@kodax-ai/kodax 0.7.48 → 0.7.50

package/README.md

@@ -17,7 +17,7 @@
   <a href="LICENSE"><img alt="license" src="https://img.shields.io/badge/license-Apache--2.0-blue?style=flat-square"></a>
   <a href="https://github.com/icetomoyo/KodaX/stargazers"><img alt="GitHub stars" src="https://img.shields.io/github/stars/icetomoyo/KodaX?style=flat-square&logo=github&color=f1c40f"></a>
   <a href="https://github.com/icetomoyo/KodaX/actions"><img alt="CI" src="https://img.shields.io/github/actions/workflow/status/icetomoyo/KodaX/release.yml?style=flat-square&label=release"></a>
-  <img alt="providers" src="https://img.shields.io/badge/LLMs-13_native_+_OpenAI%2FAnthropic--compat-2ecc71?style=flat-square">
+  <img alt="providers" src="https://img.shields.io/badge/LLMs-14_aliases_+_custom-2ecc71?style=flat-square">
 </p>
 
 <p align="center">
@@ -103,7 +103,7 @@ That's it. You're in the REPL — ask anything in natural language.
       5-stage self-modification staircase (scaffold → validate → stage → test → activate) gated by an 8-invariant admission contract.
     </td>
     <td align="center" valign="top">
-      <h3>🛠 30+ built-in tools</h3>
+      <h3>🛠 50+ built-in tools</h3>
       <sub>File · shell · search · MCP · ACP</sub>
       <br><br>
       Repo intelligence, semantic search, git worktree, web fetch — all addressable through one clean tool surface.
@@ -119,7 +119,7 @@ That's it. You're in the REPL — ask anything in natural language.
 | Node-free single binary | ✅ Bun | ❌ Node | ❌ Python | ✅ Rust | ❌ Electron | ❌ Extension |
 | Native China providers<br><sub>(Zhipu · Kimi · MiniMax · MiMo · Ark · Qwen)</sub> | ✅ 6 native | ❌ | ⚠ via LiteLLM | ❌ OpenAI-first | ❌ no provider menu | ⚠ Kimi / Qwen / DeepSeek |
 | Branchable session lineage | ✅ fork & rewind | ⚠ routines / sessions | ❌ | ❌ | ❌ | ⚠ checkpoints |
-| Multi-agent + MCP + 30+ tools | ✅ all three | ✅ all three | ⚠ tools, no MCP | ✅ all three | ⚠ Composer + MCP | ✅ all three |
+| Multi-agent + MCP + 50+ tools | ✅ all three | ✅ all three | ⚠ tools, no MCP | ✅ all three | ⚠ Composer + MCP | ✅ all three |
 
 <sub>Data verified May 2026 against public docs ([Claude Code](https://github.com/anthropics/claude-code) · [Aider](https://aider.chat/docs/llms.html) · [Codex CLI](https://github.com/openai/codex) · [Cursor](https://cursor.com) · [Cline](https://github.com/cline/cline)). ⚠ = partial / requires extra setup / not first-class. Corrections welcome via PR.</sub>
 
@@ -178,9 +178,43 @@ If you need a custom base URL or an OpenAI/Anthropic-compatible endpoint, define
 
 `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.
 
+#### OpenAI-compatible reasoning providers
+
+Some OpenAI-compatible reasoning models require KodaX to replay the previous assistant turn's `reasoning_content` on later requests. DeepSeek V4 thinking mode is the known load-bearing case. Built-in DeepSeek already opts in; custom providers must say so explicitly:
+
+```json
+{
+  "customProviders": [
+    {
+      "name": "my-deepseek-v4",
+      "protocol": "openai",
+      "baseUrl": "https://example.com/v1",
+      "apiKeyEnv": "MY_DEEPSEEK_API_KEY",
+      "model": "deepseek-v4-flash",
+      "supportsThinking": true,
+      "reasoningCapability": "native-toggle",
+      "replayReasoningContent": true
+    }
+  ]
+}
+```
+
+Keep `replayReasoningContent` unset or `false` for OpenAI proper and gateways that reject unknown assistant-message fields. If one gateway routes mixed models, prefer per-model overrides:
+
+```json
+{
+  "models": [
+    { "id": "deepseek-v4-flash", "replayReasoningContent": true },
+    { "id": "gpt-5", "replayReasoningContent": false }
+  ]
+}
+```
+
+Sidecar verifier judge calls use provider-level forced tool choice when supported. If a compatible endpoint rejects the `tool_choice` parameter, KodaX retries that verifier request once without forced tool choice and still fails open rather than blocking the main Worker.
+
 #### Opting a custom provider into image / vision input (FEATURE_134 v0.7.40)
 
