thincoder 0.12.23 → 0.12.24

package/README.md

@@ -19,7 +19,7 @@ Design philosophy (the entire meaning of the name): if the Node standard library
 - **Toolset**: `read` / `write` / `edit` / `bash` / `glob` (supports `**`) / `grep` / `websearch` / `ls` / `fetch` + `read_image` (image/video paste) + three retrieval tools + MCP — all zero-dependency, file tools confined to the working directory
 - **Memory system**: three layers (personal/project/team), FTS5 + vector RRF hybrid retrieval, git-friendly markdown format
 - **Two-phase tool scheduling**: permission prompts serialized, read-only tools parallelized, side-effect tools serialized
-- **Session persistence** ⭐0.5.0: up to 5 archive slots, `/session` to switch anytime, tool results visible after restore. Process-level isolation — multiple instances in the same directory each get their own session slot
+- **Session persistence** ⭐0.5.0: unlimited archive slots, `/session` to switch anytime, tool results visible after restore. Process-level isolation — multiple instances in the same directory each get their own session slot
 - **Concurrent subagents**: three roles — `explore`/`plan`/`coder` — dispatched in parallel, streaming output visible, reports land in the conversation; per-subagent model override (`subagent` tool `model` arg or `agent.subagentModel` config — e.g. discuss with `glm-5.2`, let `deepseek-v4-flash` implement)
 - **Plan Mode**: read-only exploration + design, implement after user approval
 - **AUTO mode**: `/auto` full authorization, no confirmations on long tasks
@@ -183,7 +183,7 @@ src/
   memory/           three-layer memory — schema.mjs (DDL/constants), core.mjs (CRUD + retrieval),
                     code-index.mjs + code-sync.mjs (code_chunks), docs.mjs (doc_chunks)
   memory.mjs        re-export shim → src/memory/*
-  session.mjs       session persistence (up to 5 archive slots, isolated by project cwd, process-level isolation via sessionId + slotSessions)
+  session.mjs       session persistence (unlimited archive slots, isolated by project cwd, process-level isolation via sessionId + slotSessions)
   skills.mjs        skill discovery/loading (.thincoder/skills/*.md)
   markdown.mjs      entry format (frontmatter parse/serialize)
   git/              checkpoint.mjs (git patch snapshots / rewind), gitmem.mjs (Team layer git sync)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "thincoder",
-  "version": "0.12.23",
+  "version": "0.12.24",
   "description": "Thin coding agent - zero dependencies, no build step, Node.js native. Sharp code, zero bloat.",
   "keywords": [
     "ai",
@@ -27,7 +27,7 @@
   ],
   "repository": {
     "type": "git",
-    "url": "https://gitee.com/shanghai-xinbo/thincoder.git"
+    "url": "https://github.com/xinbo-tech/thincoder.git"
   },
   "scripts": {
     "test": "node --test \"test/*.mjs\"",

package/src/agent.mjs

@@ -346,7 +346,7 @@ export async function runAgent(agent, input, callbacks = {}, { depth = 0, signal
           const parsed = JSON.parse(result)
           if (parsed.images?.length) {
             // tool message first — closes the tool_call pairing (OpenAI API requires tool result immediately after assistant with tool_calls)
-            pushReal(agent, { role: "tool", tool_call_id: toolCall.id, content: parsed.text })
+            pushReal(agent, { role: "tool", tool_call_id: toolCall.id, name: toolCall.name, content: parsed.text })
             if (specForModel(agent.provider.model).multimodal) {
               // then inject multimodal user message with base64 images for the model to actually "see" them on the next turn
               deferredUserMsgs.push({
@@ -371,7 +371,7 @@ export async function runAgent(agent, input, callbacks = {}, { depth = 0, signal
           }
         } catch { /* Parse failure doesn't affect normal tool messages */ }
       }
-      pushReal(agent, { role: "tool", tool_call_id: toolCall.id, content: result })
+      pushReal(agent, { role: "tool", tool_call_id: toolCall.id, name: toolCall.name, content: result })
       if (tool && ok) {
         if (FILE_MUTATORS.has(toolCall.name)) {
           // Direct file edit — code was changed. The prior advisor review and

