfig().modelReasoningEfforts?.[model] ?? "high";
 }
-function shouldCompactUseSmallModel() {
-	return getConfig().compactUseSmallModel ?? true;
-}
 function normalizeProviderBaseUrl(url) {
 	return url.trim().replace(/\/+$/u, "");
 }
@@ -161,7 +157,8 @@ function getProviderConfig(name) {
 		type,
 		baseUrl,
 		apiKey,
-		models: provider.models
+		models: provider.models,
+		adjustInputTokens: provider.adjustInputTokens
 	};
 }
 function isMessagesApiEnabled() {
@@ -169,5 +166,5 @@ function isMessagesApiEnabled() {
 }
 
 //#endregion
-export { getConfig, getExtraPromptForModel, getProviderConfig, getReasoningEffortForModel, getSmallModel, isMessagesApiEnabled, isResponsesApiContextManagementModel, mergeConfigWithDefaults, shouldCompactUseSmallModel };
-//# sourceMappingURL=config-D3COstcJ.js.map
+export { getConfig, getExtraPromptForModel, getProviderConfig, getReasoningEffortForModel, getSmallModel, isMessagesApiEnabled, isResponsesApiContextManagementModel, mergeConfigWithDefaults };
+//# sourceMappingURL=config-DYOE_-p1.js.map