-If your custom provider's underlying model supports image input (vision), add a `capabilityProfile.multimodalSupport: "image-input"` block so KodaX does not artificially block multimodal requests at the SA-path policy gate. The 12 built-in vision-capable providers (Anthropic, OpenAI, the 9 Anthropic-/OpenAI-compat clones — DeepSeek, Kimi, Kimi-code, Qwen, Zhipu, Zhipu-coding, MiniMax-coding, MiMo-coding, Ark-coding — plus Gemini-CLI via the CLI's `@<path>` file-include syntax) already ship with this flag enabled by default; only Codex-CLI and custom providers need to opt in.
+If your custom provider's underlying model supports image input (vision), add a `capabilityProfile.multimodalSupport: "image-input"` block so KodaX does not artificially block multimodal requests at the SA-path policy gate. Built-in vision-capable aliases (Anthropic, OpenAI, Anthropic-/OpenAI-compatible aliases such as DeepSeek, Kimi, Qwen, Zhipu, MiniMax, MiMo, Ark, plus Gemini-CLI via the CLI's `@<path>` file-include syntax) already ship with this flag enabled by default; Codex-CLI and custom providers need to opt in when their underlying model supports image input.
 
 ```json
 {
@@ -273,12 +307,12 @@ Setup, runtime modes, REPL controls, config schema, and external-host integratio
 
 ## Architecture
 
-KodaX uses a **monorepo architecture** with npm workspaces. Source layout has 9 workspace packages; published as a single bundled npm package `@kodax-ai/kodax` with 6 SDK subpath exports (`/agent`, `/llm`, `/coding`, `/repl`, `/skills`, `/mcp`; ADR-022 + ADR-024 v0.7.39 + ADR-032 v0.7.42 added `/mcp`):
+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/
 ├── packages/                # 4 workspace packages (FEATURE_194 v0.7.43)
-│   ├── llm/                 # @kodax-ai/llm - LLM abstraction (12 providers)
+│   ├── llm/                 # @kodax-ai/llm - LLM abstraction (14 built-in provider aliases)
 │   │   └── providers/       # Anthropic, OpenAI, DeepSeek, Kimi, MiMo, MiniMax, Zhipu, Ark, …
 │   │
 │   ├── agent/               # @kodax-ai/agent - Generic Agent framework
@@ -290,7 +324,7 @@ KodaX/
 │   │   └── tracing/         # tracing / observability (inline v0.7.43)
 │   │
 │   ├── coding/              # @kodax-ai/coding - Coding Agent (tools + prompts)
-│   │   ├── tools/           # 30+ tools: read, write, edit, bash, glob, grep, undo,
+│   │   ├── tools/           # 50+ tools: read, write, edit, bash, glob, grep, undo,
 │   │   │                    #   dispatch_child_task, send_message, task_stop,
 │   │   │                    #   ask_user_question, repo-intelligence, …
 │   │   └── repo-intelligence/ # incl. protocol.ts (inline v0.7.43)
@@ -299,7 +333,7 @@ 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}
+│   └── sdk-*.ts             # SDK subpath re-exports → @kodax-ai/kodax/{agent,llm,coding,repl,skills,mcp,session}
 │
 └── package.json             # Root workspace config; release.mjs rewrites name + injects subpath exports
 ```
@@ -326,7 +360,7 @@ KodaX/
        ┌──────────────┐ ┌──────────────────────────┐ ┌──────────────┐
        │@kodax-ai/    │ │@kodax-ai/agent           │ │@kodax-ai/llm │
        │coding (via   │ │Runner + fan-out +        │ │LLM Abstract  │
-       │above)        │ │idle-yield + session-     │ │(12 providers)│
+       │above)        │ │idle-yield + session-     │ │(14 aliases)  │
        │              │ │lineage + skills + mcp +  │ │              │
        │              │ │tracing (FEATURE_194)     │ │              │
        └──────────────┘ └──────────────────────────┘ └──────────────┘
@@ -338,9 +372,9 @@ Source-side workspace package names (`@kodax-ai/*`). npm consumers install the s
 
 | Workspace package | Purpose | Key Dependencies |
 |---------|---------|------------------|
-| `@kodax-ai/llm` | LLM abstraction (12 providers + custom registration) | @anthropic-ai/sdk, openai |
+| `@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/coding` | Coding Agent — 30+ tools (incl. `dispatch_child_task` / `send_message` / `task_stop`) + role prompts + auto-continue + repo-intelligence protocol | @kodax-ai/llm, @kodax-ai/agent |
+| `@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 |
 
 ### Source-side vs npm-published surface
@@ -354,29 +388,34 @@ KodaX has two layers that consumers should understand separately:
 
 | Source package | npm subpath | Type | What you get | Example consumer |
 |---|---|---|---|---|
-| `packages/llm`    | `@kodax-ai/kodax/llm`     | Full package | 12-provider LLM abstraction (77 exports) | Standalone LLM clients |
+| `packages/llm`    | `@kodax-ai/kodax/llm`     | Full package | 14-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 |
-| `packages/coding` | `@kodax-ai/kodax/coding`  | Full package | Coding agent + 30+ tools + repo-intelligence (342 exports) | Build a Claude Code-shape product |
+| `packages/coding` | `@kodax-ai/kodax/coding`  | Full package | Coding agent + 50+ tools + repo-intelligence (342 exports) | Build a Claude Code-shape product |
 | `packages/repl`   | `@kodax-ai/kodax/repl`    | Full package | Ink TUI + permission modes + commands (193 exports) | Terminal-UI consumers |
 | `packages/repl`   | `@kodax-ai/kodax/session` | **Narrow subset** | Session management only — `listSessions` / `forkSession` / `watchSessions` / ... (9 exports) | IDE plugins reading session history |
 
 **Rule of thumb**: if you need Runner / Agent / fan-out, import from `/agent`. If you only need skills or mcp APIs, import from `/skills` or `/mcp` to get a smaller bundle. The narrow subsets are subsets of the full packages — they do **not** expose extra symbols.
 