package/src/config.mjs

@@ -18,6 +18,7 @@ export const PROVIDER_PRESETS = {
   kimi:     { baseURL: "https://api.moonshot.cn/v1", model: "kimi-k3", thinking: null, reasoningEffort: "max", maxTokens: 131072, desc: "Kimi / Moonshot" },
   "kimi-code": { baseURL: "https://api.kimi.com/coding/v1", model: "k3", thinking: null, reasoningEffort: "max", maxTokens: 131072, desc: "Kimi For Coding (platform.kimi.com — sk-kimi- keys; NOT interchangeable with Moonshot)" },
   glm:      { baseURL: "https://open.bigmodel.cn/api/paas/v4", model: "glm-5.2", thinking: { type: "enabled" }, reasoningEffort: "max", maxTokens: 128000, desc: "Zhipu GLM" },
+  "glm-code": { baseURL: "https://open.bigmodel.cn/api/coding/paas/v4", model: "glm-5.2", thinking: { type: "enabled" }, reasoningEffort: "max", maxTokens: 128000, desc: "Zhipu GLM Coding Plan (coding endpoint — same key as GLM; server-forced thinking)" },
   qwen:     { baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1", model: "qwen3.7-max", reasoningEffort: "high", maxTokens: 131072, desc: "Qwen / Alibaba" },
   qwenplan: { baseURL: "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1", model: "qwen3.7-max", reasoningEffort: "high", maxTokens: 131072, desc: "Qwen Token Plan (百炼套餐)" },
   minimax:  { baseURL: "https://api.minimaxi.com/v1", model: "MiniMax-M3", thinking: { type: "adaptive" }, maxTokens: 128000, chatPath: "/text/chatcompletion_v2", desc: "MiniMax" },
@@ -91,18 +92,14 @@ const DEFAULTS = {
  */
 const MODEL_SPECS = [
   // DeepSeek V4 series
-  ["deepseek-v4-pro",   { context: 1_000_000, maxOutput: 384_000, thinking: true,  prefixMode: true,  cacheMode: "prompt", thinkApi: "type", reasoningEcho: "required", reasoningEffortEnum: ["high", "max"], tempRange: [0, 2] }],
-  ["deepseek-v4-flash", { context: 1_000_000, maxOutput: 384_000, thinking: true,  prefixMode: true,  cacheMode: "prompt", thinkApi: "type", reasoningEcho: "required", reasoningEffortEnum: ["high", "max"], tempRange: [0, 2] }],
-  ["deepseek-reasoner", { context: 256_000,   maxOutput: 384_000, thinking: true,  prefixMode: true,  cacheMode: "prompt", thinkApi: "type", reasoningEcho: "required", reasoningEffortEnum: ["high", "max"], tempRange: [0, 2] }],
-  ["deepseek-chat",     { context: 256_000,   maxOutput: 384_000, thinking: false, prefixMode: true,  cacheMode: "prompt", thinkApi: "type", reasoningEcho: "required", reasoningEffortEnum: ["high", "max"], tempRange: [0, 2] }],
+  ["deepseek-v4-pro",   { context: 1_000_000, maxOutput: 384_000, thinking: true,  prefixMode: true,  cacheMode: "auto", thinkApi: "type", reasoningEcho: "required", reasoningEffortEnum: ["low", "high", "max"], tempRange: [0, 2] }],
+  ["deepseek-v4-flash", { context: 1_000_000, maxOutput: 384_000, thinking: true,  prefixMode: true,  cacheMode: "auto", thinkApi: "type", reasoningEcho: "required", reasoningEffortEnum: ["low", "high", "max"], tempRange: [0, 2] }],
   // Kimi series
   ["kimi-k3",           { context: 1_000_000, maxOutput: 131_072, thinking: true,  partialMode: true, multimodal: true, cacheMode: "auto",  thinkApi: "effort", reasoningEcho: "required", reasoningEffortEnum: ["low", "high", "max"] }],
   // Qwen router prefixes model IDs with provider namespace: kimi/kimi-k3 → kimi-k3 (IK7K4V)
   ["kimi/kimi-k3",      { context: 1_000_000, maxOutput: 131_072, thinking: true,  partialMode: true, multimodal: true, cacheMode: "auto",  thinkApi: "effort", reasoningEcho: "required", reasoningEffortEnum: ["low", "high", "max"] }],
