@kodax-ai/kodax 0.7.56 → 0.7.58

package/README.md

@@ -154,7 +154,7 @@ For CLI defaults, create `~/.kodax/config.json`:
 ```json
 {
   "provider": "zhipu-coding",
-  "reasoningMode": "auto"
+  "effort": "auto"
 }
 ```
 
@@ -170,13 +170,18 @@ If you need a custom base URL or an OpenAI/Anthropic-compatible endpoint, define
       "baseUrl": "https://example.com/v1",
       "apiKeyEnv": "MY_LLM_API_KEY",
       "model": "my-model",
-      "userAgentMode": "compat"
+      "userAgentMode": "compat",
+      "reasoning": {
+        "efforts": ["off", "low", "medium", "high", "max"],
+        "default": "high"
+      }
     }
   ]
 }
 ```
 
 `userAgentMode` defaults to `"compat"`, which sends `KodaX` instead of the official SDK User-Agent. Switch it to `"sdk"` only when your gateway expects the upstream SDK header.
+For custom reasoning models, `reasoning: { efforts, default }` is the preferred v0.7.57 shape; use `"reasoning": "none"` for models without thinking capability. SDK hosts should render effort pickers from `reasoningProfile.supportedEfforts` / `defaultEffort` rather than assuming a fixed five-option ladder.
 
 #### OpenAI-compatible reasoning providers
 
@@ -191,8 +196,7 @@ Some OpenAI-compatible reasoning models require KodaX to replay the previous ass
       "baseUrl": "https://example.com/v1",
       "apiKeyEnv": "MY_DEEPSEEK_API_KEY",
       "model": "deepseek-v4-flash",
-      "supportsThinking": true,
-      "reasoningCapability": "native-toggle",
+      "reasoningPreset": "deepseek-v4-openai",
       "replayReasoningContent": true
     }
   ]
@@ -281,7 +285,7 @@ registerCustomProviders([
 const result = await runKodaX(
   {
     provider: 'my-openai-compatible',
-    reasoningMode: 'auto',
+    effort: 'auto',
   },
   'Explain this codebase'
 );
@@ -292,27 +296,25 @@ const result = await runKodaX(
 > surface (`startKodaX` + `RunningSession`), MCP popout manager API (`McpManager`),
 > Skill `` !`cmd` `` host hook, and per-app data dir namespacing (`getAppDataDir`).
 
-## Repo Intelligence (optional premium engine)
+## Repo Intelligence
 
-KodaX ships with built-in OSS repo intelligence (`repo_overview`, `module_context`, `symbol_context`, `process_context`, `impact_estimate`, …) that helps the coding agent understand large codebases without ad-hoc grep/glob exploration.
+KodaX ships with built-in repo intelligence (`repo_overview`, `module_context`, `symbol_context`, `process_context`, `impact_estimate`, and related tools) that helps the coding agent understand large codebases without ad-hoc grep/glob exploration.
 
-An optional **premium engine** (`repointel` local daemon, distributed via the sibling `KodaX-private` repo) adds proactive context injection, deeper module capsules, and a native auto-lane integration. KodaX automatically falls back to OSS when premium is unavailable.
+Use `/repo-intel status` in the REPL to inspect the active engine. The former standalone `repointel` host skill has been removed; repo intelligence is built into KodaX and requires no external installation.
 
 ```bash
-# Pick a runtime mode (off | oss | premium-shared | premium-native | auto)
-kodax --repo-intelligence premium-native --repo-intelligence-trace
+# Pick a runtime mode (auto | full | light | off)
+kodax --repo-intelligence full --repo-intelligence-trace
 ```
 
-Setup, runtime modes, REPL controls, config schema, and external-host integrations: see [docs/REPOINTEL.md](docs/REPOINTEL.md).
-
 ## Architecture
 
-KodaX uses a **monorepo architecture** with npm workspaces. Source layout currently has 4 workspace packages; published as a single bundled npm package `@kodax-ai/kodax` with 7 SDK subpath exports (`/agent`, `/llm`, `/coding`, `/repl`, `/skills`, `/mcp`, `/session`; ADR-024 + ADR-032 + ADR-038, with ADR-036 consolidation):
+KodaX uses a **monorepo architecture** with npm workspaces. Source layout currently has 4 workspace packages; published as a single bundled npm package `@kodax-ai/kodax` with 8 SDK subpath exports (`/agent`, `/llm`, `/coding`, `/media`, `/repl`, `/skills`, `/mcp`, `/session`; ADR-024 + ADR-032 + ADR-038, with ADR-036 consolidation):
 
