tachibot-mcp 2.21.2 → 2.22.0

package/CHANGELOG.md

@@ -5,6 +5,55 @@ All notable changes to TachiBot MCP will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [2.22.0] - 2026-06-10
+
+### Added
+- **Four new reasoning providers** via OpenRouter: **DeepSeek V4 Pro** (`deepseek_reason`, `deepseek_algo` — open-weight frontier math/CP, top AIME/CodeElo), **Zhipu GLM-5.1** (`glm_reason` — SWE-Bench Pro leader, agentic tool-use), **StepFun Step 3.7 Flash** (`stepfun_reason` — efficient reasoning at flash-tier cost), **Baidu ERNIE 4.5 VL** (`ernie_reason` — broad knowledge, human-preference strength). Each with quota fallbacks and 600s reasoning timeouts.
+- **Local model provider** (`local_query`): any OpenAI-compatible server — Ollama, LM Studio, llama.cpp, vLLM. Ollama gets the native `/api/chat` endpoint so `num_ctx` is honored; failures raise a typed `LocalLLMError`. Configure via `LOCAL_LLM_BASE_URL` / `LOCAL_LLM_MODEL` / `LOCAL_LLM_NUM_CTX`.
+- **Jury roster expansion**: new jurors `deepseek`, `glm`, `stepfun`, `ernie`, `hermes`, `local` (13 total). New lab-diverse default panel: `grok, deepseek, kimi, openai`. Offline jurors are dropped (not error-leaked) when the local server is down.
+- **Three new Claude Code skills**: `/lens` (long-context analysis over Kimi's 256K window), `/reflect` (grounded reflexion loop against external evidence), `/tot` (Tree-of-Thought with jury-based branch pruning). 12 skills total.
+- `deepseek_algo` is now the lead model in `/algo` (strongest algorithmic review).
+
+### Changed
+- Profile counts: minimal 12, code_focus 34, research_power 35, balanced 45, heavy_coding 50, full 57.
+- Merged the `local-models-ollama` release line (v2.21.3–v2.21.5): Gemini 3.5 Flash search tier, Grok 4.3 default, Kimi K2.6 repoints.
+
+## [2.21.5] - 2026-06-04
+
+### Fixed
+- **Kimi tools were calling a retired model.** All Kimi call sites hardcoded `moonshotai/kimi-k2.5`, which OpenRouter no longer serves — every `kimi_*` request failed with a JSON/timeout error (surfaced as "Kimi down"). The model config (`KIMI_MODELS.K2_6`) was already correct but unused by the tools. Repointed all 5 call sites — `kimi_thinking`, `kimi_code`, `kimi_decompose`, `kimi_long_context` (`openrouter-tools.ts`) and the Kimi juror (`jury-tool.ts`) — to `moonshotai/kimi-k2.6`.
+- Fixed the `MODEL_FALLBACKS` entry for `KIMI_K2_6`, which pointed at the retired `KIMI_K2_5`; it now falls back to `KIMI_K2_THINKING` (`moonshotai/kimi-k2-thinking`, still live).
+
+### Notes