+**Dynamic Workflows (FEATURE_217, v0.7.49)**: the domain-neutral workflow runtime is part of `/agent` — `import { createWorkflowRuntime, runWorkflow, WorkflowAbortError, WorkflowLimitError } from '@kodax-ai/kodax/agent'`. The coding-side integration (agent backend + built-in workflows + saved-workflow discovery/generation: `createCodingWorkflowBackend`, `runWorkflowFromOptions`, `parallelInvestigation`, `discoverSavedWorkflows`, `generateWorkflowFromOptions`, …) is part of `/coding`. FEATURE_217 is the v0.7.49 home for the full Dynamic Workflow product loop: `/workflow create <request>` generates restricted scripts, `/workflow save <runId> <name>` stores `.workflow.json` rerunnable workflows, generated/saved scripts coordinate agents through `WorkflowApi`, run lifecycle state stays observable, opt-in `isolation:"worktree"` routes selected children to parent-managed worktrees, and all file/shell effects still pass through agent tools and the existing permission gates. There is **no** separate `@kodax-ai/kodax/agent/workflow` root-package subpath; source-package consumers of `@kodax-ai/agent` can still use that package's `./workflow` subpath.
+
+**Workflow Process Surface (FEATURE_229, v0.7.50 implementation complete; release validation pending)**: workflow progress is now a reusable Agent-layer process contract rather than private REPL text. SDK hosts can subscribe to `WorkflowProcessEvent`/poll `WorkflowProcessSnapshot`, use `createWorkflowRunManager` and `createWorkflowLifecycleController` for stop/pause/resume/result/artifact/delete/prune/identity/preflight controls, and receive ANSI-free provenance fields (`source`, `sourceRunId`, `sourceWorkflowName`, `savedWorkflowName`, `revisionOf`) plus `resultSummary`. `/coding` owns the coding workflow backend and run graph, `/repl` renders the same snapshots, and the terminal UI is not the hidden source of truth. `KodaXEvents` callbacks also take an optional metadata arg (`KodaXToolEventMeta` / `KodaXActivityEventMeta` / `KodaXWorkflowEventMeta`) so a host can attribute every child-agent tool/thinking/progress event to its workflow run and child id without a second event protocol, and generated/saved workflow scripts pass `validateRestrictedWorkflowSource` (compile + source-policy check) plus a generator repair/smoke loop before they run. See [docs/ADR.md ADR-040](docs/ADR.md) for the layering rationale.
+
 ---
 