package/dist/config-DYOE_-p1.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"config-DYOE_-p1.js","names":["defaultConfig: AppConfig","cachedConfig: AppConfig | null"],"sources":["../src/lib/config.ts"],"sourcesContent":["import consola from \"consola\"\nimport fs from \"node:fs\"\n\nimport { PATHS } from \"./paths\"\n\nexport interface AppConfig {\n  auth?: {\n    apiKeys?: Array<string>\n  }\n  providers?: Record<string, ProviderConfig>\n  extraPrompts?: Record<string, string>\n  smallModel?: string\n  responsesApiContextManagementModels?: Array<string>\n  modelReasoningEfforts?: Record<\n    string,\n    \"none\" | \"minimal\" | \"low\" | \"medium\" | \"high\" | \"xhigh\"\n  >\n  useFunctionApplyPatch?: boolean\n  useMessagesApi?: boolean\n}\n\nexport interface ModelConfig {\n  temperature?: number\n  topP?: number\n  topK?: number\n}\n\nexport interface ProviderConfig {\n  type?: string\n  enabled?: boolean\n  baseUrl?: string\n  apiKey?: string\n  models?: Record<string, ModelConfig>\n  adjustInputTokens?: boolean\n}\n\nexport interface ResolvedProviderConfig {\n  name: string\n  type: \"anthropic\"\n  baseUrl: string\n  apiKey: string\n  models?: Record<string, ModelConfig>\n  adjustInputTokens?: boolean\n}\n\nconst gpt5ExplorationPrompt = `## Exploration and reading files\n- **Think first.** Before any tool call, decide ALL files/resources you will need.\n- **Batch everything.** If you need multiple files (even from different places), read them together.\n- **multi_tool_use.parallel** Use multi_tool_use.parallel to parallelize tool calls and only this.\n- **Only make sequential calls if you truly cannot know the next file without seeing a result first.**\n- **Workflow:** (a) plan all needed reads → (b) issue one parallel batch → (c) analyze results → (d) repeat if new, unpredictable reads arise.`\n\nconst gpt5CommentaryPrompt = `# Working with the user\n\nYou interact with the user through a terminal. You have 2 ways of communicating with the users:  \n- Share intermediary updates in \\`commentary\\` channel.  \n- After you have completed all your work, send a message to the \\`final\\` channel.  \n\n## Intermediary updates\n\n- Intermediary updates go to the \\`commentary\\` channel.\n- User updates are short updates while you are working, they are NOT final answers.\n- You use 1-2 sentence user updates to communicate progress and new information to the user as you are doing work.\n- Do not begin responses with conversational interjections or meta commentary. Avoid openers such as acknowledgements (“Done —”, “Got it”, “Great question, ”) or framing phrases.\n- You provide user updates frequently, every 20s.\n- Before exploring or doing substantial work, you start with a user update acknowledging the request and explaining your first step. You should include your understanding of the user request and explain what you will do. Avoid commenting on the request or using starters such as \"Got it -\" or \"Understood -\" etc.\n- When exploring, e.g. searching, reading files, you provide user updates as you go, every 20s, explaining what context you are gathering and what you've learned. Vary your sentence structure when providing these updates to avoid sounding repetitive - in particular, don't start each sentence the same way.\n- After you have sufficient context, and the work is substantial, you provide a longer plan (this is the only user update that may be longer than 2 sentences and can contain formatting).\n- Before performing file edits of any kind, you provide updates explaining what edits you are making.\n- As you are thinking, you very frequently provide updates even if not taking any actions, informing the user of your progress. You interrupt your thinking and send multiple updates in a row if thinking for more than 100 words.\n- Tone of your updates MUST match your personality.