 ```
 KodaX/
 ├── packages/                # 4 workspace packages (FEATURE_194 v0.7.43)
-│   ├── llm/                 # @kodax-ai/llm - LLM abstraction (14 built-in provider aliases)
+│   ├── llm/                 # @kodax-ai/llm - LLM abstraction (15 built-in provider aliases)
 │   │   └── providers/       # Anthropic, OpenAI, DeepSeek, Kimi, MiMo, MiniMax, Zhipu, Ark, …
 │   │
 │   ├── agent/               # @kodax-ai/agent - Generic Agent framework
@@ -333,7 +335,7 @@ KodaX/
 │
 ├── src/                     # CLI entry + SDK subpath entries
 │   ├── kodax_cli.ts         # Main CLI entry point (bin: `kodax`)
-│   └── sdk-*.ts             # SDK subpath re-exports → @kodax-ai/kodax/{agent,llm,coding,repl,skills,mcp,session}
+│   └── sdk-*.ts             # SDK subpath re-exports → @kodax-ai/kodax/{agent,llm,coding,media,repl,skills,mcp,session}
 │
 └── package.json             # Root workspace config; release.mjs rewrites name + injects subpath exports
 ```
@@ -360,7 +362,7 @@ KodaX/
        ┌──────────────┐ ┌──────────────────────────┐ ┌──────────────┐
        │@kodax-ai/    │ │@kodax-ai/agent           │ │@kodax-ai/llm │
        │coding (via   │ │Runner + fan-out +        │ │LLM Abstract  │
-       │above)        │ │idle-yield + session-     │ │(14 aliases)  │
+       │above)        │ │idle-yield + session-     │ │(15 aliases)  │
        │              │ │lineage + skills + mcp +  │ │              │
        │              │ │tracing (FEATURE_194)     │ │              │
        └──────────────┘ └──────────────────────────┘ └──────────────┘
@@ -372,8 +374,8 @@ Source-side workspace package names (`@kodax-ai/*`). npm consumers install the s
 
 | Workspace package | Purpose | Key Dependencies |
 |---------|---------|------------------|
-| `@kodax-ai/llm` | LLM abstraction (14 built-in provider aliases + custom registration) | @anthropic-ai/sdk, openai |
-| `@kodax-ai/agent` | Generic Agent framework — Runner, fan-out, idle-yield, session-lineage, capabilities (mcp + skills), tracing (ADR-036 v0.7.43 consolidation; subpaths: `/session-lineage`, `/capabilities/mcp`, `/capabilities/skills`, `/tracing`) | @kodax-ai/llm, js-tiktoken, fflate, yaml |
+| `@kodax-ai/llm` | LLM abstraction (15 built-in provider aliases + custom registration) | @anthropic-ai/sdk, openai |
+| `@kodax-ai/agent` | Generic Agent framework — Runner, fan-out, idle-yield, media/input artifacts, session-lineage, capabilities (mcp + skills), tracing (ADR-036 v0.7.43 consolidation; subpaths: `/media`, `/session-lineage`, `/capabilities/mcp`, `/capabilities/skills`, `/tracing`) | @kodax-ai/llm, js-tiktoken, fflate, jimp, yaml |
 | `@kodax-ai/coding` | Coding Agent — 50+ tools (incl. `dispatch_child_task` / `send_message` / `task_stop`) + role prompts + auto-continue + repo-intelligence protocol | @kodax-ai/llm, @kodax-ai/agent |
 | `@kodax-ai/repl` | Complete interactive terminal UI (Ink/React, permission modes, commands, streaming) | @kodax-ai/coding, ink, react |
 
@@ -382,13 +384,13 @@ Source-side workspace package names (`@kodax-ai/*`). npm consumers install the s
 KodaX has two layers that consumers should understand separately:
 
 - **Source-side**: 4 workspace packages above (what developers see when reading the repo).
-- **npm-published**: a single bundled package `@kodax-ai/kodax` with 7 SDK subpaths (what SDK consumers `import` from). The subpaths are split into two roles:
+- **npm-published**: a single bundled package `@kodax-ai/kodax` with 8 SDK subpaths (what SDK consumers `import` from). The subpaths are split into two roles:
   - **Full-package subpaths** (`/agent`, `/llm`, `/coding`, `/repl`) — each one maps 1:1 to a source workspace and exposes its complete public API.
-  - **Narrow-subset subpaths** (`/skills`, `/mcp`, `/session`) — each one exposes only a focused capability slice carved out of `/agent` or `/repl`. This lets consumers who only need (say) the Skills system import a much smaller surface without pulling in the full agent framework.
+  - **Narrow-subset subpaths** (`/media`, `/skills`, `/mcp`, `/session`) — each one exposes only a focused capability slice carved out of `/agent` or `/repl`. This lets consumers who only need (say) the Skills system import a much smaller surface without pulling in the full agent framework.
 
 | Source package | npm subpath | Type | What you get | Example consumer |
 |---|---|---|---|---|
-| `packages/llm`    | `@kodax-ai/kodax/llm`     | Full package | 14-alias LLM abstraction (77 exports) | Standalone LLM clients |
+| `packages/llm`    | `@kodax-ai/kodax/llm`     | Full package | 15-alias LLM abstraction (77 exports) | Standalone LLM clients |
 | `packages/agent`  | `@kodax-ai/kodax/agent`   | Full package | Runner / fan-out / session-lineage / capabilities / tracing (202 exports) | Custom agent frameworks |
 | `packages/agent`  | `@kodax-ai/kodax/skills`  | **Narrow subset** | Skills system only — `SkillRegistry` / `loadFullSkill` / `expandSkillForLLM` / ... (26 exports = pre-v0.7.43 `@kodax-ai/skills` complete API) | Skill loaders, IDE plugins |
 | `packages/agent`  | `@kodax-ai/kodax/mcp`     | **Narrow subset** | MCP only — `McpCapabilityProvider` / `createMcpTransport` / `searchMcpCatalog` / ... (11 exports = pre-v0.7.43 `@kodax-ai/mcp` complete API) | MCP server hosts |
@@ -409,14 +411,14 @@ KodaX has two layers that consumers should understand separately:
 ## Features
 
 - **Modular Architecture** - Use as CLI, as a library, or as a Node-free single binary
-- **14 Built-in Provider Aliases** - Anthropic, OpenAI, DeepSeek, Kimi, Kimi Code, Qwen, Zhipu, Zhipu Coding, MiniMax Coding, MiMo Coding, MiMo, Ark Coding, Gemini CLI, Codex CLI - plus user-defined OpenAI/Anthropic-compatible providers
+- **15 Built-in Provider Aliases** - Anthropic, OpenAI, DeepSeek, Kimi, Kimi Code, Qwen, Zhipu, Zhipu Coding, Zai Coding, MiniMax Coding, MiMo Coding, MiMo, Ark Coding, Gemini CLI, Codex CLI - plus user-defined OpenAI/Anthropic-compatible providers
 - **Dynamic Workflows + SDK Process Surface** - Generate/reuse capability-routed workflows, observe live progress through `WorkflowProcessSnapshot`, and control workflow lifecycle from SDK hosts without parsing REPL output
 - **V2 Worker single-loop + Sidecar Verifier (default)** - Single-agent main loop with an out-of-band Sidecar Verifier as Stop-hook (claudecode-shape; FEATURE_184 v0.7.42, ADR-030). Verifier returns accept/revise/blocked verdict on Worker text-only termination. The pre-v0.7.43 V1 chain is retired, `emit_handoff` is deleted, accept-verdict UI silently passes through, and content-aware gating skips trivial-chat sidecar calls. Async child steering uses `dispatch_child_task` + `send_message` + `task_stop` with idle-yield wait; specialist routing uses `subagent_type`.
-- **Reasoning Modes** - Unified `off/auto/quick/balanced/deep` interface across providers
+- **Reasoning Effort** - Effort-first control (`off/auto/low/medium/high` plus model-supported extras) across providers
 - **Streaming Output** - Real-time response display
 - **Session Management** - JSONL format with branchable session lineage tree
 - **Skills System** - Natural language triggering, extensible, role-projected in AMA
-- **Repo Intelligence** - OSS baseline + optional `repointel` premium engine, with native KodaX auto-injection lane
+- **Repo Intelligence** - Built-in full/light repository intelligence with native KodaX auto-injection lane
 - **Rich Tool Surface** - 50+ built-in tools across file ops, shell, search, repo intelligence, MCP capabilities, git worktree, and agent control
 - **Permission Control** - 3 permission modes with pattern-based control
 - **Standalone Binary** - `bun --compile` releases for Win/macOS/Linux x64+arm64, no Node.js required on target machines
@@ -491,7 +493,7 @@ process.env.ZHIPU_API_KEY = process.env.ZHIPU_API_KEY ?? 'your_api_key';
 
 const result = await runKodaX({
   provider: 'zhipu-coding',
-  reasoningMode: 'auto',
+  effort: 'auto',
   events: {
     onTextDelta: (text) => process.stdout.write(text),
     onComplete: () => console.log('\nDone!'),
@@ -507,7 +509,7 @@ For smaller surface and tree-shake-friendly imports, the SDK is also exposed via
 