 ## Features
 
 - **Modular Architecture** - Use as CLI, as a library, or as a Node-free single binary
-- **12 LLM Providers** - Anthropic, OpenAI, DeepSeek, Kimi, Kimi Code, Qwen, Zhipu, Zhipu Coding, MiniMax Coding, MiMo Coding (Xiaomi Token Plan), Gemini CLI, Codex CLI — plus user-defined OpenAI/Anthropic-compatible providers
-- **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. V1 Scout/Planner/Generator/Evaluator chain fully retired (FEATURE_193 v0.7.43); `emit_handoff` tool deleted (FEATURE_190 v0.7.43); accept-verdict UI silently passes through (FEATURE_195 v0.7.43); content-aware fire gate skips trivial-chat sidecar calls (FEATURE_196 v0.7.43). Async child steering via `dispatch_child_task` + `send_message` + `task_stop` with idle-yield wait (FEATURE_120 / FEATURE_155, v0.7.39); specialist routing via `subagent_type` (FEATURE_191 v0.7.43).
+- **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
+- **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
 - **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
-- **Rich Tool Surface** - 30+ built-in tools across file ops, shell, search, repo intelligence, MCP capabilities, git worktree, and agent control
+- **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
 - **Cross-Platform** - Windows/macOS/Linux
@@ -466,14 +505,15 @@ 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 { createProvider } from '@kodax-ai/kodax/llm';           // LLM abstraction (12 providers)
+import { getProvider } from '@kodax-ai/kodax/llm';              // LLM abstraction (14 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
 import { createMcpManager } from '@kodax-ai/kodax/mcp';         // MCP popout manager (v0.7.42)
+import { listSessions } from '@kodax-ai/kodax/session';         // session history helpers
 ```
 
-All 7 entries (root + 6 subpaths) share internal code via ESM chunk splitting — importing from `/agent` does not pull in `/repl`'s Ink + React surface.
+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.
 
 > **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.
 
@@ -656,6 +696,20 @@ Related variables: `KODAX_MAX_TOKENS` (global fallback when no provider/model ca
 
 > **Retired in v0.7.42**: `KODAX_RST_PRONE_PROVIDERS` and `KODAX_WRITE_TURN_MAX_TOKENS` (the v0.7.28 P2b write-turn cap mechanism) are no longer recognized. The 2026-04 bench measured RST as time-based (zhipu-coding 308s server kill window), not payload-size-based, so the cap was retired in favor of the per-provider `streamMaxDurationMs` watchdog + non-streaming fallback chain (configured in `registry.ts`). Existing env exports become silent no-ops; remove them from shell profiles when convenient.
 
+#### Sidecar verifier diagnostics
+
+Use these when diagnosing Worker text-only completion stalls or custom provider verifier behavior:
+
+```bash
+export KODAX_VERIFIER_LOG=1
+export KODAX_VERIFIER_PROVIDER=anthropic
+export KODAX_VERIFIER_MODEL=claude-haiku-4-5-20251001
+```
+
+- `KODAX_VERIFIER_LOG=1` shows verifier gate/elapsed/trace information and is equivalent to `"verifierLog": true` in `~/.kodax/config.json`.
+- `KODAX_VERIFIER_PROVIDER` + `KODAX_VERIFIER_MODEL` route the verifier to a separate provider/model instead of inheriting the main Worker model. Set both together.
+- `KODAX_VERIFIER_ALWAYS=1` forces the verifier to fire on every text-only completion for debugging/regression sweeps.
+
 ## Advanced Library Usage
 
 #### Simple Mode (runKodaX)
@@ -740,7 +794,7 @@ await runKodaX({
 
 ## SDK Usage
 
-KodaX ships as a single npm package `@kodax-ai/kodax` with 6 SDK subpath exports (ADR-024 v0.7.39 + ADR-032 v0.7.42 added `/mcp`). Each subpath is tree-shake-friendly so consumers pull only what they need:
+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:
 
 ```bash
 npm install @kodax-ai/kodax
@@ -749,18 +803,19 @@ 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';                // 12-provider LLM abstraction
+import { getProvider } from '@kodax-ai/kodax/llm';                // 14-alias LLM abstraction
 import { KODAX_TOOLS } from '@kodax-ai/kodax/coding';             // tools + prompts + agent loop
-import { InkREPL } from '@kodax-ai/kodax/repl';                   // Ink TUI components
+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)
+import { listSessions } from '@kodax-ai/kodax/session';           // session history helpers
 ```
 
 > The SDK is **ESM-only**. CommonJS consumers (Electron main / Webpack CJS / `require()` callers) must use `await import('@kodax-ai/kodax/...')` — see [docs/SDK_EMBEDDER_GUIDE.md §5](docs/SDK_EMBEDDER_GUIDE.md#5-consuming-from-a-commonjs-context-electron-main-cjs-bundles).
 
 ### `@kodax-ai/kodax/llm` — LLM Abstraction
 
-12 built-in providers (Anthropic, OpenAI, DeepSeek, Kimi, Kimi-Code, Qwen, Zhipu, Zhipu-Coding, MiniMax-Coding, MiMo-Coding, Ark-Coding, Gemini-CLI, Codex-CLI) + custom provider registration.
+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.
 
 ```typescript
 import { getProvider, KodaXBaseProvider } from '@kodax-ai/kodax/llm';
@@ -838,7 +893,7 @@ const result = await executeSkill({
 
 ### `@kodax-ai/kodax/coding` — Coding Agent
 
-Complete coding agent: 30+ tools (`read`/`write`/`edit`/`bash`/`grep`/`glob`/`dispatch_child_task`/`send_message`/`task_stop`/...) + Worker role prompt + Sidecar Verifier (out-of-band Stop-hook) + agent loop + auto-continue + session management.
+Complete coding agent: 50+ tools (`read`/`write`/`edit`/`bash`/`grep`/`glob`/`dispatch_child_task`/`send_message`/`task_stop`/...) + Worker role prompt + Sidecar Verifier (out-of-band Stop-hook) + agent loop + auto-continue + session management.
 
 ```typescript
 import { runKodaX, KodaXClient, KODAX_TOOLS } from '@kodax-ai/kodax/coding';
@@ -860,14 +915,14 @@ await client.send('Create a new file');
 await client.send('Add a function to it'); // Has context from previous message
 ```
 
-**Key Features**: 30+ built-in tools (see [Tools](#tools)) · V2 Worker single-loop + Sidecar Verifier (FEATURE_184 v0.7.42 / V1 chain fully retired by FEATURE_193 v0.7.43) · async child steering via `send_message` / `task_stop` (FEATURE_120, v0.7.39) · idle-yield wait mechanic (FEATURE_155, v0.7.38) · specialist routing via `subagent_type` (FEATURE_191, v0.7.43) · auto-continue · session lineage.
+**Key Features**: 50+ built-in tools (see [Tools](#tools)) · V2 Worker single-loop + Sidecar Verifier (FEATURE_184 v0.7.42 / V1 chain fully retired by FEATURE_193 v0.7.43) · async child steering via `send_message` / `task_stop` (FEATURE_120, v0.7.39) · idle-yield wait mechanic (FEATURE_155, v0.7.38) · specialist routing via `subagent_type` (FEATURE_191, v0.7.43) · auto-continue · session lineage.
 