+- The `KIMI_K2_5` enum value is retained for back-compat but is marked do-not-call; `moonshotai/kimi-k2.5` is no longer a valid OpenRouter model ID.
+
+## [2.21.4] - 2026-06-01
+
+### Changed
+- **Grok bumped `grok-4.20` → `grok-4.3`** (xAI's Apr 30 2026 flagship). All Grok roles (`grok_reason`, `grok_code`, `grok_debug`, `grok_brainstorm`, `grok_search`, `grok_architect`) now resolve to `grok-4.3`: 1M context, lowest hallucination rate, and **cheaper** ($1.25/$2.50 vs 4.20's $2/$6). Pricing entry dropped `0.004` → `0.001875`.
+- `grok-4.3` is a single model ID with **configurable reasoning effort** (replacing 4.20's reasoning/non-reasoning/multi-agent split). `callGrok` now (a) treats `grok-4.3` as a long-timeout flagship (180s) and (b) forwards `reasoning.effort` for `grok-4.3` as well as multi-agent — so `grok_architect` keeps its `high`-effort behaviour.
+- Repointed `CURRENT_MODELS.grok`, `MODELS.GROK`, workflow `model-router` routing, `ModelProviderRegistry` alias, and `config.ts` available-models list to `grok-4.3`.
+
+### Added
+- `GROK_MODELS._4_3` / `GROK_MODELS._BUILD` constants (+ `GrokModel.GROK_4_3`, `GROK_4_3_LATEST`, `GROK_BUILD`). `grok-build-0.1` (May 29 2026 coding specialist, 256k ctx) added as a constant for future wiring.
+- Display name, pricing, OpenRouter-gateway mapping (`x-ai/grok-4.3`), cost-monitor entry, and ANSI terminal labels (all 4 style maps) for `grok-4.3`.
+
+### Notes
+- Legacy `GROK_4_20_*` enum keys are retained (now resolving to `grok-4.3`) for back-compat; grok-4.20 itself was **not** retired by xAI and remains a valid fallback.
+
+## [2.21.3] - 2026-05-29
+
+### Added
+- **Gemini 3.5 Flash** (`gemini-3.5-flash`) — went GA at Google I/O on 2026-05-19. Now the Flash/search tier: `gemini_query` (`flash`), `gemini_search` grounding, and `tool-mapper` `flash` routing all resolve to it via `GEMINI_MODELS.FLASH`. Agentic/coding focus, 1M context, $1.50/$9 per M tokens. SWE-bench Verified 78.8%, Terminal-bench 76.2%.
+- Display name + pricing for `gemini-3.5-flash`; ANSI terminal labels in all 4 style maps.
+
+### Changed
+- `GEMINI_MODELS.FLASH` alias bumped `gemini-3-flash-preview` → `gemini-3.5-flash`. The legacy `GEMINI_3_FLASH` constant is retained for `model-router.ts` cost tiers.
+
+### Notes
+- **Reasoning default unchanged** — `gemini.default` stays `gemini-3.1-pro-preview`. Gemini 3.5 **Pro** is not yet released (announced at I/O, expected June 2026, no API model ID). Swap the default to 3.5 Pro once it ships.
+- No OpenAI change: GPT-5.5 (Apr 23) remains the latest flagship; no GPT-5.6 exists.
+
 ## [2.21.2] - 2026-05-04
 