 ```typescript
 import { Runner } from '@kodax-ai/kodax/agent';                // agent runtime
-import { getProvider } from '@kodax-ai/kodax/llm';              // LLM abstraction (14 aliases)
+import { getProvider } from '@kodax-ai/kodax/llm';              // LLM abstraction (15 aliases)
 import { runKodaX } from '@kodax-ai/kodax/coding';              // coding tools + prompts
 import { SkillRegistry } from '@kodax-ai/kodax/skills';         // zero-dep skill loader
 import { loadConfig } from '@kodax-ai/kodax/repl';              // REPL config / session helpers
@@ -515,7 +517,7 @@ import { createMcpManager } from '@kodax-ai/kodax/mcp';         // MCP popout ma
 import { listSessions } from '@kodax-ai/kodax/session';         // session history helpers
 ```
 
-All 8 SDK entries (root + 7 subpaths) share internal code via ESM chunk splitting — importing from `/agent` does not pull in `/repl`'s Ink + React surface.
+All 9 SDK entries (root + 8 subpaths) share internal code via ESM chunk splitting — importing from `/agent` does not pull in `/repl`'s Ink + React surface.
 
 > **ESM-only.** The SDK is published as ES Modules. In a CommonJS context (Electron main process, legacy Webpack CJS bundles, `require()`-based code) you must use `await import(...)` instead of `require()`. See [docs/SDK_EMBEDDER_GUIDE.md §5](docs/SDK_EMBEDDER_GUIDE.md#5-consuming-from-a-commonjs-context-electron-main-cjs-bundles) for the canonical recipe + the technical reason most subpaths cannot ship a dual ESM/CJS build.
 
@@ -554,8 +556,8 @@ kodax "Help me create a TypeScript project"
 # Choose a provider explicitly
 kodax --provider openai --model gpt-5.4 "Create a REST API"
 
-# Use a deeper reasoning mode
-kodax --reasoning deep "Review this architecture"
+# Use higher reasoning effort
+kodax --effort high "Review this architecture"
 ```
 
 ### Session Workflows
@@ -664,7 +666,7 @@ kodax -h init          # Long-running project initialization
 kodax -h project       # Project mode / harness workflow
 kodax -h auto          # Auto-continue mode
 kodax -h provider      # LLM provider configuration
-kodax -h thinking      # Thinking/reasoning mode
+kodax -h thinking      # Thinking/reasoning effort and compatibility modes
 kodax -h team          # Multi-agent parallel execution
 kodax -h print         # Print configuration
 ```
@@ -735,7 +737,7 @@ const events: KodaXEvents = {
 
 const result = await runKodaX({
   provider: 'zhipu-coding',
-  reasoningMode: 'auto',
+  effort: 'auto',
   events,
 }, 'What is 1+1?');
 
@@ -749,7 +751,7 @@ import { KodaXClient } from '@kodax-ai/kodax';
 
 const client = new KodaXClient({
   provider: 'zhipu-coding',
-  reasoningMode: 'auto',
+  effort: 'auto',
   events: {
     onTextDelta: (t) => process.stdout.write(t),
   },
@@ -802,7 +804,7 @@ await runKodaX({
 
 ## SDK Usage
 
-KodaX ships as a single npm package `@kodax-ai/kodax` with 7 SDK subpath exports (ADR-024 v0.7.39 + ADR-032 v0.7.42 + ADR-038 v0.7.49). Each subpath is tree-shake-friendly so consumers pull only what they need:
+KodaX ships as a single npm package `@kodax-ai/kodax` with 8 SDK subpath exports (ADR-024 v0.7.39 + ADR-032 v0.7.42 + ADR-038 v0.7.49 + v0.7.56 `/media`). Each subpath is tree-shake-friendly so consumers pull only what they need:
 
