codeep 2.11.0 → 2.11.2

package/README.md

@@ -346,7 +346,7 @@ Run `/agents` to list them. The agent invokes them itself via the `delegate` too
 name: migrator
 description: Writes and runs database migrations
 tools: [read_file, write_file, edit_file, execute_command]   # allowlist; omit = all
-model: glm-5.2[1m]        # optional override
+model: glm-5.2            # optional override
 personality: senior-reviewer   # optional preset
 maxIterations: 12         # optional budget
 ---
@@ -1007,7 +1007,7 @@ After installation, `codeep` is available globally in your terminal. Simply run
 **Model favorites** — save provider+model combos and switch instantly:
 ```
 > /provider      # switch to z.ai
-> /model glm-5.2[1m]
+> /model glm-5.2
 > /profile save fast
 
 > /provider      # switch to openai

package/dist/acp/session.js

@@ -90,8 +90,15 @@ export async function runAgentSession(opts) {
     const result = await runAgent(opts.prompt, projectContext, {
         abortSignal: opts.abortSignal,
         onChunk: (text) => { chunksEmitted++; opts.onChunk(text); },
-        onIteration: (_iteration, _message) => {
-            // Intentionally not forwarded — iteration count is internal detail
+        onIteration: (_iteration, message) => {
+            // The bare iteration counter is internal noise, but transient notices —
+            // API retry/backoff ("retrying in Ns") and context warnings (⚠) — are
+            // exactly what the user needs to see when a request stalls, otherwise
+            // the editor just shows an endless "Thinking…" spinner. Surface those
+            // (and only those) as a thought.
+            if (opts.onThought && /retry|⚠/i.test(message)) {
+                opts.onThought(message);
+            }
         },
         onThinking: (text) => {
             if (opts.onThought) {

package/dist/config/index.js

@@ -143,7 +143,7 @@ function createConfig() {
         apiKey: '',
         migrationVersion: 0,
         provider: 'z.ai',
-        model: 'glm-5.2[1m]',
+        model: 'glm-5.2',
         agentMode: 'on',
         ollamaUrl: 'http://localhost:11434',
         ollamaNativeApi: false,

package/dist/config/providers.js

@@ -18,13 +18,10 @@ export const PROVIDERS = {
             },
         },
         models: [
-            { id: 'glm-5.2[1m]', name: 'GLM-5.2 (1M)', description: 'Latest GLM model with 1M context, available to all users' },
             { id: 'glm-5.2', name: 'GLM-5.2', description: 'Latest GLM model, available to all users' },
-            { id: 'glm-5.1', name: 'GLM-5.1', description: 'Previous GLM model, available to all users' },
             { id: 'glm-5-turbo', name: 'GLM-5 Turbo', description: 'Fast GLM-5 variant, available to all users' },
-            { id: 'glm-5', name: 'GLM-5', description: 'Most capable GLM-5 model (Pro/Max plan only)' },
         ],
-        defaultModel: 'glm-5.2[1m]',
+        defaultModel: 'glm-5.2',
         defaultProtocol: 'openai',
         envKey: 'ZAI_API_KEY',
         subscribeUrl: 'https://z.ai/subscribe?ic=NXYNXZOV14',
@@ -47,13 +44,10 @@ export const PROVIDERS = {
             },
         },
         models: [
-            { id: 'glm-5.2[1m]', name: 'GLM-5.2 (1M)', description: 'Latest GLM model with 1M context' },
             { id: 'glm-5.2', name: 'GLM-5.2', description: 'Latest GLM model' },
-            { id: 'glm-5.1', name: 'GLM-5.1', description: 'Previous GLM model' },
             { id: 'glm-5-turbo', name: 'GLM-5 Turbo', description: 'Fast GLM-5 variant' },
-            { id: 'glm-5', name: 'GLM-5', description: 'Most capable GLM-5 model' },
         ],
-        defaultModel: 'glm-5.2[1m]',
+        defaultModel: 'glm-5.2',
         defaultProtocol: 'openai',
         envKey: 'ZAI_API_KEY',
         subscribeUrl: 'https://api.z.ai',
@@ -76,13 +70,10 @@ export const PROVIDERS = {
             },
         },
         models: [
-            { id: 'glm-5.2[1m]', name: 'GLM-5.2 (1M)', description: 'Latest GLM model with 1M context, available to all users' },
             { id: 'glm-5.2', name: 'GLM-5.2', description: 'Latest GLM model, available to all users' },
-            { id: 'glm-5.1', name: 'GLM-5.1', description: 'Previous GLM model, available to all users' },
             { id: 'glm-5-turbo', name: 'GLM-5 Turbo', description: 'Fast GLM-5 variant, available to all users' },
-            { id: 'glm-5', name: 'GLM-5', description: 'Most capable GLM-5 model (Pro/Max plan only)' },
         ],
-        defaultModel: 'glm-5.2[1m]',