 ### `@kodax-ai/kodax/repl` — Interactive Terminal UI
 
 Ink/React-based interactive REPL. Permission modes, command system, themed streaming display.
 
 ```typescript
-import { InkREPL } from '@kodax-ai/kodax/repl';
+import { runInkInteractiveMode } from '@kodax-ai/kodax/repl';
 
 // Usually used via the `kodax` bin command; can be embedded:
 // - Interactive terminal UI (Ink components)
@@ -875,6 +930,7 @@ import { InkREPL } from '@kodax-ai/kodax/repl';
 // - Command system (/help, /mode, /clear, /status, …)
 // - Skills integration
 // - Theme support
+await runInkInteractiveMode({ provider: 'zhipu-coding', reasoningMode: 'auto' });
 ```
 
 **Key Features**: Ink-based React components · 3 permission modes (auto / plan / accept-edits) · built-in commands · real-time streaming display · context-usage indicator.
@@ -897,7 +953,7 @@ import { InkREPL } from '@kodax-ai/kodax/repl';
 
 | Use Case | Subpath | Why |
 |----------|---------|-----|
-| Only need LLM abstraction | `@kodax-ai/kodax/llm` | Minimal deps; 12 providers |
+| Only need LLM abstraction | `@kodax-ai/kodax/llm` | Minimal deps; 14 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 |
@@ -906,18 +962,18 @@ import { InkREPL } from '@kodax-ai/kodax/repl';
 
 | Provider | Environment Variable | Reasoning Support | Default Model |
 |----------|----------------------|-------------------|---------------|
-| anthropic | `ANTHROPIC_API_KEY` | Native | claude-sonnet-4-6 |
-| openai | `OPENAI_API_KEY` | Native | gpt-5.3-codex |
-| kimi | `KIMI_API_KEY` | Native | kimi-k2.6 |
+| anthropic | `ANTHROPIC_API_KEY` | Native | claude-sonnet-4-6 (`claude-opus-4-6` / `claude-haiku-4-5` via `/model`) |
+| openai | `OPENAI_API_KEY` | Native | gpt-5.3-codex (`gpt-5.4` / `gpt-5.3-codex-spark` via `/model`) |
+| kimi | `KIMI_API_KEY` | Native | kimi-k2.6 (`kimi-k2.7-code` 256K / `k2.5` via `/model`) |
 | kimi-code | `KIMI_CODE_API_KEY` | Native | kimi-for-coding |
 | qwen | `QWEN_API_KEY` | Native | qwen3.5-plus |
-| zhipu | `ZHIPU_API_KEY` | Native | glm-5 |
-| zhipu-coding | `ZHIPU_CODING_API_KEY` | Native | glm-5 |
-| minimax-coding | `MINIMAX_CODING_API_KEY` | Native | MiniMax-M2.7 (M2 family default; `MiniMax-M3` Frontier Coding with native multimodal + 1M ctx available via `/model`, plus M2.7-highspeed / M2.5 / M2.5-highspeed / M2.1 / M2.1-highspeed / M2 on the same gateway) |
+| 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`) |
+| 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) |
-| ark-coding | `ARK_CODING_API_KEY` | Native | glm-5.1 (Volcengine Ark Coding Plan, multi-model gateway, Anthropic-compat) |
-| deepseek | `DEEPSEEK_API_KEY` | Native | deepseek-v4-flash |
+| ark-coding | `ARK_CODING_API_KEY` | Native | glm-5.1 (Volcengine Ark Coding Plan: GLM, Kimi, MiniMax M3/M2.7, DeepSeek V3.2/V4, Doubao Seed 2.0 routes) |
+| deepseek | `DEEPSEEK_API_KEY` | Native | deepseek-v4-flash (`deepseek-v4-pro` via `/model`) |
 | gemini-cli | `GEMINI_API_KEY` | Prompt-only / CLI bridge | (via gemini CLI) |
 | codex-cli | `OPENAI_API_KEY` | Prompt-only / CLI bridge | (via codex CLI) |
 
@@ -950,7 +1006,7 @@ kodax --agent-mode ama "Analyze code structure, check test coverage, find bugs"
 
 ## Tools
 
-KodaX ships 30+ built-in tools, grouped below. They are registered as a single flat tool surface to the LLM; the categories here are just for navigation.
+KodaX ships 50+ built-in tools, grouped below. They are registered as a single flat tool surface to the LLM; the categories here are just for navigation.
 