 ```bash
 npm install @kodax-ai/kodax
@@ -811,8 +813,9 @@ npm install @kodax-ai/kodax
 ```typescript
 import { runKodaX } from '@kodax-ai/kodax';                       // root: CLI helpers + runKodaX
 import { Runner, runFanOut } from '@kodax-ai/kodax/agent';        // generic Agent framework
-import { getProvider } from '@kodax-ai/kodax/llm';                // 14-alias LLM abstraction
+import { getProvider } from '@kodax-ai/kodax/llm';                // 15-alias LLM abstraction
 import { KODAX_TOOLS } from '@kodax-ai/kodax/coding';             // tools + prompts + agent loop
+import { createImageArtifactFromPath } from '@kodax-ai/kodax/media'; // input artifact helpers
 import { runInkInteractiveMode } from '@kodax-ai/kodax/repl';     // Ink TUI entrypoint
 import { SkillRegistry } from '@kodax-ai/kodax/skills';           // zero-dep skill loader
 import { createMcpManager } from '@kodax-ai/kodax/mcp';           // MCP popout manager (v0.7.42)
@@ -823,7 +826,7 @@ import { listSessions } from '@kodax-ai/kodax/session';           // session his
 
 ### `@kodax-ai/kodax/llm` — LLM Abstraction
 
-14 built-in provider aliases (Anthropic, OpenAI, DeepSeek, Kimi, Kimi-Code, Qwen, Zhipu, Zhipu-Coding, MiniMax-Coding, MiMo, MiMo-Coding, Ark-Coding, Gemini-CLI, Codex-CLI) + custom provider registration.
+15 built-in provider aliases (Anthropic, OpenAI, DeepSeek, Kimi, Kimi-Code, Qwen, Zhipu, Zhipu-Coding, Zai-Coding, MiniMax-Coding, MiMo, MiMo-Coding, Ark-Coding, Gemini-CLI, Codex-CLI) + custom provider registration.
 
 ```typescript
 import { getProvider, KodaXBaseProvider } from '@kodax-ai/kodax/llm';
@@ -840,7 +843,7 @@ for await (const result of stream) {
 }
 ```
 
-**Key Features**: unified provider interface · streaming · reasoning modes (`off/auto/quick/balanced/deep`) · per-provider retry + error handling · zero business-logic dependencies.
+**Key Features**: unified provider interface · streaming · reasoning effort (`off/auto/low/medium/high` plus model-supported extras) · per-provider retry + error handling · zero business-logic dependencies.
 
 ### `@kodax-ai/kodax/agent` — Agent Framework (standalone-consumable)
 
@@ -909,14 +912,14 @@ import { runKodaX, KodaXClient, KODAX_TOOLS } from '@kodax-ai/kodax/coding';
 // Single-task helper
 const result = await runKodaX({
   provider: 'zhipu-coding',
-  reasoningMode: 'auto',
+  effort: 'auto',
   events: { onTextDelta: (text) => process.stdout.write(text) },
 }, 'Read package.json and explain the dependencies');
 
 // Continuous session
 const client = new KodaXClient({
   provider: 'anthropic',
-  reasoningMode: 'auto',
+  effort: 'auto',
   events: { /* … */ },
 });
 await client.send('Create a new file');
@@ -938,7 +941,7 @@ import { runInkInteractiveMode } from '@kodax-ai/kodax/repl';
 // - Command system (/help, /mode, /clear, /status, …)
 // - Skills integration
 // - Theme support
-await runInkInteractiveMode({ provider: 'zhipu-coding', reasoningMode: 'auto' });
+await runInkInteractiveMode({ provider: 'zhipu-coding', effort: 'auto' });
 ```
 
 **Key Features**: Ink-based React components · 3 permission modes (auto / plan / accept-edits) · built-in commands · real-time streaming display · context-usage indicator.
@@ -961,7 +964,7 @@ await runInkInteractiveMode({ provider: 'zhipu-coding', reasoningMode: 'auto' })
 
 | Use Case | Subpath | Why |
 |----------|---------|-----|
-| Only need LLM abstraction | `@kodax-ai/kodax/llm` | Minimal deps; 14 built-in aliases |
+| Only need LLM abstraction | `@kodax-ai/kodax/llm` | Minimal deps; 15 built-in aliases |
 | Building custom agent | `@kodax-ai/kodax/agent` | Runner + fan-out + idle-yield + session-lineage + capabilities |
 | Coding tasks | `@kodax-ai/kodax/coding` | Complete coding agent + tools |
 | Terminal app | `@kodax-ai/kodax/repl` | Full interactive experience |
@@ -977,6 +980,7 @@ await runInkInteractiveMode({ provider: 'zhipu-coding', reasoningMode: 'auto' })
 | qwen | `QWEN_API_KEY` | Native | qwen3.5-plus |
 | zhipu | `ZHIPU_API_KEY` | Native | glm-5 (`glm-5.2` 1M ctx / `glm-5.1` / `glm-5-turbo` via `/model`) |
 | zhipu-coding | `ZHIPU_CODING_API_KEY` | Native | glm-5 (`glm-5.2` 1M ctx / `glm-5.1` / `glm-5-turbo` via `/model`) |
+| zai-coding | `ZAI_CODING_API_KEY` | Native | glm-5.2 (Zhipu Coding Plan overseas mirror via `api.z.ai`, Anthropic-compat — same model lineup as `zhipu-coding`, served from outside CN) |
 | minimax-coding | `MINIMAX_CODING_API_KEY` | Native | MiniMax-M2.7 (`MiniMax-M3` Frontier Coding, native multimodal + 1M ctx, plus `MiniMax-M2.7-highspeed` via `/model`) |
 | mimo | `MIMO_API_KEY` | Native | mimo-v2.5-pro (Xiaomi MiMo pay-per-token, Anthropic-compat) |
 | mimo-coding | `MIMO_CODING_API_KEY` | Native | mimo-v2.5-pro (Xiaomi Token Plan, Anthropic-compat) |
@@ -1168,20 +1172,20 @@ npm run clean
 
 ### Repo Intelligence cache directories
 
-KodaX now uses two repo-intelligence cache locations on disk:
+KodaX uses one repo-intelligence cache root with separate built-in engine profiles:
 
 - `.agent/repo-intelligence/`
-  - OSS baseline repo-intelligence artifacts and existing task-engine snapshots.
-- `.repointel/`
-  - Premium `repointel` workspace cache shared by the local daemon/native frontdoor.
+  - Full-engine repo-intelligence artifacts and existing task-engine snapshots.
+- `.agent/repo-intelligence/light/`
+  - Light-mode heuristic index artifacts.
 