+        defaultModel: 'glm-5.2',
         defaultProtocol: 'openai',
         envKey: 'ZAI_CN_API_KEY',
         subscribeUrl: 'https://open.bigmodel.cn/glm-coding',
@@ -105,13 +96,10 @@ export const PROVIDERS = {
             },
         },
         models: [
-            { id: 'glm-5.2[1m]', name: 'GLM-5.2 (1M)', description: 'Latest GLM model with 1M context' },
             { id: 'glm-5.2', name: 'GLM-5.2', description: 'Latest GLM model' },
-            { id: 'glm-5.1', name: 'GLM-5.1', description: 'Previous GLM model' },
             { id: 'glm-5-turbo', name: 'GLM-5 Turbo', description: 'Fast GLM-5 variant' },
-            { id: 'glm-5', name: 'GLM-5', description: 'Most capable GLM-5 model' },
         ],
-        defaultModel: 'glm-5.2[1m]',
+        defaultModel: 'glm-5.2',
         defaultProtocol: 'openai',
         envKey: 'ZAI_CN_API_KEY',
         subscribeUrl: 'https://open.bigmodel.cn',
@@ -229,7 +217,6 @@ export const PROVIDERS = {
             { id: 'gpt-5.5', name: 'GPT-5.5', description: 'Latest GPT model — best for coding' },
             { id: 'gpt-5.4', name: 'GPT-5.4', description: 'Previous generation GPT' },
             { id: 'gpt-5.4-mini', name: 'GPT-5.4 Mini', description: 'Faster and cheaper GPT-5.4' },
-            { id: 'gpt-5.4-nano', name: 'GPT-5.4 Nano', description: 'Most affordable, great for simple tasks' },
         ],
         defaultModel: 'gpt-5.5',
         defaultProtocol: 'openai',
@@ -251,7 +238,6 @@ export const PROVIDERS = {
             },
         },
         models: [
-            { id: 'claude-fable-5', name: 'Claude Fable 5', description: 'Most powerful — new tier above Opus' },
             { id: 'claude-opus-4-8', name: 'Claude Opus 4.8', description: 'Most capable Opus model' },
             { id: 'claude-sonnet-4-6', name: 'Claude Sonnet', description: 'Best balance of speed and intelligence' },
             { id: 'claude-haiku-4-5-20251001', name: 'Claude Haiku', description: 'Fastest and most affordable' },

package/dist/utils/tokenTracker.js

@@ -7,18 +7,13 @@
 // and produce phantom estimates against the wrong context size.
 const MODEL_CONTEXT_WINDOWS = {
     // Z.AI / ZhipuAI
-    'glm-5.2[1m]': 1_000_000,
     'glm-5.2': 200_000,
-    'glm-5.1': 131_072,
-    'glm-5': 80_000,
     'glm-5-turbo': 202_752,
     // OpenAI
     'gpt-5.5': 1_200_000,
     'gpt-5.4': 1_050_000,
     'gpt-5.4-mini': 400_000,
-    'gpt-5.4-nano': 400_000,
     // Anthropic
-    'claude-fable-5': 1_000_000,
     'claude-opus-4-8': 1_000_000,
     'claude-sonnet-4-6': 1_000_000,
     'claude-haiku-4-5-20251001': 200_000,
@@ -48,18 +43,13 @@ const MODEL_PRICING = {
     // its successor) provisionally so /cost stays sane; update when z.ai posts it.
     // Note: on the GLM Coding Plan (the default `z.ai` provider) billing is a flat
     // subscription, so this only affects the pay-per-use estimate.
-    'glm-5.2[1m]': { inputPer1M: 1.00, outputPer1M: 3.20 },
     'glm-5.2': { inputPer1M: 1.00, outputPer1M: 3.20 },
-    'glm-5.1': { inputPer1M: 1.00, outputPer1M: 3.20 },
-    'glm-5': { inputPer1M: 0.72, outputPer1M: 2.30 },
     'glm-5-turbo': { inputPer1M: 1.20, outputPer1M: 4.00 },
     // OpenAI
     'gpt-5.5': { inputPer1M: 5.00, outputPer1M: 30.00 },
     'gpt-5.4': { inputPer1M: 2.50, outputPer1M: 15.00 },
     'gpt-5.4-mini': { inputPer1M: 0.75, outputPer1M: 4.50 },
-    'gpt-5.4-nano': { inputPer1M: 0.20, outputPer1M: 1.25 },
     // Anthropic
-    'claude-fable-5': { inputPer1M: 10.00, outputPer1M: 50.00 },
     'claude-opus-4-8': { inputPer1M: 5.00, outputPer1M: 25.00 },
     'claude-sonnet-4-6': { inputPer1M: 3.00, outputPer1M: 15.00 },
     'claude-haiku-4-5-20251001': { inputPer1M: 1.00, outputPer1M: 5.00 },

package/dist/version.d.ts

@@ -1 +1 @@
-export declare const VERSION = "2.11.0";
+export declare const VERSION = "2.11.2";

package/dist/version.js

@@ -1,4 +1,4 @@
 // AUTO-GENERATED by scripts/gen-version.js — do not edit by hand.
 // Baked from package.json at build time so the bun-compiled binary reports
 // the right version (it has no package.json on disk to read at runtime).
-export const VERSION = '2.11.0';
+export const VERSION = '2.11.2';

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "codeep",
-  "version": "2.11.0",
+  "version": "2.11.2",
   "description": "AI-powered coding assistant built for the terminal. Multiple LLM providers, project-aware context, and a seamless development workflow.",
   "type": "module",
   "main": "dist/index.js",