`\n\nconst defaultConfig: AppConfig = {\n  auth: {\n    apiKeys: [],\n  },\n  providers: {},\n  extraPrompts: {\n    \"gpt-5-mini\": gpt5ExplorationPrompt,\n    \"gpt-5.3-codex\": gpt5CommentaryPrompt,\n    \"gpt-5.4\": gpt5CommentaryPrompt,\n  },\n  smallModel: \"gpt-5-mini\",\n  responsesApiContextManagementModels: [],\n  modelReasoningEfforts: {\n    \"gpt-5-mini\": \"low\",\n    \"gpt-5.3-codex\": \"xhigh\",\n    \"gpt-5.4\": \"xhigh\",\n  },\n  useFunctionApplyPatch: true,\n  useMessagesApi: true,\n}\n\nlet cachedConfig: AppConfig | null = null\n\nfunction ensureConfigFile(): void {\n  try {\n    fs.accessSync(PATHS.CONFIG_PATH, fs.constants.R_OK | fs.constants.W_OK)\n  } catch {\n    fs.mkdirSync(PATHS.APP_DIR, { recursive: true })\n    fs.writeFileSync(\n      PATHS.CONFIG_PATH,\n      `${JSON.stringify(defaultConfig, null, 2)}\\n`,\n      \"utf8\",\n    )\n    try {\n      fs.chmodSync(PATHS.CONFIG_PATH, 0o600)\n    } catch {\n      return\n    }\n  }\n}\n\nfunction readConfigFromDisk(): AppConfig {\n  ensureConfigFile()\n  try {\n    const raw = fs.readFileSync(PATHS.CONFIG_PATH, \"utf8\")\n    if (!raw.trim()) {\n      fs.writeFileSync(\n        PATHS.CONFIG_PATH,\n        `${JSON.stringify(defaultConfig, null, 2)}\\n`,\n        \"utf8\",\n      )\n      return defaultConfig\n    }\n    return JSON.parse(raw) as AppConfig\n  } catch (error) {\n    consola.error(\"Failed to read config file, using default config\", error)\n    return defaultConfig\n  }\n}\n\nfunction mergeDefaultConfig(config: AppConfig): {\n  mergedConfig: AppConfig\n  changed: boolean\n} {\n  const extraPrompts = config.extraPrompts ?? {}\n  const defaultExtraPrompts = defaultConfig.extraPrompts ?? {}\n  const modelReasoningEfforts = config.modelReasoningEfforts ?? {}\n  const defaultModelReasoningEfforts = defaultConfig.modelReasoningEfforts ?? {}\n\n  const missingExtraPromptModels = Object.keys(defaultExtraPrompts).filter(\n    (model) => !Object.hasOwn(extraPrompts, model),\n  )\n\n  const missingReasoningEffortModels = Object.keys(\n    defaultModelReasoningEfforts,\n  ).filter((model) => !Object.hasOwn(modelReasoningEfforts, model))\n\n  const hasExtraPromptChanges = missingExtraPromptModels.length > 0\n  const hasReasoningEffortChanges = missingReasoningEffortModels.length > 0\n\n  if (!hasExtraPromptChanges && !hasReasoningEffortChanges) {\n    return { mergedConfig: config, changed: false }\n  }\n\n  return {\n    mergedConfig: {\n      ...config,\n      extraPrompts: {\n        ...defaultExtraPrompts,\n        ...extraPrompts,\n      },\n      modelReasoningEfforts: {\n        ...defaultModelReasoningEfforts,\n        ...modelReasoningEfforts,\n      },\n    },\n    changed: true,\n  }\n}\n\nexport function mergeConfigWithDefaults(): AppConfig {\n  const config = readConfigFromDisk()\n  const { mergedConfig, changed } = mergeDefaultConfig(config)\n\n  if (changed) {\n    try {\n      fs.writeFileSync(\n        PATHS.CONFIG_PATH,\n        `${JSON.stringify(mergedConfig, null, 2)}\\n`,\n        \"utf8\",\n      )\n    } catch (writeError) {\n      consola.warn(\n        \"Failed to write merged extraPrompts to config file\",\n        writeError,\n      )\n    }\n  }\n\n  cachedConfig = mergedConfig\n  return mergedConfig\n}\n\nexport function getConfig(): AppConfig {\n  cachedConfig ??= readConfigFromDisk()\n  return cachedConfig\n}\n\nexport function getExtraPromptForModel(model: string): string {\n  const config = getConfig()\n  return config.extraPrompts?.[model] ?? \"\"\n}\n\nexport function getSmallModel(): string {\n  const config = getConfig()\n  return config.smallModel ?? \"gpt-5-mini\"\n}\n\nexport function getResponsesApiContextManagementModels(): Array<string> {\n  const config = getConfig()\n  return (\n    config.responsesApiContextManagementModels\n    ?? defaultConfig.responsesApiContextManagementModels\n    ?? []\n  )\n}\n\nexport function isResponsesApiContextManagementModel(model: string): boolean {\n  return getResponsesApiContextManagementModels().includes(model)\n}\n\nexport function getReasoningEffortForModel(\n  model: string,\n): \"none\" | \"minimal\" | \"low\" | \"medium\" | \"high\" | \"xhigh\" {\n  const config = getConfig()\n  return config.modelReasoningEfforts?.