 They are intentionally separated so:
 
-- OSS fallback stays available even when premium is disabled or unavailable.
-- Premium cache does not pollute OSS artifacts.
-- KodaX and other hosts can share the same premium workspace cache.
+- full and light profiles can be rebuilt independently.
+- light-mode confidence/capability state cannot be mistaken for full-engine state.
+- future cache migrations can delete one profile without corrupting the other.
 
-`.repointel/` is a local generated directory and should not be committed.
+`.agent/repo-intelligence/` is local generated state and should not be committed.
 
 ---
 

package/README_CN.md

@@ -160,7 +160,7 @@ $env:ZHIPU_API_KEY="your_api_key"
 ```json
 {
   "provider": "zhipu-coding",
-  "reasoningMode": "auto"
+  "effort": "auto"
 }
 ```
 
@@ -194,7 +194,7 @@ import { runKodaX } from '@kodax-ai/kodax';
 const result = await runKodaX(
   {
     provider: 'zhipu-coding',
-    reasoningMode: 'auto',
+    effort: 'auto',
   },
   'Explain this codebase'
 );
@@ -206,15 +206,16 @@ const result = await runKodaX(
 
 ```typescript
 import { Runner } from '@kodax-ai/kodax/agent';                // Agent runtime
-import { getProvider } from '@kodax-ai/kodax/llm';              // LLM 抽象（14 个内置 alias）
+import { getProvider } from '@kodax-ai/kodax/llm';              // LLM 抽象（15 个内置 alias）
 import { runKodaX } from '@kodax-ai/kodax/coding';              // Coding tools + prompts
+import { createImageArtifactFromPath } from '@kodax-ai/kodax/media'; // 输入 artifact helpers
 import { SkillRegistry } from '@kodax-ai/kodax/skills';         // 零依赖 skill loader
 import { loadConfig } from '@kodax-ai/kodax/repl';              // REPL 配置 / session 工具
 import { createMcpManager } from '@kodax-ai/kodax/mcp';         // MCP popout manager（v0.7.42 起）
 import { listSessions } from '@kodax-ai/kodax/session';         // session 历史工具
 ```
 
-8 个 SDK 入口（root + 7 subpath）通过 ESM 共享 chunk 复用底层代码 —— 只 import `/agent` 不会把 `/repl` 的 Ink + React 一起拉进来。
+9 个 SDK 入口（root + 8 subpath）通过 ESM 共享 chunk 复用底层代码 —— 只 import `/agent` 不会把 `/repl` 的 Ink + React 一起拉进来。
 
 > **SDK 是 ESM-only**。在 CommonJS 上下文（Electron main 进程、传统 Webpack CJS bundle、`require()` 调用方）必须用 `await import('@kodax-ai/kodax/...')` 代替 `require()`。详见 [docs/SDK_EMBEDDER_GUIDE.md §5](docs/SDK_EMBEDDER_GUIDE.md#5-consuming-from-a-commonjs-context-electron-main-cjs-bundles)，含 Electron main 完整 recipe + 为什么大多数 subpath 物理上无法做 dual ESM/CJS bundle。
 
@@ -232,7 +233,11 @@ import { listSessions } from '@kodax-ai/kodax/session';         // session 历
       "baseUrl": "https://example.com/v1",
       "apiKeyEnv": "MY_LLM_API_KEY",
       "model": "my-model",
-      "userAgentMode": "compat"
+      "userAgentMode": "compat",
+      "reasoning": {
+        "efforts": ["off", "low", "medium", "high", "max"],
+        "default": "high"
+      }
     }
   ]
 }
@@ -240,6 +245,8 @@ import { listSessions } from '@kodax-ai/kodax/session';         // session 历
 
 `userAgentMode` 默认 `"compat"`（发送 `KodaX` 而非上游 SDK 的 User-Agent）；如果你的网关要求原生 SDK header，再切到 `"sdk"`。
 
+自定义 reasoning 模型优先使用 v0.7.57 的 `reasoning: { efforts, default }`；无 thinking 能力的模型使用 `"reasoning": "none"`。SDK 宿主的 effort 选择器应从 `reasoningProfile.supportedEfforts` / `defaultEffort` 动态生成，不要假定固定五档。
+
 #### OpenAI 兼容推理模型
 