 ### Fixed

package/README.md

@@ -5,17 +5,17 @@
 ### Multi-Model AI Orchestration Platform
 
 [![Version](https://img.shields.io/badge/version-2.15.2-blue.svg)](https://www.npmjs.com/package/tachibot-mcp)
-[![Tools](https://img.shields.io/badge/tools-51_active-brightgreen.svg)](#-tool-ecosystem-51-tools)
+[![Tools](https://img.shields.io/badge/tools-57_active-brightgreen.svg)](#-tool-ecosystem-57-tools)
 [![License](https://img.shields.io/badge/license-AGPL--3.0-green.svg)](LICENSE)
 [![Node](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg)](https://nodejs.org)
 [![MCP](https://img.shields.io/badge/MCP-Compatible-purple.svg)](https://modelcontextprotocol.io)
 
-**51 AI tools. 7 providers. One protocol.**
+**57 AI tools. 12 providers. One protocol.**
 
 Orchestrate Perplexity, Grok, GPT-5, Gemini, Qwen, Kimi K2.5, and MiniMax M2.5
 from Claude Code, Claude Desktop, Cursor, or any MCP client.
 
-[Get Started](#-quick-start) · [View Tools](#-tool-ecosystem-51-tools) · [Documentation](https://tachibot.com/docs)
+[Get Started](#-quick-start) · [View Tools](#-tool-ecosystem-57-tools) · [Documentation](https://tachibot.com/docs)
 
 <br>
 
@@ -70,7 +70,7 @@ Techniques are embedded directly in tool system prompts for automatic applicatio
 
 ## Skills (Claude Code)
 
-TachiBot ships with 9 slash commands for Claude Code. These orchestrate the tools into powerful workflows:
+TachiBot ships with 12 slash commands for Claude Code. These orchestrate the tools into powerful workflows:
 
 | Skill | What it does | Example |
 |-------|-------------|---------|
@@ -81,7 +81,10 @@ TachiBot ships with 9 slash commands for Claude Code. These orchestrate the tool
 | `/breakdown` | Strategic decomposition with pre-mortem | `/breakdown refactor payment module` |
 | `/decompose` | Split into sub-problems, deep-dive each one | `/decompose implement collaborative editor` |
 | `/prompt` | Recommend the right thinking technique (31 available) | `/prompt why do users churn` |
-| `/algo` | Algorithm analysis with 3 specialized models | `/algo optimize LRU cache O(1)` |
+| `/algo` | Algorithm analysis with 4 specialized models (DeepSeek lead) | `/algo optimize LRU cache O(1)` |
+| `/lens` | Long-context analysis over Kimi's 256K window | `/lens find inconsistencies in this spec` |
+| `/reflect` | Grounded reflexion loop — critique vs external evidence | `/reflect harden this auth middleware` |
+| `/tot` | Tree-of-Thought: branch → jury-prune → synthesize | `/tot design a rate limiter` |
 | `/tachi` | Help - see available skills, tools, key status | `/tachi` |
 
 Skills automatically adapt to your configured API keys. Even with just 1-2 providers, all skills work.
@@ -93,7 +96,8 @@ Skills automatically adapt to your configured API keys. Even with just 1-2 provi
 ## Key Features
 
 ### Multi-Model Intelligence
-- **51 AI Tools** across 7 providers &mdash; Perplexity, Grok, GPT-5, Gemini, Qwen, Kimi, MiniMax
+- **57 AI Tools** across 12 providers &mdash; Perplexity, Grok, GPT-5, Gemini, Qwen, Kimi, MiniMax, DeepSeek, GLM (Zhipu), StepFun, ERNIE (Baidu), plus free local models (Ollama / LM Studio / llama.cpp / vLLM)
+- **Gemini 3.5 Flash** (`gemini-3.5-flash`, GA May 19 2026) &mdash; Flash/search tier; reasoning default stays `gemini-3.1-pro-preview`
 - **Multi-Model Council** &mdash; planner_maker synthesizes plans from 5+ models into bite-sized TDD steps
 - **Smart Routing** &mdash; Automatic model selection for optimal results
 - **OpenRouter Gateway** &mdash; Optional single API key for all providers
@@ -108,11 +112,11 @@ Skills automatically adapt to your configured API keys. Even with just 1-2 provi
 | Profile | Tools | Best For |
 |---------|-------|----------|
 | **Minimal** | 12 | Quick tasks, low token budget |
-| **Research Power** | 31 | Deep investigation, multi-source |
-| **Code Focus** | 29 | Software development, SWE tasks |
-| **Balanced** | 39 | General-purpose, mixed workflows |
-| **Heavy Coding** (default) | 45 | Max code tools + agentic workflows |
-| **Full** | 51 | Everything enabled |
+| **Research Power** | 35 | Deep investigation, multi-source |
+| **Code Focus** | 34 | Software development, SWE tasks |
+| **Balanced** | 45 | General-purpose, mixed workflows |
+| **Heavy Coding** (default) | 50 | Max code tools + agentic workflows |
+| **Full** | 57 | Everything enabled |
 
 ### Developer Experience
 - **Claude Code** &mdash; First-class support
@@ -174,16 +178,16 @@ See [Installation Guide](docs/INSTALLATION_BOTH.md) for detailed instructions.
 