 ### File operations
 | Tool | Description |

package/README_CN.md

@@ -17,7 +17,7 @@
   <a href="LICENSE"><img alt="license" src="https://img.shields.io/badge/license-Apache--2.0-blue?style=flat-square"></a>
   <a href="https://github.com/icetomoyo/KodaX/stargazers"><img alt="GitHub stars" src="https://img.shields.io/github/stars/icetomoyo/KodaX?style=flat-square&logo=github&color=f1c40f"></a>
   <a href="https://github.com/icetomoyo/KodaX/actions"><img alt="CI" src="https://img.shields.io/github/actions/workflow/status/icetomoyo/KodaX/release.yml?style=flat-square&label=release"></a>
-  <img alt="providers" src="https://img.shields.io/badge/LLMs-13_原生_+_OpenAI%2FAnthropic--compat-2ecc71?style=flat-square">
+  <img alt="providers" src="https://img.shields.io/badge/LLMs-14_aliases_+_custom-2ecc71?style=flat-square">
 </p>
 
 <p align="center">
@@ -103,7 +103,7 @@ kodax
       5 阶自改造阶梯（scaffold → validate → stage → test → activate），由 8 条 admission invariant 守护。
     </td>
     <td align="center" valign="top">
-      <h3>🛠 30+ 内置工具</h3>
+      <h3>🛠 50+ 内置工具</h3>
       <sub>文件 · shell · 搜索 · MCP · ACP</sub>
       <br><br>
       repo intelligence、语义搜索、git worktree、web fetch，统一从干净的 tool definition 接口暴露。
@@ -119,7 +119,7 @@ kodax
 | 免 Node 单文件 | ✅ Bun | ❌ 需 Node | ❌ 需 Python | ✅ Rust | ❌ Electron | ❌ 插件 |
 | 国内 6 家原生<br><sub>（智谱·Kimi·MiniMax·MiMo·方舟·Qwen）</sub> | ✅ 6 家原生 | ❌ | ⚠ 走 LiteLLM | ❌ OpenAI 主线 | ❌ 无 provider 菜单 | ⚠ Kimi/Qwen/DeepSeek |
 | 可分叉会话血缘 | ✅ fork & rewind | ⚠ routines/sessions | ❌ | ❌ | ❌ | ⚠ checkpoints |
-| Multi-agent + MCP + 30+ 工具 | ✅ 三项全有 | ✅ 三项全有 | ⚠ 有 tools, 无 MCP | ✅ 三项全有 | ⚠ Composer + MCP | ✅ 三项全有 |
+| Multi-agent + MCP + 50+ 工具 | ✅ 三项全有 | ✅ 三项全有 | ⚠ 有 tools, 无 MCP | ✅ 三项全有 | ⚠ Composer + MCP | ✅ 三项全有 |
 
 <sub>数据于 2026-05 对照官方公开文档核对（[Claude Code](https://github.com/anthropics/claude-code) · [Aider](https://aider.chat/docs/llms.html) · [Codex CLI](https://github.com/openai/codex) · [Cursor](https://cursor.com) · [Cline](https://github.com/cline/cline)）。⚠ 表示部分支持 / 需额外配置 / 非 first-class。欢迎 PR 修正。</sub>
 
@@ -206,14 +206,15 @@ const result = await runKodaX(
 
 ```typescript
 import { Runner } from '@kodax-ai/kodax/agent';                // Agent runtime
-import { createProvider } from '@kodax-ai/kodax/llm';           // LLM 抽象（12 家 provider）
+import { getProvider } from '@kodax-ai/kodax/llm';              // LLM 抽象（14 个内置 alias）
 import { runKodaX } from '@kodax-ai/kodax/coding';              // Coding tools + prompts
 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
 ```
 
-7 个入口（root + 6 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。
+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。
 
 > **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。
 
@@ -239,9 +240,53 @@ import { createMcpManager } from '@kodax-ai/kodax/mcp';         // MCP popout ma
 
 `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"`。
 
+#### 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：
+
+```json
+{
+  "customProviders": [
+    {
+      "name": "my-deepseek-v4",
+      "protocol": "openai",
+      "baseUrl": "https://example.com/v1",
+      "apiKeyEnv": "MY_DEEPSEEK_API_KEY",
+      "model": "deepseek-v4-flash",
+      "supportsThinking": true,
+      "reasoningCapability": "native-toggle",
+      "replayReasoningContent": true
+    }
+  ]
+}
+```
+
+如果网关同时代理 DeepSeek 和 OpenAI proper，建议用 per-model override，避免把 `reasoning_content` 发给不接受该字段的模型：
+
+```json
+{
+  "models": [
+    { "id": "deepseek-v4-flash", "replayReasoningContent": true },
+    { "id": "gpt-5", "replayReasoningContent": false }
+  ]
+}
+```
+
+Sidecar verifier 的结构化裁决请求会优先使用 provider 级 `tool_choice` 强制工具调用；如果某个兼容端点明确拒绝 `tool_choice` 参数，KodaX 会对该 verifier 请求自动重试一次“不强制但仍带 tools”的兼容模式，并保持 fail-open，不会阻塞主 Worker。
+
+调试 Worker 结束后的 verifier 行为时可设置：
+
+```bash
+export KODAX_VERIFIER_LOG=1
+export KODAX_VERIFIER_PROVIDER=anthropic
+export KODAX_VERIFIER_MODEL=claude-haiku-4-5-20251001
+```
+
+`KODAX_VERIFIER_LOG=1` 等价于在 `~/.kodax/config.json` 写 `"verifierLog": true`，会显示 verifier gate、elapsedMs 和 trace；`KODAX_VERIFIER_PROVIDER` / `KODAX_VERIFIER_MODEL` 需要成对设置，用独立模型执行 verifier；`KODAX_VERIFIER_ALWAYS=1` 仅建议调试和回归测试时使用。
+
 #### 给自定义 provider 开图片 / vision 输入（FEATURE_134 v0.7.40）
 