 部分 OpenAI-compatible 推理模型要求多轮请求时回放上一轮 assistant 的 `reasoning_content`。DeepSeek V4 thinking mode 是已知必须开启的场景；内置 DeepSeek provider 已经默认开启，但自定义 provider 需要显式配置：
@@ -253,8 +260,7 @@ import { listSessions } from '@kodax-ai/kodax/session';         // session 历
       "baseUrl": "https://example.com/v1",
       "apiKeyEnv": "MY_DEEPSEEK_API_KEY",
       "model": "deepseek-v4-flash",
-      "supportsThinking": true,
-      "reasoningCapability": "native-toggle",
+      "reasoningPreset": "deepseek-v4-openai",
       "replayReasoningContent": true
     }
   ]
@@ -380,6 +386,7 @@ dist/binary/linux-x64/
 | qwen | `QWEN_API_KEY` | Native | qwen3.5-plus |
 | zhipu | `ZHIPU_API_KEY` | Native | glm-5（可 `/model` 切换 `glm-5.2` 1M ctx / `glm-5.1` / `glm-5-turbo`） |
 | zhipu-coding | `ZHIPU_CODING_API_KEY` | Native | glm-5（GLM Coding Plan；可 `/model` 切换 `glm-5.2` 1M ctx / `glm-5.1` / `glm-5-turbo`） |
+| zai-coding | `ZAI_CODING_API_KEY` | Native | glm-5.2（GLM Coding Plan 海外站，通过 `api.z.ai` 接入，Anthropic 协议 — 模型清单和 `zhipu-coding` 完全一致） |
 | minimax-coding | `MINIMAX_CODING_API_KEY` | Native | MiniMax-M2.7（可 `/model` 切换 `MiniMax-M3` Frontier Coding，原生多模态 + 1M ctx；以及 `MiniMax-M2.7-highspeed`） |
 | mimo | `MIMO_API_KEY` | Native | mimo-v2.5-pro（小米 MiMo 按量计费，Anthropic 协议） |
 | mimo-coding | `MIMO_CODING_API_KEY` | Native | mimo-v2.5-pro（小米 MiMo Token Plan，Anthropic 协议） |
@@ -452,44 +459,42 @@ KodaX 有 50+ 个内置工具，按类别分组如下（实际暴露给 LLM 是
 | `exit_plan_mode` | Plan 模式下提交最终方案给用户审批（仅 REPL） |
 | `emit_managed_protocol` | managed-task 协议侧信道（verdict role payload）。v0.7.42 FEATURE_184 起默认走 V2 Worker 单循环 + Sidecar Verifier；v0.7.43 FEATURE_193 退役 V1 chain。 |
 
-## Repo Intelligence（可选 premium 引擎）
+## Repo Intelligence（内置 full/light 引擎）
 
-KodaX 内置 OSS repo intelligence（`repo_overview` / `module_context` / `symbol_context` / `process_context` / `impact_estimate` 等），让 coding agent 不靠零散 grep/glob 就能理解大型仓库。
+KodaX 内置 repo intelligence（`repo_overview` / `module_context` / `symbol_context` / `process_context` / `impact_estimate` 等），让 coding agent 不靠零散 grep/glob 就能理解大型仓库。
 
-可选的 **premium 引擎**（`repointel` 本地 daemon，通过 sibling `KodaX-private` 仓发布）增加主动上下文注入、更深的 module capsule，以及一条 KodaX 原生 auto-lane。premium 不可用时 KodaX 自动 fallback 到 OSS。
+REPL 中使用 `/repo-intel status` 查看当前引擎状态。旧的独立 `repointel` host skill 已移除；repo intelligence 已内置于 KodaX，无需任何外部安装。
 
 ```bash
-# 选一个运行模式（off | oss | premium-shared | premium-native | auto）
-kodax --repo-intelligence premium-native --repo-intelligence-trace
+# 选一个运行模式（auto | full | light | off）
+kodax --repo-intelligence full --repo-intelligence-trace
 ```
 
-完整安装 / 运行模式 / REPL 控制 / config schema / 第三方宿主接入，详见 [docs/REPOINTEL.md](docs/REPOINTEL.md)。
-
 ## 仓库结构
 
-KodaX 是基于 npm workspaces 的 TypeScript monorepo，**源码层 4 个 workspace 包**（FEATURE_194 v0.7.43 包合并 — 9 → 4，ADR-036），npm 上以单 bundle 包 `@kodax-ai/kodax` 发布 + 7 个 SDK subpath exports（`/agent`、`/llm`、`/coding`、`/repl`、`/skills`、`/mcp`、`/session`；ADR-024 + ADR-032 + ADR-038）。核心包：
+KodaX 是基于 npm workspaces 的 TypeScript monorepo，**源码层 4 个 workspace 包**（FEATURE_194 v0.7.43 包合并 — 9 → 4，ADR-036），npm 上以单 bundle 包 `@kodax-ai/kodax` 发布 + 8 个 SDK subpath exports（`/agent`、`/llm`、`/coding`、`/media`、`/repl`、`/skills`、`/mcp`、`/session`；ADR-024 + ADR-032 + ADR-038）。核心包：
 
 | Workspace 包 | 作用 | 主要依赖 |
 |----|------|---------|
-| `@kodax-ai/llm` | LLM 抽象层（14 个内置 provider alias + 自定义 provider 注册），可独立使用 | `@anthropic-ai/sdk`, `openai` |
-| `@kodax-ai/agent` | 通用 Agent 框架 —— Runner / runFanOut / runWithIdleYield / ChildTaskRegistry + 会话管理 + tokenization + 可插拔 compaction + **inline 后**:session-lineage 子树 + capabilities (mcp + skills + builtin) + tracing（subpaths: `/session-lineage`、`/capabilities/mcp`、`/capabilities/skills`、`/tracing`） | `@kodax-ai/llm`, `js-tiktoken`, `fflate`, `yaml` |
+| `@kodax-ai/llm` | LLM 抽象层（15 个内置 provider alias + 自定义 provider 注册），可独立使用 | `@anthropic-ai/sdk`, `openai` |
+| `@kodax-ai/agent` | 通用 Agent 框架 —— Runner / runFanOut / runWithIdleYield / ChildTaskRegistry + media/input artifacts + 会话管理 + tokenization + 可插拔 compaction + **inline 后**:session-lineage 子树 + capabilities (mcp + skills + builtin) + tracing（subpaths: `/media`、`/session-lineage`、`/capabilities/mcp`、`/capabilities/skills`、`/tracing`） | `@kodax-ai/llm`, `js-tiktoken`, `fflate`, `jimp`, `yaml` |
 | `@kodax-ai/coding` | Coding Agent:50+ 工具(含 `dispatch_child_task`/`send_message`/`task_stop`)、role prompts、agent loop、auto-continue + repo-intelligence protocol(v0.7.43 inline) | `@kodax-ai/llm`, `@kodax-ai/agent` |
 | `@kodax-ai/repl` | 完整交互式终端 UI（Ink / React、权限模式、命令系统、流式渲染） | `@kodax-ai/coding`, `ink`, `react` |
 