 ---
 
-## Tool Ecosystem (51 Tools)
+## Tool Ecosystem (57 Tools)
 
 ### Research & Search (6)
 `perplexity_ask` &#183; `perplexity_research` &#183; `perplexity_reason` &#183; `grok_search` &#183; `openai_search` &#183; `gemini_search`
 
-### Reasoning & Planning (9)
-`grok_reason` &#183; `openai_reason` &#183; `qwen_reason` &#183; `qwq_reason` &#183; `kimi_thinking` &#183; `kimi_decompose` &#183; `planner_maker` &#183; `planner_runner` &#183; `list_plans`
+### Reasoning & Planning (13)
+`grok_reason` &#183; `openai_reason` &#183; `qwen_reason` &#183; `qwq_reason` &#183; `kimi_thinking` &#183; `kimi_decompose` &#183; `deepseek_reason` &#183; `glm_reason` &#183; `stepfun_reason` &#183; `ernie_reason` &#183; `planner_maker` &#183; `planner_runner` &#183; `list_plans`
 
-### Code Intelligence (8)
-`kimi_code` &#183; `grok_code` &#183; `grok_debug` &#183; `qwen_coder` &#183; `qwen_algo` &#183; `qwen_competitive` &#183; `minimax_code` &#183; `minimax_agent`
+### Code Intelligence (9)
+`kimi_code` &#183; `grok_code` &#183; `grok_debug` &#183; `qwen_coder` &#183; `qwen_algo` &#183; `qwen_competitive` &#183; `deepseek_algo` &#183; `minimax_code` &#183; `minimax_agent`
 
 ### Analysis & Judgment (11)
 `gemini_analyze_text` &#183; `gemini_analyze_code` &#183; `gemini_judge` &#183; `jury` &#183; `gemini_brainstorm` &#183; `openai_brainstorm` &#183; `openai_code_review` &#183; `openai_explain` &#183; `grok_brainstorm` &#183; `grok_architect` &#183; `kimi_long_context`
@@ -197,6 +201,9 @@ See [Installation Guide](docs/INSTALLATION_BOTH.md) for detailed instructions.
 ### Prompt Engineering (3)
 `list_prompt_techniques` &#183; `preview_prompt_technique` &#183; `execute_prompt_technique`
 
+### Local Models (1)
+`local_query` &mdash; any OpenAI-compatible local server (Ollama / LM Studio / llama.cpp / vLLM). Zero-cost, offline, private; also available as `hermes`/`local` jury jurors.
+
 ### Advanced Modes (bonus)
 - **Challenger** &mdash; Critical analysis with multi-model fact-checking
 - **Verifier** &mdash; Multi-model consensus verification