[model] ?? \"high\"\n}\n\nexport function normalizeProviderBaseUrl(url: string): string {\n  return url.trim().replace(/\\/+$/u, \"\")\n}\n\nexport function getProviderConfig(name: string): ResolvedProviderConfig | null {\n  const providerName = name.trim()\n  if (!providerName) {\n    return null\n  }\n\n  const config = getConfig()\n  const provider = config.providers?.[providerName]\n  if (!provider) {\n    return null\n  }\n\n  if (provider.enabled === false) {\n    return null\n  }\n\n  const type = provider.type ?? \"anthropic\"\n  if (type !== \"anthropic\") {\n    consola.warn(\n      `Provider ${providerName} is ignored because only anthropic type is supported`,\n    )\n    return null\n  }\n\n  const baseUrl = normalizeProviderBaseUrl(provider.baseUrl ?? \"\")\n  const apiKey = (provider.apiKey ?? \"\").trim()\n  if (!baseUrl || !apiKey) {\n    consola.warn(\n      `Provider ${providerName} is enabled but missing baseUrl or apiKey`,\n    )\n    return null\n  }\n\n  return {\n    name: providerName,\n    type,\n    baseUrl,\n    apiKey,\n    models: provider.models,\n    adjustInputTokens: provider.adjustInputTokens,\n  }\n}\n\nexport function listEnabledProviders(): Array<string> {\n  const config = getConfig()\n  const providerNames = Object.keys(config.providers ?? {})\n  return providerNames.filter((name) => getProviderConfig(name) !== null)\n}\n\nexport function isMessagesApiEnabled(): boolean {\n  const config = getConfig()\n  return config.useMessagesApi ?? true\n}\n"],"mappings":";;;;;AA6CA,MAAM,wBAAwB;;;;;;AAO9B,MAAM,uBAAuB;;;;;;;;;;;;;;;;;;;AAoB7B,MAAMA,gBAA2B;CAC/B,MAAM,EACJ,SAAS,EAAE,EACZ;CACD,WAAW,EAAE;CACb,cAAc;EACZ,cAAc;EACd,iBAAiB;EACjB,WAAW;EACZ;CACD,YAAY;CACZ,qCAAqC,EAAE;CACvC,uBAAuB;EACrB,cAAc;EACd,iBAAiB;EACjB,WAAW;EACZ;CACD,uBAAuB;CACvB,gBAAgB;CACjB;AAED,IAAIC,eAAiC;AAErC,SAAS,mBAAyB;AAChC,KAAI;AACF,KAAG,WAAW,MAAM,aAAa,GAAG,UAAU,OAAO,GAAG,UAAU,KAAK;SACjE;AACN,KAAG,UAAU,MAAM,SAAS,EAAE,WAAW,MAAM,CAAC;AAChD,KAAG,cACD,MAAM,aACN,GAAG,KAAK,UAAU,eAAe,MAAM,EAAE,CAAC,KAC1C,OACD;AACD,MAAI;AACF,MAAG,UAAU,MAAM,aAAa,IAAM;UAChC;AACN;;;;AAKN,SAAS,qBAAgC;AACvC,mBAAkB;AAClB,KAAI;EACF,MAAM,MAAM,GAAG,aAAa,MAAM,aAAa,OAAO;AACtD,MAAI,CAAC,IAAI,MAAM,EAAE;AACf,MAAG,cACD,MAAM,aACN,GAAG,KAAK,UAAU,eAAe,MAAM,EAAE,CAAC,KAC1C,OACD;AACD,UAAO;;AAET,SAAO,KAAK,MAAM,IAAI;UACf,OAAO;AACd,UAAQ,MAAM,oDAAoD,MAAM;AACxE,SAAO;;;AAIX,SAAS,mBAAmB,QAG1B;CACA,MAAM,eAAe,OAAO,gBAAgB,EAAE;CAC9C,MAAM,sBAAsB,cAAc,gBAAgB,EAAE;CAC5D,MAAM,wBAAwB,OAAO,yBAAyB,EAAE;CAChE,MAAM,+BAA+B,cAAc,yBAAyB,EAAE;CAE9E,MAAM,2BAA2B,OAAO,KAAK,oBAAoB,CAAC,QAC/D,UAAU,CAAC,OAAO,OAAO,cAAc,MAAM,CAC/C;CAED,MAAM,+BAA+B,OAAO,KAC1C,6BACD,CAAC,QAAQ,UAAU,CAAC,OAAO,OAAO,uBAAuB,MAAM,CAAC;CAEjE,MAAM,wBAAwB,yBAAyB,SAAS;CAChE,MAAM,4BAA4B,6BAA6B,SAAS;AAExE,KAAI,CAAC,yBAAyB,CAAC,0BAC7B,QAAO;EAAE,cAAc;EAAQ,SAAS;EAAO;AAGjD,QAAO;EACL,cAAc;GACZ,GAAG;GACH,cAAc;IACZ,GAAG;IACH,GAAG;IACJ;GACD,uBAAuB;IACrB,GAAG;IACH,GAAG;IACJ;GACF;EACD,SAAS;EACV;;AAGH,SAAgB,0BAAqC;CACnD,MAAM,SAAS,oBAAoB;CACnC,MAAM,EAAE,cAAc,YAAY,mBAAmB,OAAO;AAE5D,KAAI,QACF,KAAI;AACF,KAAG,cACD,MAAM,aACN,GAAG,KAAK,UAAU,cAAc,MAAM,EAAE,CAAC,KACzC,OACD;UACM,YAAY;AACnB,UAAQ,KACN,sDACA,WACD;;AAIL,gBAAe;AACf,QAAO;;AAGT,SAAgB,YAAuB;AACrC,kBAAiB,oBAAoB;AACrC,QAAO;;AAGT,SAAgB,uBAAuB,OAAuB;AAE5D,QADe,WAAW,CACZ,eAAe,UAAU;;AAGzC,SAAgB,gBAAwB;AAEtC,QADe,WAAW,CACZ,cAAc;;AAG9B,SAAgB,yCAAwD;AAEtE,QADe,WAAW,CAEjB,uCACJ,cAAc,uCACd,EAAE;;AAIT,SAAgB,qCAAqC,OAAwB;AAC3E,QAAO,wCAAwC,CAAC,SAAS,MAAM;;AAGjE,SAAgB,2BACd,OAC0D;AAE1D,QADe,WAAW,CACZ,wBAAwB,UAAU;;AAGlD,SAAgB,yBAAyB,KAAqB;AAC5D,QAAO,IAAI,MAAM,CAAC,QAAQ,SAAS,GAAG;;AAGxC,SAAgB,kBAAkB,MAA6C;CAC7E,MAAM,eAAe,KAAK,MAAM;AAChC,KAAI,CAAC,aACH,QAAO;CAIT,MAAM,WADS,WAAW,CACF,YAAY;AACpC,KAAI,CAAC,SACH,QAAO;AAGT,KAAI,SAAS,YAAY,MACvB,QAAO;CAGT,MAAM,OAAO,SAAS,QAAQ;AAC9B,KAAI,SAAS,aAAa;AACxB,UAAQ,KACN,YAAY,aAAa,sDAC1B;AACD,SAAO;;CAGT,MAAM,UAAU,yBAAyB,SAAS,WAAW,GAAG;CAChE,MAAM,UAAU,SAAS,UAAU,IAAI,MAAM;AAC7C,KAAI,CAAC,WAAW,CAAC,QAAQ;AACvB,UAAQ,KACN,YAAY,aAAa,2CAC1B;AACD,SAAO;;AAGT,QAAO;EACL,MAAM;EACN;EACA;EACA;EACA,QAAQ,SAAS;EACjB,mBAAmB,SAAS;EAC7B;;AASH,SAAgB,uBAAgC;AAE9C,QADe,WAAW,CACZ,kBAAkB"}