-如果你的自定义 provider 后面的模型支持 vision，加 `capabilityProfile.multimodalSupport: "image-input"` 显式开启，KodaX 的 SA-path policy gate 就不会人为拦截多模态请求。内置的 12 个 vision-capable provider（Anthropic、OpenAI、9 个 Anthropic-/OpenAI-compat clone：DeepSeek / Kimi / Kimi-code / Qwen / Zhipu / Zhipu-coding / MiniMax-coding / MiMo-coding / Ark-coding，加 Gemini-CLI 通过 CLI 的 `@<path>` file-include 语法）已经默认开了这个 flag。只有 Codex-CLI 和自定义 provider 需要手动 opt-in。
+如果你的自定义 provider 后面的模型支持 vision，加 `capabilityProfile.multimodalSupport: "image-input"` 显式开启，KodaX 的 SA-path policy gate 就不会人为拦截多模态请求。内置 vision-capable alias（Anthropic、OpenAI、DeepSeek、Kimi、Qwen、Zhipu、MiniMax、MiMo、Ark，以及通过 CLI `@<path>` file-include 语法传图的 Gemini-CLI）已经默认开了这个 flag。Codex-CLI 和自定义 provider 在底层模型支持图片输入时需要手动 opt-in。
 
 ```json
 {
@@ -324,18 +369,18 @@ dist/binary/linux-x64/
 
 | Provider | 环境变量 | Reasoning | 默认 Model |
 |----------|----------|-----------|-----------|
-| anthropic | `ANTHROPIC_API_KEY` | Native | claude-sonnet-4-6 |
-| openai | `OPENAI_API_KEY` | Native | gpt-5.3-codex |
-| kimi | `KIMI_API_KEY` | Native | kimi-k2.6 |
+| anthropic | `ANTHROPIC_API_KEY` | Native | claude-sonnet-4-6（可 `/model` 切换 `claude-opus-4-6` / `claude-haiku-4-5`） |
+| openai | `OPENAI_API_KEY` | Native | gpt-5.3-codex（可 `/model` 切换 `gpt-5.4` / `gpt-5.3-codex-spark`） |
+| kimi | `KIMI_API_KEY` | Native | kimi-k2.6（可 `/model` 切换 `kimi-k2.7-code` 256K / `k2.5`） |
 | kimi-code | `KIMI_CODE_API_KEY` | Native | kimi-for-coding |
 | qwen | `QWEN_API_KEY` | Native | qwen3.5-plus |
-| zhipu | `ZHIPU_API_KEY` | Native | glm-5 |
-| zhipu-coding | `ZHIPU_CODING_API_KEY` | Native | glm-5（GLM Coding Plan 端点） |
-| minimax-coding | `MINIMAX_CODING_API_KEY` | Native | MiniMax-M2.7（M2 系列默认；`MiniMax-M3` 原生多模态 + 1M 上下文 Frontier Coding 模型可 `/model` 切换，同网关还有 M2.7-highspeed / M2.5 / M2.5-highspeed / M2.1 / M2.1-highspeed / M2）|
+| 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`） |
+| 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） |
-| ark-coding | `ARK_CODING_API_KEY` | Native | glm-5.1（火山方舟 Coding Plan，多模型网关，Anthropic 协议） |
-| deepseek | `DEEPSEEK_API_KEY` | Native | deepseek-v4-flash |
+| ark-coding | `ARK_CODING_API_KEY` | Native | glm-5.1（火山方舟 Coding Plan：GLM、Kimi、MiniMax M3/M2.7、DeepSeek V3.2/V4、Doubao Seed 2.0 路由） |
+| deepseek | `DEEPSEEK_API_KEY` | Native | deepseek-v4-flash（可 `/model` 切换 `deepseek-v4-pro`） |
 | gemini-cli | `GEMINI_API_KEY` | Prompt-only / CLI bridge | （通过 gemini CLI） |
 | codex-cli | `OPENAI_API_KEY` | Prompt-only / CLI bridge | （通过 codex CLI） |
 
@@ -343,7 +388,7 @@ dist/binary/linux-x64/
 
 ## 内置工具一览
 
-KodaX 有 30+ 个内置工具，按类别分组如下（实际暴露给 LLM 是一张扁平表）。
+KodaX 有 50+ 个内置工具，按类别分组如下（实际暴露给 LLM 是一张扁平表）。
 
 **文件操作**
 
@@ -418,13 +463,13 @@ kodax --repo-intelligence premium-native --repo-intelligence-trace
 
 ## 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 + SDK subpath exports（`/agent`、`/llm`、`/coding`、`/repl`；ADR-022 + ADR-024 v0.7.39）。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 + 7 个 SDK subpath exports（`/agent`、`/llm`、`/coding`、`/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（12 个内置 provider + 自定义 provider 注册），可独立使用 | `@anthropic-ai/sdk`, `openai` |
+| `@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/coding` | Coding Agent:30+ 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/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>/`。