package/dist/src/config/model-constants.js

@@ -42,15 +42,19 @@ export const OPENAI_REASONING = {
 // =============================================================================
 // GEMINI MODELS (Google)
 // =============================================================================
+// Gemini 3.5 Flash went GA May 19, 2026 (Google I/O) — agentic/coding, 1M ctx, $1.50/$9.
+// It is the new FLASH/search tier. Gemini 3.5 Pro is NOT out yet (June 2026), so the
+// reasoning DEFAULT stays on gemini-3.1-pro-preview until 3.5 Pro ships.
 export const GEMINI_MODELS = {
-    // Gemini 3.1 Pro - default (3.0 Pro retires Mar 9, 2026)
-    GEMINI_3_PRO: "gemini-3.1-pro-preview", // Migrated: 3.0 retires Mar 9
+    // Gemini 3.1 Pro - reasoning default (3.0 Pro retired Mar 9, 2026)
+    GEMINI_3_PRO: "gemini-3.1-pro-preview", // Default: top reasoning model available
     GEMINI_3_1_PRO: "gemini-3.1-pro-preview", // Enhanced reasoning, 1M context
-    GEMINI_3_FLASH: "gemini-3-flash-preview", // Fast frontier model
+    GEMINI_3_5_FLASH: "gemini-3.5-flash", // GA May 19, 2026 - agentic/coding, 1M ctx
+    GEMINI_3_FLASH: "gemini-3-flash-preview", // Legacy fast frontier (kept for model-router)
     GEMINI_3_1_FLASH_LITE: "gemini-3.1-flash-lite", // Mar 3, 2026 - fastest/cheapest in 3.1 series
     // Aliases
     PRO: "gemini-3.1-pro-preview",
-    FLASH: "gemini-3-flash-preview",
+    FLASH: "gemini-3.5-flash", // Bumped: 3-flash-preview -> 3.5-flash (May 2026)
     FLASH_LITE: "gemini-3.1-flash-lite",
 };
 // Perplexity Models
@@ -59,12 +63,18 @@ export const PERPLEXITY_MODELS = {
     SONAR_PRO: "sonar-pro", // Advanced search
     SONAR_REASONING: "sonar-reasoning-pro", // Reasoning model (expensive - avoid)
 };
-// Grok Models (xAI) - Updated 2026-04-10 with Grok 4.20 (Mar 2026)
+// Grok Models (xAI) - Updated 2026-06-01 with Grok 4.3 (Apr 30, 2026 flagship)
 export const GROK_MODELS = {
-    // Grok 4.20 models (Mar 10, 2026) - FLAGSHIP
-    _4_20_REASONING: "grok-4.20-0309-reasoning", // Flagship: 2M context, $2/$6, low hallucination
-    _4_20_NON_REASONING: "grok-4.20-0309-non-reasoning", // Standard: 2M context, $2/$6
-    _4_20_MULTI_AGENT: "grok-4.20-multi-agent-0309", // Multi-agent: 4-16 agents via reasoning.effort, $2/$6
+    // Grok 4.3 (Apr 30, 2026) - CURRENT FLAGSHIP
+    // Single model ID with configurable reasoning effort (replaces 4.20's reasoning/non-reasoning/multi-agent split).
+    // 1M context, $1.25/$2.50 (cheaper than 4.20), xAI's recommended model, lowest hallucination rate.
+    _4_3: "grok-4.3", // Flagship: 1M ctx, $1.25/$2.50, reasoning.effort low|high
+    _4_3_LATEST: "grok-4.3-latest", // Rolling alias for newest 4.3 snapshot
+    _BUILD: "grok-build-0.1", // Coding specialist (May 29, 2026): 256k ctx, fast agentic coding
+    // Grok 4.20 models (Mar 10, 2026) - LEGACY (still valid; kept as fallback). Now resolve to 4.3 via deprecated keys.
+    _4_20_REASONING: "grok-4.3", // [deprecated key] → grok-4.3 (was grok-4.20-0309-reasoning)
+    _4_20_NON_REASONING: "grok-4.3", // [deprecated key] → grok-4.3 (was grok-4.20-0309-non-reasoning)
+    _4_20_MULTI_AGENT: "grok-4.3", // [deprecated key] → grok-4.3 (architect uses high reasoning.effort)
     // Grok 4.1 fast models (Nov 2025) - BEST VALUE (10x cheaper)
     _4_1_FAST_REASONING: "grok-4-1-fast-reasoning", // Fast reasoning: 2M context, $0.20/$0.50