package/dist/{get-copilot-usage-xj7WA78o.js → get-copilot-usage-CuVET98U.js}

@@ -1,4 +1,4 @@
-import { HTTPError, getGitHubApiBaseUrl, githubHeaders, state } from "./utils-artyYmCm.js";
+import { HTTPError, getGitHubApiBaseUrl, githubHeaders, state } from "./utils-DKqD66k9.js";
 
 //#region src/services/github/get-copilot-usage.ts
 const getCopilotUsage = async () => {
@@ -9,4 +9,4 @@ const getCopilotUsage = async () => {
 
 //#endregion
 export { getCopilotUsage };
-//# sourceMappingURL=get-copilot-usage-xj7WA78o.js.map
+//# sourceMappingURL=get-copilot-usage-CuVET98U.js.map

package/dist/{get-copilot-usage-xj7WA78o.js.map → get-copilot-usage-CuVET98U.js.map}

@@ -1 +1 @@
-{"version":3,"file":"get-copilot-usage-xj7WA78o.js","names":[],"sources":["../src/services/github/get-copilot-usage.ts"],"sourcesContent":["import { getGitHubApiBaseUrl, githubHeaders } from \"~/lib/api-config\"\nimport { HTTPError } from \"~/lib/error\"\nimport { state } from \"~/lib/state\"\n\nexport const getCopilotUsage = async (): Promise<CopilotUsageResponse> => {\n  const response = await fetch(\n    `${getGitHubApiBaseUrl()}/copilot_internal/user`,\n    {\n      headers: githubHeaders(state),\n    },\n  )\n\n  if (!response.ok) {\n    throw new HTTPError(\"Failed to get Copilot usage\", response)\n  }\n\n  return (await response.json()) as CopilotUsageResponse\n}\n\nexport interface QuotaDetail {\n  entitlement: number\n  overage_count: number\n  overage_permitted: boolean\n  percent_remaining: number\n  quota_id: string\n  quota_remaining: number\n  remaining: number\n  unlimited: boolean\n}\n\ninterface QuotaSnapshots {\n  chat: QuotaDetail\n  completions: QuotaDetail\n  premium_interactions: QuotaDetail\n}\n\ninterface CopilotUsageResponse {\n  access_type_sku: string\n  analytics_tracking_id: string\n  assigned_date: string\n  can_signup_for_limited: boolean\n  chat_enabled: boolean\n  copilot_plan: string\n  organization_login_list: Array<unknown>\n  organization_list: Array<unknown>\n  quota_reset_date: string\n  quota_snapshots: QuotaSnapshots\n}\n"],"mappings":";;;AAIA,MAAa,kBAAkB,YAA2C;CACxE,MAAM,WAAW,MAAM,MACrB,GAAG,qBAAqB,CAAC,yBACzB,EACE,SAAS,cAAc,MAAM,EAC9B,CACF;AAED,KAAI,CAAC,SAAS,GACZ,OAAM,IAAI,UAAU,+BAA+B,SAAS;AAG9D,QAAQ,MAAM,SAAS,MAAM"}
+{"version":3,"file":"get-copilot-usage-CuVET98U.js","names":[],"sources":["../src/services/github/get-copilot-usage.ts"],"sourcesContent":["import { getGitHubApiBaseUrl, githubHeaders } from \"~/lib/api-config\"\nimport { HTTPError } from \"~/lib/error\"\nimport { state } from \"~/lib/state\"\n\nexport const getCopilotUsage = async (): Promise<CopilotUsageResponse> => {\n  const response = await fetch(\n    `${getGitHubApiBaseUrl()}/copilot_internal/user`,\n    {\n      headers: githubHeaders(state),\n    },\n  )\n\n  if (!response.ok) {\n    throw new HTTPError(\"Failed to get Copilot usage\", response)\n  }\n\n  return (await response.json()) as CopilotUsageResponse\n}\n\nexport interface QuotaDetail {\n  entitlement: number\n  overage_count: number\n  overage_permitted: boolean\n  percent_remaining: number\n  quota_id: string\n  quota_remaining: number\n  remaining: number\n  unlimited: boolean\n}\n\ninterface QuotaSnapshots {\n  chat: QuotaDetail\n  completions: QuotaDetail\n  premium_interactions: QuotaDetail\n}\n\ninterface CopilotUsageResponse {\n  access_type_sku: string\n  analytics_tracking_id: string\n  assigned_date: string\n  can_signup_for_limited: boolean\n  chat_enabled: boolean\n  copilot_plan: string\n  organization_login_list: Array<unknown>\n  organization_list: Array<unknown>\n  quota_reset_date: string\n  quota_snapshots: QuotaSnapshots\n}\n"],"mappings":";;;AAIA,MAAa,kBAAkB,YAA2C;CACxE,MAAM,WAAW,MAAM,MACrB,GAAG,qBAAqB,CAAC,yBACzB,EACE,SAAS,cAAc,MAAM,EAC9B,CACF;AAED,KAAI,CAAC,SAAS,GACZ,OAAM,IAAI,UAAU,+BAA+B,SAAS;AAG9D,QAAQ,MAAM,SAAS,MAAM"}

package/dist/main.js

@@ -20,10 +20,10 @@ const args = parseArgs(process.argv, cliArgs);
 if (typeof args["api-home"] === "string") process.env.COPILOT_API_HOME = args["api-home"];
 if (typeof args["oauth-app"] === "string") process.env.COPILOT_API_OAUTH_APP = args["oauth-app"];
 if (typeof args["enterprise-url"] === "string") process.env.COPILOT_API_ENTERPRISE_URL = args["enterprise-url"];
-const { auth } = await import("./auth-PjO-EXxs.js");
-const { checkUsage } = await import("./check-usage-C9abXGdq.js");
+const { auth } = await import("./auth-DteTbqnM.js");
+const { checkUsage } = await import("./check-usage-Z8fnzZQt.js");
 const { debug } = await import("./debug-Dx1S6uWG.js");
-const { start } = await import("./start-CiUssY8j.js");
+const { start } = await import("./start-BaeeWbdc.js");
 const main = defineCommand({
 	meta: {
 		name: "copilot-api",