@@ -440,20 +485,22 @@ KodaX 有两层结构，SDK 用户需要分开理解：
 
 | 源码包 | npm subpath | 类型 | 内容 | 典型消费者 |
 |---|---|---|---|---|
-| `packages/llm`    | `@kodax-ai/kodax/llm`     | 完整包 | 12 provider LLM 抽象 (77 exports) | 独立 LLM 客户端 |
+| `packages/llm`    | `@kodax-ai/kodax/llm`     | 完整包 | 14-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 |
-| `packages/coding` | `@kodax-ai/kodax/coding`  | 完整包 | Coding agent + 30+ 工具 + repo-intelligence (342 exports) | 构建 Claude Code 形态产品 |
+| `packages/coding` | `@kodax-ai/kodax/coding`  | 完整包 | Coding agent + 50+ 工具 + repo-intelligence (342 exports) | 构建 Claude Code 形态产品 |
 | `packages/repl`   | `@kodax-ai/kodax/repl`    | 完整包 | Ink TUI + 权限模式 + 命令系统 (193 exports) | 终端 UI 消费者 |
 | `packages/repl`   | `@kodax-ai/kodax/session` | **窄子集** | 仅会话管理 —— `listSessions` / `forkSession` / `watchSessions` 等 (9 exports) | 读取 session 历史的 IDE 插件 |
 
 **经验法则**：需要 Runner / Agent / fan-out 时从 `/agent` 引入；只需要 skills 或 mcp API 时从 `/skills` 或 `/mcp` 引入，bundle 更小。窄子集是完整包的真子集 —— **不会**有额外符号。
 
+**Workflow process surface（FEATURE_229，v0.7.50 实现已完成，发布验证待跑）**：动态工作流不再只是 REPL 私有文本，而是 Agent 层可复用的 process/event/snapshot 契约。SDK 宿主可以订阅 `WorkflowProcessEvent`、轮询 `WorkflowProcessSnapshot`，并通过 `createWorkflowRunManager` / `createWorkflowLifecycleController` 做 stop/pause/resume、读取 final result/artifact、删除/清理 terminal runs、管理 workflow identity/preflight。`/coding` 负责 coding workflow backend 与 run graph，`/repl` 只是消费同一份 snapshot 渲染 UI；SDK 不需要解析 slash-command 输出或 Ink view-model。`KodaXEvents` 回调新增可选 meta 尾参（`KodaXToolEventMeta` / `KodaXActivityEventMeta` / `KodaXWorkflowEventMeta`），宿主据此把每个子 Agent 的 tool/thinking/progress 事件归因到对应 workflow run 与 child id，无需第二套事件协议；生成/保存的工作流脚本在运行前过 `validateRestrictedWorkflowSource`（编译 + 源策略检查）与 generator 的 repair/smoke 循环。分层取舍见 [docs/ADR.md ADR-040](docs/ADR.md)。
+
 ```
 KodaX/                       # 4 workspace packages(FEATURE_194 v0.7.43)
 ├── packages/
-│   ├── llm/                 # @kodax-ai/llm —— 12 个 LLM provider 实现
+│   ├── llm/                 # @kodax-ai/llm —— 14 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/
@@ -465,9 +512,9 @@ 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}
+│   └── sdk-*.ts             # SDK subpath 入口 → @kodax-ai/kodax/{agent,llm,coding,repl,skills,mcp,session}
 ├── scripts/
-│   ├── build-bundle.mjs     # esbuild 单 bundle 多 entry 打包（CLI + 6 SDK entry + chunks）
+│   ├── build-bundle.mjs     # esbuild 单 bundle 多 entry 打包（CLI + root + 7 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/

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

@@ -59,5 +59,5 @@ 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/core/src/` - 审查目录
+- `/code-review packages/coding/src/` - 审查目录
 - `/code-review` - 审查当前 git 变更

package/dist/chunks/argument-completer-3WX5B42G.js

@@ -0,0 +1,2 @@
+// @kodax-ai/kodax — bundled distribution. See docs/ADR.md ADR-022 + ADR-024.
+import{ia as a,ja as b}from"./chunk-UB5IAZHF.js";import"./chunk-HR64F32V.js";import"./chunk-SK4HOYT2.js";import"./chunk-MFOMFMSK.js";import"./chunk-XZY4CIDV.js";import"./chunk-5UJQ2GKJ.js";import"./chunk-V4WSBIXB.js";export{a as ArgumentCompleter,b as createArgumentCompleter};