     _4_1_FAST_NON_REASONING: "grok-4-1-fast-non-reasoning", // Tool-calling optimized: 2M context, $0.20/$0.50
@@ -160,12 +170,12 @@ export const CURRENT_MODELS = {
         premium: OPENAI_MODELS.PRO, // Expert mode (gpt-5.5-pro - higher compute)
     },
     grok: {
-        reason: GROK_MODELS._4_20_REASONING, // grok-4.20-0309-reasoning (flagship, low hallucination)
-        code: GROK_MODELS._4_20_NON_REASONING, // grok-4.20 non-reasoning (flagship quality, tool-calling)
-        debug: GROK_MODELS._4_20_NON_REASONING, // grok-4.20 non-reasoning (low hallucination for debugging)
-        brainstorm: GROK_MODELS._4_20_NON_REASONING, // grok-4.20-0309-non-reasoning (2M context)
-        search: GROK_MODELS._4_20_REASONING, // grok-4.20 LOW HALLUCINATION - critical for search
-        architect: GROK_MODELS._4_20_MULTI_AGENT, // grok-4.20-multi-agent-0309 (4-16 agent swarm)
+        reason: GROK_MODELS._4_3, // grok-4.3 (flagship, low hallucination, high reasoning effort)
+        code: GROK_MODELS._4_3, // grok-4.3 (flagship quality, tool-calling)
+        debug: GROK_MODELS._4_3, // grok-4.3 (low hallucination for debugging)
+        brainstorm: GROK_MODELS._4_3, // grok-4.3 (1M context)
+        search: GROK_MODELS._4_3, // grok-4.3 LOW HALLUCINATION - critical for search
+        architect: GROK_MODELS._4_3, // grok-4.3 with high reasoning.effort (agentic swarm behaviour)
     },
     gemini: {
         default: GEMINI_MODELS.GEMINI_3_PRO,
@@ -337,9 +347,13 @@ export const MODEL_DISPLAY_NAMES = {
     "gpt-5.4-pro": "gpt-5.4-pro",
     // Gemini
     "gemini-3.1-pro-preview": "gemini-3.1-pro",
+    "gemini-3.5-flash": "gemini-3.5-flash",
     "gemini-3-flash-preview": "gemini-3-flash",
     "gemini-3.1-flash-lite": "gemini-3.1-flash-lite",
     // Grok (xAI)
+    "grok-4.3": "grok-4.3",
+    "grok-4.3-latest": "grok-4.3",
+    "grok-build-0.1": "grok-build",
     "grok-4.20-0309-reasoning": "grok-4.20",
     "grok-4.20-0309-non-reasoning": "grok-4.20-fast",
     "grok-4.20-multi-agent-0309": "grok-4.20-multi",
@@ -385,12 +399,16 @@ export const MODEL_PRICING = {
     "gpt-5.4-pro": 0.105, // ($30 + $180) / 2 / 1000 (Mar 2026)
     // Gemini
     "gemini-3.1-pro-preview": 0.007, // ($2 + $12) / 2 / 1000
-    "gemini-3-flash-preview": 0.00175, // ($0.50 + $3) / 2 / 1000
+    "gemini-3.5-flash": 0.00525, // ($1.50 + $9) / 2 / 1000 (GA May 19, 2026)
+    "gemini-3-flash-preview": 0.00175, // ($0.50 + $3) / 2 / 1000 (legacy)
     "gemini-3.1-flash-lite": 0.001, // Cheapest/fastest in 3.1 series (Mar 2026)
     // Grok
-    "grok-4.20-0309-reasoning": 0.004, // ($2 + $6) / 2 / 1000
-    "grok-4.20-0309-non-reasoning": 0.004, // ($2 + $6) / 2 / 1000
-    "grok-4.20-multi-agent-0309": 0.004, // ($2 + $6) / 2 / 1000
+    "grok-4.3": 0.001875, // ($1.25 + $2.50) / 2 / 1000 (Apr 30, 2026 - cheaper than 4.20)
+    "grok-4.3-latest": 0.001875,
+    "grok-build-0.1": 0.001875, // Coding specialist (estimate, same tier)
+    "grok-4.20-0309-reasoning": 0.004, // ($2 + $6) / 2 / 1000 (legacy)
+    "grok-4.20-0309-non-reasoning": 0.004, // ($2 + $6) / 2 / 1000 (legacy)
+    "grok-4.20-multi-agent-0309": 0.004, // ($2 + $6) / 2 / 1000 (legacy)
     "grok-4-1-fast-reasoning": 0.00035,
     "grok-4-1-fast-non-reasoning": 0.00035,
     "grok-4-fast-reasoning": 0.00035,