   // Kimi For Coding endpoint uses the short model ID "k3" (same specs as kimi-k3) — IK5VGJ
   ["k3",                { context: 1_000_000, maxOutput: 131_072, thinking: true,  partialMode: true, multimodal: true, cacheMode: "auto",  thinkApi: "effort", reasoningEcho: "required", reasoningEffortEnum: ["low", "high", "max"] }],
-  ["kimi-k2",           { context: 256_000,   maxOutput: 128_000, thinking: false, partialMode: true, multimodal: true, cacheMode: "none" }],
-  ["moonshot",          { context: 128_000,   maxOutput: 32_000,  thinking: false, cacheMode: "none" }],
   // GLM series
   ["glm-5.2",           { context: 1_000_000, maxOutput: 128_000, thinking: true,  cacheMode: "auto", thinkApi: "type", reasoningEcho: "optional", reasoningEffortEnum: ["max", "xhigh", "high", "medium", "low", "minimal", "none"], tempRange: [0, 1], noUsageStream: true }],
   ["glm-5",             { context: 1_000_000, maxOutput: 128_000, thinking: true,  cacheMode: "auto", thinkApi: "type", reasoningEcho: "optional", reasoningEffortEnum: ["max", "xhigh", "high", "medium", "low", "minimal", "none"], tempRange: [0, 1], noUsageStream: true }],
@@ -115,9 +112,9 @@ const MODEL_SPECS = [
   // qwen3.7-max rejects image parts outright (DashScope 400 "Unexpected item type in content") — text-only
   ["qwen3.7-max",       { context: 1_000_000, maxOutput: 128_000, thinking: true, partialMode: true, cacheMode: "none", thinkApi: "effort", reasoningEffortEnum: ["xhigh", "high"], tempRange: [0, 2] }],
   ["qwen3.8-max",       { context: 1_000_000, maxOutput: 128_000, thinking: true, partialMode: true, multimodal: true, cacheMode: "none", thinkApi: "effort", reasoningEffortEnum: ["xhigh", "high"], tempRange: [0, 2] }],
-  ["qwen-max",          { context: 1_000_000, maxOutput: 128_000, thinking: false, partialMode: true, multimodal: true, cacheMode: "none", thinkApi: "effort", tempRange: [0, 2] }],
-  ["qwen-plus",         { context: 1_000_000, maxOutput: 32_000,  thinking: false, partialMode: true, multimodal: true, cacheMode: "none", thinkApi: "effort", tempRange: [0, 2] }],
-  ["qwen",              { context: 1_000_000, maxOutput: 128_000, thinking: false, partialMode: true, multimodal: true, cacheMode: "none", thinkApi: "effort", tempRange: [0, 2] }],
+  ["qwen-max",          { context: 1_000_000, maxOutput: 131_072, thinking: false, partialMode: true, multimodal: true, cacheMode: "none", thinkApi: "effort", tempRange: [0, 2] }],
+  ["qwen-plus",         { context: 1_000_000, maxOutput: 131_072,  thinking: false, partialMode: true, multimodal: true, cacheMode: "none", thinkApi: "effort", tempRange: [0, 2] }],
+  ["qwen",              { context: 1_000_000, maxOutput: 131_072, thinking: false, partialMode: true, multimodal: true, cacheMode: "none", thinkApi: "effort", tempRange: [0, 2] }],
   // MiniMax series
   ["MiniMax-M3",        { context: 1_000_000, maxOutput: 128_000, thinking: true,  multimodal: true, cacheMode: "auto", thinkApi: "type", thinkEnabledValue: "adaptive", tempRange: [0, 2], noUsageStream: true }],
   ["minimax-m3",        { context: 1_000_000, maxOutput: 128_000, thinking: true,  multimodal: true, cacheMode: "auto", thinkApi: "type", thinkEnabledValue: "adaptive", tempRange: [0, 2], noUsageStream: true }],