-根目录 `src/kodax_cli.ts` 是 CLI 入口；`src/sdk-{agent,llm,coding,repl,skills,mcp,session}.ts` 是 SDK subpath 入口；构建产物在 `dist/`，单文件二进制在 `dist/binary/<target>/`。
+根目录 `src/kodax_cli.ts` 是 CLI 入口；`src/sdk-{agent,llm,coding,media,repl,skills,mcp,session}.ts` 是 SDK subpath 入口；构建产物在 `dist/`，单文件二进制在 `dist/binary/<target>/`。
 
 ### 源码层 vs npm 发布层
 
 KodaX 有两层结构，SDK 用户需要分开理解：
 
 - **源码层**：上面 4 个 workspace 包（开发者读代码时看到的物理结构）。
-- **npm 发布层**：单个 bundled 包 `@kodax-ai/kodax`，对外暴露 7 个 SDK subpath（SDK 消费者 `import` 时看到的接口）。subpath 分两种角色：
+- **npm 发布层**：单个 bundled 包 `@kodax-ai/kodax`，对外暴露 8 个 SDK subpath（SDK 消费者 `import` 时看到的接口）。subpath 分两种角色：
   - **完整包 subpath**（`/agent`、`/llm`、`/coding`、`/repl`）—— 每个 1:1 对应一个源码包，暴露完整公开 API。
-  - **窄子集 subpath**（`/skills`、`/mcp`、`/session`）—— 从 `/agent` 或 `/repl` 切出聚焦的能力子集，让"只用 Skills/MCP/会话管理"的消费者引入更小的依赖。
+  - **窄子集 subpath**（`/media`、`/skills`、`/mcp`、`/session`）—— 从 `/agent` 或 `/repl` 切出聚焦的能力子集，让"只用 Skills/MCP/会话管理"的消费者引入更小的依赖。
 