package/dist/src/config/model-defaults.js

@@ -21,7 +21,7 @@ const MODELS = {
     OPENAI: OPENAI_MODELS.THINKING, // gpt-5.5 (default - most capable, agentic)
     OPENAI_REASON: OPENAI_MODELS.THINKING, // gpt-5.5 (deep reasoning)
     // xAI Grok
-    GROK: GROK_MODELS._4_20_REASONING, // grok-4.20-0309-reasoning
+    GROK: GROK_MODELS._4_3, // grok-4.3 (Apr 2026 flagship, 1M ctx, $1.25/$2.50)
     // Perplexity
     PERPLEXITY: PERPLEXITY_MODELS.SONAR, // sonar (cheapest)
     PERPLEXITY_REASON: PERPLEXITY_MODELS.SONAR_REASONING, // sonar-reasoning-pro ($2/$8 per M)

package/dist/src/config/timeout-config.js

@@ -33,12 +33,22 @@ export function getTimeoutConfig() {
 }
 /**
  * Get OpenRouter timeout based on model ID.
- * Thinking/reasoning models get extended timeout (600s default).
+ * Thinking/reasoning/swarm models get extended timeout (600s default).
  * Standard models get 180s default.
+ *
+ * NOTE: All Kimi K2 variants (incl. 'moonshotai/kimi-k2.6') run the Agent Swarm
+ * and need the extended timeout — but their model IDs don't contain 'thinking',
+ * so we match 'kimi' explicitly. Same applies to DeepSeek V4 and Zhipu GLM, whose
+ * reasoning passes are slow but whose IDs lack the 'thinking'/'reasoning' marker.
+ * This keeps primary and fallback consistent and lets these tools inherit 600s
+ * instead of the 180s default. Single source of truth — no per-call timeouts.
  */
 export function getOpenRouterModelTimeout(modelId) {
     const config = getTimeoutConfig();
-    if (modelId.includes('thinking') || modelId.includes('reasoning')) {
+    const id = modelId.toLowerCase();
+    if (id.includes('thinking') || id.includes('reasoning') ||
+        id.includes('kimi') || id.includes('deepseek') || id.includes('glm') ||
+        id.includes('stepfun') || id.includes('ernie')) {
         return config.openrouterThinking;
     }
     return config.openrouter;

package/dist/src/config.js

@@ -128,7 +128,7 @@ export function getAvailableModels(config) {
         models.push('sonar-pro', 'sonar-reasoning-pro', 'sonar-deep-research');
     }
     if (config.apiKeys.grok) {
-        models.push('grok-3', 'grok-4.20-0309-reasoning', 'grok-4.20-multi-agent-0309');
+        models.push('grok-4.3', 'grok-4.3-latest', 'grok-build-0.1');
     }
     if (config.apiKeys.openrouter) {
         models.push('qwen3-coder', 'qwq-32b', 'qwen3-32b');

package/dist/src/mcp-client.js

@@ -13,8 +13,8 @@ export class MCPClient {
             'mcp__openai-mcp__openai_reason',
             'mcp__openai-mcp__openai_brainstorm',
             'mcp__think-mcp-server__think',
-            'mcp__devlog-search__search_devlogs',
-            'mcp__devlog-core__devlog_session_log'
+            'mcp__dokoro__dokoro_session_recall',
+            'mcp__dokoro__dokoro_session_summary_add'
         ]);
     }
     hasTools(tools) {