package/dist/{server-DJvut6rC.js → server-BBSm2bHY.js}

@@ -1,13 +1,14 @@
 import { PATHS } from "./paths-Cla6y5eD.js";
-import { HTTPError, cacheModels, copilotBaseUrl, copilotHeaders, forwardError, generateRequestIdFromPayload, getRootSessionId, getUUID, isNullish, prepareInteractionHeaders, sleep, state } from "./utils-artyYmCm.js";
-import { getCopilotUsage } from "./get-copilot-usage-xj7WA78o.js";
-import { getConfig, getExtraPromptForModel, getProviderConfig, getReasoningEffortForModel, getSmallModel, isMessagesApiEnabled, isResponsesApiContextManagementModel, shouldCompactUseSmallModel } from "./config-D3COstcJ.js";
+import { HTTPError, cacheModels, copilotBaseUrl, copilotHeaders, forwardError, generateRequestIdFromPayload, getRootSessionId, getUUID, isNullish, prepareForCompact, prepareInteractionHeaders, sleep, state } from "./utils-DKqD66k9.js";
+import { getCopilotUsage } from "./get-copilot-usage-CuVET98U.js";
+import { getConfig, getExtraPromptForModel, getProviderConfig, getReasoningEffortForModel, getSmallModel, isMessagesApiEnabled, isResponsesApiContextManagementModel } from "./config-DYOE_-p1.js";
 import consola from "consola";
 import path from "node:path";
 import { Hono } from "hono";
 import { cors } from "hono/cors";
 import { logger } from "hono/logger";
 import fs, { readFileSync } from "node:fs";
+import { AsyncLocalStorage } from "node:async_hooks";
 import { streamSSE } from "hono/streaming";
 import util from "node:util";
 import { events } from "fetch-event-stream";
@@ -57,6 +58,40 @@ function createAuthMiddleware(options = {}) {
 	};
 }
 
+//#endregion
+//#region src/lib/request-context.ts
+const TRACE_ID_MAX_LENGTH = 64;
+const TRACE_ID_PATTERN = /^\w[\w.-]*$/;
+const asyncLocalStorage = new AsyncLocalStorage();
+const requestContext = {
+	getStore: () => asyncLocalStorage.getStore(),
+	run: (context, callback) => asyncLocalStorage.run(context, callback)
+};
+function generateTraceId() {
+	const timestamp = Date.now().toString(36);
+	const random = Math.random().toString(36).slice(2, 8);
+	return `${timestamp}-${random}`;
+}
+function resolveTraceId(traceId) {
+	const candidate = traceId?.trim();
+	if (!candidate || candidate.length > TRACE_ID_MAX_LENGTH || !TRACE_ID_PATTERN.test(candidate)) return generateTraceId();
+	return candidate;
+}
+
+//#endregion
+//#region src/lib/trace.ts
+const traceIdMiddleware = async (c, next) => {
+	const traceId = resolveTraceId(c.req.header("x-trace-id"));
+	c.header("x-trace-id", traceId);
+	const context = {
+		traceId,
+		startTime: Date.now()
+	};
+	await requestContext.run(context, async () => {
+		await next();
+	});
+};
+
 //#endregion
 //#region src/lib/approval.ts
 const awaitApproval = async () => {
@@ -165,12 +200,14 @@ const createHandlerLogger = (name) => {
 			cleanupOldLogs();
 			lastCleanup = Date.now();
 		}
+		const traceId = requestContext.getStore()?.traceId;
 		const date = logObj.date;
 		const dateKey = date.toLocaleDateString("sv-SE");
 		const timestamp = date.toLocaleString("sv-SE", { hour12: false });
 		const filePath = path.join(LOG_DIR, `${sanitizedName}-${dateKey}.log`);
 		const message = formatArgs(logObj.args);
-		const line = `[${timestamp}] [${logObj.type}] [${logObj.tag || name}]${message ? ` ${message}` : ""}`;
+		const traceIdStr = traceId ? ` [${traceId}]` : "";
+		const line = `[${timestamp}] [${logObj.type}] [${logObj.tag || name}]${traceIdStr}${message ? ` ${message}` : ""}`;
 		appendLine(filePath, line);
 	} });
 	return instance;
@@ -433,6 +470,7 @@ const createChatCompletions = async (payload, options) => {
 		"x-initiator": isAgentCall ? "agent" : "user"
 	};
 	prepareInteractionHeaders(options.sessionId, Boolean(options.subagentMarker), headers);
+	prepareForCompact(headers, options.isCompact);
 	const response = await fetch(`${copilotBaseUrl(state)}/chat/completions`, {
 		method: "POST",
 		headers,
@@ -839,13 +877,14 @@ async function handleCountTokens(c) {
 