 | 源码包 | npm subpath | 类型 | 内容 | 典型消费者 |
 |---|---|---|---|---|
-| `packages/llm`    | `@kodax-ai/kodax/llm`     | 完整包 | 14-alias LLM 抽象 (77 exports) | 独立 LLM 客户端 |
+| `packages/llm`    | `@kodax-ai/kodax/llm`     | 完整包 | 15-alias LLM 抽象 (77 exports) | 独立 LLM 客户端 |
 | `packages/agent`  | `@kodax-ai/kodax/agent`   | 完整包 | Runner / fan-out / session-lineage / capabilities / tracing (202 exports) | 自定义 agent 框架 |
 | `packages/agent`  | `@kodax-ai/kodax/skills`  | **窄子集** | 仅 Skills 系统 —— `SkillRegistry` / `loadFullSkill` / `expandSkillForLLM` 等 (26 exports = v0.7.43 之前 `@kodax-ai/skills` 完整 API) | Skill 加载器、IDE 插件 |
 | `packages/agent`  | `@kodax-ai/kodax/mcp`     | **窄子集** | 仅 MCP —— `McpCapabilityProvider` / `createMcpTransport` / `searchMcpCatalog` 等 (11 exports = v0.7.43 之前 `@kodax-ai/mcp` 完整 API) | MCP server 宿主 |
@@ -506,7 +511,7 @@ KodaX 有两层结构，SDK 用户需要分开理解：
 ```
 KodaX/                       # 4 workspace packages(FEATURE_194 v0.7.43)
 ├── packages/
-│   ├── llm/                 # @kodax-ai/llm —— 14 个内置 provider alias
+│   ├── llm/                 # @kodax-ai/llm —— 15 个内置 provider alias
 │   ├── agent/               # @kodax-ai/agent —— Runner / fan-out / idle-yield + 子树:
 │   │   ├── session-lineage/ # 分支 session tree (v0.7.43 inline)
 │   │   ├── capabilities/
@@ -518,9 +523,9 @@ KodaX/                       # 4 workspace packages(FEATURE_194 v0.7.43)
 │   └── repl/                # @kodax-ai/repl —— Ink TUI
 ├── src/
 │   ├── kodax_cli.ts         # CLI 主入口（bin: `kodax`）
-│   └── sdk-*.ts             # SDK subpath 入口 → @kodax-ai/kodax/{agent,llm,coding,repl,skills,mcp,session}
+│   └── sdk-*.ts             # SDK subpath 入口 → @kodax-ai/kodax/{agent,llm,coding,media,repl,skills,mcp,session}
 ├── scripts/
-│   ├── build-bundle.mjs     # esbuild 单 bundle 多 entry 打包（CLI + root + 7 SDK subpath + chunks）
+│   ├── build-bundle.mjs     # esbuild 单 bundle 多 entry 打包（CLI + root + 8 SDK subpath + chunks）
 │   ├── build-binary.mjs     # Bun --compile 单文件二进制打包
 │   └── release.mjs          # ADR-024 release-time pkg name/exports 注入
 └── .github/workflows/
@@ -594,20 +599,20 @@ npm run clean
 
 ### Repo Intelligence 缓存目录
 
-KodaX 现在会把 Repo Intelligence 的本地缓存分成两条路径：
+KodaX 现在会把 Repo Intelligence 的本地缓存分成内置引擎 profile：
 
 - `.agent/repo-intelligence/`
-  - OSS baseline 的索引、缓存和现有 task-engine 产物。
-- `.repointel/`
-  - premium `repointel` 的 workspace 级共享缓存，供本地 daemon / native frontdoor 使用。
+  - full 引擎索引、缓存和现有 task-engine 产物。
+- `.agent/repo-intelligence/light/`
+  - light 模式启发式索引缓存。
 
 这样拆开的目的很明确：
 
-- premium 不可用时，OSS fallback 仍然可以稳定工作。
-- premium 缓存不会污染 OSS 产物目录。
-- KodaX 和其他宿主可以共享同一份 premium workspace cache。
+- full 和 light profile 可以独立重建。
+- light 模式的低置信度状态不会被误认为 full 引擎状态。
+- 未来缓存迁移可以删除一个 profile，而不破坏另一个。
 
-`.repointel/` 是本地生成目录，不应该提交到 Git。
+`.agent/repo-intelligence/` 是本地生成目录，不应该提交到 Git。
 
 ---
 

package/dist/builtin/code-review/SKILL.md

@@ -58,6 +58,25 @@ compatibility: "Works best in a git repository or when the review target is prov
 
 ## 使用示例
 
-- `/code-review src/auth.ts` - 审查单个文件
-- `/code-review packages/coding/src/` - 审查目录
-- `/code-review` - 审查当前 git 变更
+- `/code-review src/auth.ts` - 审查单个文件
+- `/code-review packages/coding/src/` - 审查目录
+- `/code-review` - 审查当前 git 变更
+
+## Lean Review Lens
+
+When the user asks for lean review, minimal diff, YAGNI, over-engineering, or
+native/stdlib replacement opportunities, add this lens after correctness and
+security findings:
+
+- Look for code, files, abstractions, dependencies, configuration, or workflow
+  changes that can be deleted without losing requested behavior.
+- Prefer existing repository code, stdlib/native platform features, or an
+  already-installed dependency when that is verifiably simpler than new custom
+  code.
+- Do not recommend cutting trust-boundary validation, security checks,
+  data-loss protection, accessibility basics, observability needed for safety,
+  or explicitly requested behavior.
+- Do not present optional cleanup as a high-severity finding. Put non-blocking
+  deletion/replacement ideas under `## Lean Suggestions`.
+- For each lean suggestion, explain what can be skipped or removed and when it
+  should be added back.

package/dist/chunks/agent-YJNC2755.js

@@ -0,0 +1,2 @@
+// @kodax-ai/kodax — bundled distribution. See docs/ADR.md ADR-022 + ADR-024.
+import{I as c,J as d,K as e,L as f,Z as g,_ as h,ia as i,oa as j}from"./chunk-CQ6EQG7E.js";import"./chunk-D6QVXQNI.js";import"./chunk-526OILYL.js";import"./chunk-7QB55SYG.js";import"./chunk-HS2K74I4.js";import{mb as a,nb as b}from"./chunk-ZZDC75H4.js";import"./chunk-P4VF3JEP.js";import"./chunk-V4WSBIXB.js";export{d as bucketProviderPayloadSize,g as buildAutoRepoIntelligenceContext,e as checkPromiseSignal,b as cleanupIncompleteToolCalls,h as describeTransientProviderRetry,f as emitResilienceDebug,c as estimateProviderPayloadBytes,j as runKodaX,i as saveSessionSnapshot,a as validateAndFixToolHistory};

package/dist/chunks/argument-completer-QGBNXTYJ.js

@@ -0,0 +1,2 @@
+// @kodax-ai/kodax — bundled distribution. See docs/ADR.md ADR-022 + ADR-024.
+import{Aa as b,za as a}from"./chunk-QHWXPJEG.js";import"./chunk-6AU6EPO6.js";import"./chunk-XXEIFNBE.js";import"./chunk-NKHXRN7G.js";import"./chunk-73Z7BK5H.js";import"./chunk-PIQWODWN.js";import"./chunk-CQ6EQG7E.js";import"./chunk-D6QVXQNI.js";import"./chunk-526OILYL.js";import"./chunk-7QB55SYG.js";import"./chunk-HS2K74I4.js";import"./chunk-ZZDC75H4.js";import"./chunk-P4VF3JEP.js";import"./chunk-V4WSBIXB.js";export{a as ArgumentCompleter,b as createArgumentCompleter};

package/dist/chunks/chunk-526OILYL.js

@@ -0,0 +1,2 @@
+// @kodax-ai/kodax — bundled distribution. See docs/ADR.md ADR-022 + ADR-024.
+import{l as o}from"./chunk-HS2K74I4.js";import{a as i}from"./chunk-V4WSBIXB.js";function r(u){let e=o(u?.llm);if(!e)return;let t={};return e.requestTimeoutMs!==void 0&&(t.requestTimeoutMs=e.requestTimeoutMs),e.streamIdleTimeoutMs!==void 0&&(t.streamIdleTimeoutMs=e.streamIdleTimeoutMs),e.chunkTimeoutMs!==void 0&&(t.chunkTimeoutMs=e.chunkTimeoutMs),e.maxRetryDelayMs!==void 0&&(t.maxRetryDelayMs=e.maxRetryDelayMs),Object.keys(t).length>0?t:void 0}i(r,"providerResilienceConfigFromTimeouts");export{r as a};

package/dist/chunks/{chunk-ZBK3DZ3S.js → chunk-6AU6EPO6.js}

@@ -1,2 +1,2 @@
 // @kodax-ai/kodax — bundled distribution. See docs/ADR.md ADR-022 + ADR-024.
-import{wa as e}from"./chunk-JCDO2FR4.js";import{a as n}from"./chunk-V4WSBIXB.js";import{readFile as i}from"fs/promises";var c={enabled:!0,triggerPercent:75};async function g(o){let t=e("config.json");try{let r=await a(t);if(r?.compaction)return{...c,...r.compaction}}catch{}return c}n(g,"loadCompactionConfig");async function a(o){try{let t=await i(o,"utf-8");return JSON.parse(t)}catch{return null}}n(a,"readConfigFile");export{g as a};
+import{wa as e}from"./chunk-ZZDC75H4.js";import{a as n}from"./chunk-V4WSBIXB.js";import{readFile as i}from"fs/promises";var c={enabled:!0,triggerPercent:75};async function g(o){let t=e("config.json");try{let r=await a(t);if(r?.compaction)return{...c,...r.compaction}}catch{}return c}n(g,"loadCompactionConfig");async function a(o){try{let t=await i(o,"utf-8");return JSON.parse(t)}catch{return null}}n(a,"readConfigFile");export{g as a};