package/dist/src/memory/index.js

@@ -9,7 +9,7 @@ export * from './memory-manager.js';
 // Provider exports
 export * from './providers/local-provider.js';
 export * from './providers/mem0-provider.js';
-// export * from './providers/devlog-provider.js';
+// export * from './providers/dokoro-provider.js';
 // export * from './providers/hybrid-provider.js';
 // Main API
 export { getMemoryManager, resetMemoryManager, HierarchicalMemoryManager } from './memory-manager.js';

package/dist/src/memory/memory-config.js

@@ -1,6 +1,6 @@
 /**
  * Memory Configuration System
- * Flexible memory backend configuration with support for mem0, DevLog, local, and hybrid modes
+ * Flexible memory backend configuration with support for mem0, Dokoro, local, and hybrid modes
  */
 /**
  * Default configuration
@@ -51,13 +51,13 @@ export function loadMemoryConfigFromEnv() {
             enableGraphMemory: process.env.MEM0_ENABLE_GRAPH !== 'false'
         };
     }
-    // DevLog configuration
-    if (process.env.DEVLOG_CONNECTION) {
-        config.devlog = {
-            connectionString: process.env.DEVLOG_CONNECTION,
-            workspace: process.env.DEVLOG_WORKSPACE,
-            projectId: process.env.DEVLOG_PROJECT,
-            enableSync: process.env.DEVLOG_SYNC !== 'false'
+    // Dokoro configuration
+    if (process.env.DOKORO_CONNECTION) {
+        config.dokoro = {
+            connectionString: process.env.DOKORO_CONNECTION,
+            workspace: process.env.DOKORO_WORKSPACE,
+            projectId: process.env.DOKORO_PROJECT,
+            enableSync: process.env.DOKORO_SYNC !== 'false'
         };
     }
     // Local storage configuration
@@ -109,8 +109,8 @@ export function validateMemoryConfig(config) {
     if (config.provider === 'mem0' && !config.mem0?.apiKey && !process.env.MEM0_API_KEY) {
         errors.push('Mem0 provider requires API key (MEM0_API_KEY or config.mem0.apiKey)');
     }
-    if (config.provider === 'devlog' && !config.devlog?.connectionString && !process.env.DEVLOG_CONNECTION) {
-        errors.push('DevLog provider requires connection string');
+    if (config.provider === 'dokoro' && !config.dokoro?.connectionString && !process.env.DOKORO_CONNECTION) {
+        errors.push('Dokoro provider requires connection string');
     }
     if (config.provider === 'local' && !config.local?.path) {
         errors.push('Local provider requires storage path');

package/dist/src/memory/memory-interface.js

@@ -1,6 +1,6 @@
 /**
  * Memory Provider Interface
- * Common interface for all memory providers (mem0, DevLog, local, etc.)
+ * Common interface for all memory providers (mem0, Dokoro, local, etc.)
  */
 /**
  * Abstract base class for memory providers with common functionality

package/dist/src/memory/memory-manager.js

@@ -6,7 +6,7 @@ import { mergeMemoryConfig, validateMemoryConfig } from './memory-config.js';
 import { LocalProvider } from './providers/local-provider.js';
 import { Mem0Provider } from './providers/mem0-provider.js';
 import { randomBytes } from 'crypto';
-// import { DevLogProvider } from './providers/devlog-provider.js';
+// import { DokoroProvider } from './providers/dokoro-provider.js';
 // import { HybridProvider } from './providers/hybrid-provider.js';
 /**
  * Main memory manager that coordinates all providers
@@ -244,9 +244,9 @@ export class HierarchicalMemoryManager {
                     console.error('Failed to create Mem0 provider:', error);
                     return null;
                 }
-            case 'devlog':
-                // TODO: Implement DevLog provider
-                console.warn('DevLog provider not yet implemented');
+            case 'dokoro':
+                // TODO: Implement Dokoro provider
+                console.warn('Dokoro provider not yet implemented');
                 return null;
             case 'local':
                 return await this.createLocalProvider();