 //#endregion
 //#region src/services/copilot/create-responses.ts
-const createResponses = async (payload, { vision, initiator, subagentMarker, requestId, sessionId }) => {
+const createResponses = async (payload, { vision, initiator, subagentMarker, requestId, sessionId, isCompact }) => {
 	if (!state.copilotToken) throw new Error("Copilot token not found");
 	const headers = {
 		...copilotHeaders(state, requestId, vision),
 		"x-initiator": initiator
 	};
 	prepareInteractionHeaders(sessionId, Boolean(subagentMarker), headers);
+	prepareForCompact(headers, isCompact);
 	payload.service_tier = null;
 	const response = await fetch(`${copilotBaseUrl(state)}/responses`, {
 		method: "POST",
@@ -1816,6 +1855,7 @@ const createMessages = async (payload, anthropicBetaHeader, options) => {
 		"x-initiator": isInitiateRequest ? "user" : "agent"
 	};
 	prepareInteractionHeaders(options.sessionId, Boolean(options.subagentMarker), headers);
+	prepareForCompact(headers, options.isCompact);
 	const anthropicBeta = buildAnthropicBetaHeader(anthropicBetaHeader, payload.thinking);
 	if (anthropicBeta) headers["anthropic-beta"] = anthropicBeta;
 	const response = await fetch(`${copilotBaseUrl(state)}/v1/messages`, {
@@ -2143,10 +2183,8 @@ async function handleCompletion(c) {
 	logger$5.debug("Anthropic Beta header:", anthropicBeta);
 	const noTools = !anthropicPayload.tools || anthropicPayload.tools.length === 0;
 	if (anthropicBeta && noTools && !isCompact) anthropicPayload.model = getSmallModel();
-	if (isCompact) {
-		logger$5.debug("Is compact request:", isCompact);
-		if (shouldCompactUseSmallModel()) anthropicPayload.model = getSmallModel();
-	} else mergeToolResultForClaude(anthropicPayload);
+	if (isCompact) logger$5.debug("Is compact request:", isCompact);
+	else mergeToolResultForClaude(anthropicPayload);
 	const requestId = generateRequestIdFromPayload(anthropicPayload, sessionId);
 	logger$5.debug("Generated request ID:", requestId);
 	if (state.manualApprove) await awaitApproval();
@@ -2157,30 +2195,34 @@ async function handleCompletion(c) {
 		subagentMarker,
 		selectedModel,
 		requestId,
-		sessionId
+		sessionId,
+		isCompact
 	});
 	if (shouldUseResponsesApi(selectedModel)) return await handleWithResponsesApi(c, anthropicPayload, {
 		subagentMarker,
 		selectedModel,
 		requestId,
-		sessionId
+		sessionId,
+		isCompact
 	});
 	return await handleWithChatCompletions(c, anthropicPayload, {
 		subagentMarker,
 		requestId,
-		sessionId
+		sessionId,
+		isCompact
 	});
 }
 const RESPONSES_ENDPOINT$1 = "/responses";
 const MESSAGES_ENDPOINT = "/v1/messages";
 const handleWithChatCompletions = async (c, anthropicPayload, options) => {
-	const { subagentMarker, requestId, sessionId } = options;
+	const { subagentMarker, requestId, sessionId, isCompact } = options;
 	const openAIPayload = translateToOpenAI(anthropicPayload);
 	logger$5.debug("Translated OpenAI request payload:", JSON.stringify(openAIPayload));
 	const response = await createChatCompletions(openAIPayload, {
 		subagentMarker,
 		requestId,
-		sessionId
+		sessionId,
+		isCompact
 	});
 	if (isNonStreaming(response)) {
 		logger$5.debug("Non-streaming response from Copilot:", JSON.stringify(response));
@@ -2214,7 +2256,7 @@ const handleWithChatCompletions = async (c, anthropicPayload, options) => {
 	});
 };
 const handleWithResponsesApi = async (c, anthropicPayload, options) => {
-	const { subagentMarker, selectedModel, requestId, sessionId } = options;
+	const { subagentMarker, selectedModel, requestId, sessionId, isCompact } = options;
 	const responsesPayload = translateAnthropicMessagesToResponsesPayload(anthropicPayload);
 	applyResponsesApiContextManagement(responsesPayload, selectedModel?.capabilities.limits.max_prompt_tokens);
 	compactInputByLatestCompaction(responsesPayload);
@@ -2225,7 +2267,8 @@ const handleWithResponsesApi = async (c, anthropicPayload, options) => {
 		initiator,
 		subagentMarker,
 		requestId,
-		sessionId
+		sessionId,
+		isCompact
 	});
 	if (responsesPayload.stream && isAsyncIterable$1(response)) {
 		logger$5.debug("Streaming response from Copilot (Responses API)");
@@ -2272,7 +2315,7 @@ const handleWithResponsesApi = async (c, anthropicPayload, options) => {
 	return c.json(anthropicResponse);
 };
 const handleWithMessagesApi = async (c, anthropicPayload, options) => {
-	const { anthropicBetaHeader, subagentMarker, selectedModel, requestId, sessionId } = options;
+	const { anthropicBetaHeader, subagentMarker, selectedModel, requestId, sessionId, isCompact } = options;
 	for (const msg of anthropicPayload.messages) if (msg.role === "assistant" && Array.isArray(msg.content)) msg.content = msg.content.filter((block) => {
 		if (block.type !== "thinking") return true;
 		return block.thinking && block.thinking !== "Thinking..." && block.signature && !block.signature.includes("@");
@@ -2287,7 +2330,8 @@ const handleWithMessagesApi = async (c, anthropicPayload, options) => {
 	const response = await createMessages(anthropicPayload, anthropicBetaHeader, {
 		subagentMarker,
 		requestId,
-		sessionId
+		sessionId,
+		isCompact
 	});
 	if (isAsyncIterable$1(response)) {
 		logger$5.debug("Streaming response from Copilot (Messages API)");
@@ -2544,14 +2588,37 @@ async function handleProviderMessages(c) {
 			provider
 		}));
 		const upstreamResponse = await forwardProviderMessages(providerConfig, payload, c.req.raw.headers);
+		if (!upstreamResponse.ok) {
+			logger$3.error("Failed to create responses", upstreamResponse);
+			throw new HTTPError("Failed to create responses", upstreamResponse);
+		}
 		const contentType = upstreamResponse.headers.get("content-type") ?? "";
 		if (Boolean(payload.stream) && contentType.includes("text/event-stream")) {
 			logger$3.debug("provider.messages.streaming");
 			return streamSSE(c, async (stream) => {
-				for await (const event of events(upstreamResponse)) {
-					const eventName = event.event;
-					const data = event.data ?? "";
-					logger$3.debug("provider.messages.raw_stream_event", data);
+				for await (const chunk of events(upstreamResponse)) {
+					logger$3.debug("provider.messages.raw_stream_event:", chunk.data);
+					const eventName = chunk.event;
+					if (eventName === "ping") {
+						await stream.writeSSE({
+							event: "ping",
+							data: "{\"type\":\"ping\"}"
+						});
+						continue;
+					}
+					let data = chunk.data;
+					if (!data) continue;
+					try {
+						const parsed = JSON.parse(data);
+						if (parsed.type === "message_start") adjustInputTokens(providerConfig, parsed.message.usage);
+						else if (parsed.type === "message_delta") adjustInputTokens(providerConfig, parsed.usage);
+						data = JSON.stringify(parsed);
+					} catch (error) {
+						logger$3.error("provider.messages.streaming.adjust_tokens_error", {
+							error,
+							originalData: data
+						});
+					}
 					await stream.writeSSE({
 						event: eventName,
 						data
@@ -2559,7 +2626,10 @@ async function handleProviderMessages(c) {
 				}
 			});
 		}
-		return createProviderProxyResponse(upstreamResponse);
+		const jsonBody = await upstreamResponse.json();
+		adjustInputTokens(providerConfig, jsonBody.usage);
+		logger$3.debug("provider.messages.no_stream result:", JSON.stringify(jsonBody));
+		return c.json(jsonBody);
 	} catch (error) {
 		logger$3.error("provider.messages.error", {
 			provider,
@@ -2568,6 +2638,11 @@ async function handleProviderMessages(c) {
 		throw error;
 	}
 }
+const adjustInputTokens = (providerConfig, usage) => {
+	if (!providerConfig.adjustInputTokens || !usage) return;
+	usage.input_tokens = Math.max(0, (usage.input_tokens ?? 0) - (usage.cache_read_input_tokens ?? 0) - (usage.cache_creation_input_tokens ?? 0));
+	logger$3.debug("provider.messages.adjusted_usage:", JSON.stringify(usage));
+};
 
 //#endregion
 //#region src/routes/provider/messages/route.ts
@@ -2775,6 +2850,7 @@ usageRoute.get("/", async (c) => {
 //#endregion
 //#region src/server.ts
 const server = new Hono();
+server.use(traceIdMiddleware);
 server.use(logger());
 server.use(cors());
 server.use("*", createAuthMiddleware({ allowUnauthenticatedPaths: [
@@ -2804,4 +2880,4 @@ server.route("/:provider/v1/models", providerModelRoutes);
 
 //#endregion
 export { server };
-//# sourceMappingURL=server-DJvut6rC.js.map
+//# sourceMappingURL=server-BBSm2bHY.js.map