docs(i18n): fix English doc inaccuracies and add first zh_hans translations for Tier-2

docs/AGENT_RUNTIME.md

@@ -1,5 +1,7 @@
 # The CodeWhale Agent Runtime — one durable substrate, familiar launchers
 
+> 阅读简体中文版：[zh_hans/AGENT_RUNTIME.md](zh_hans/AGENT_RUNTIME.md)
+
 This document explains how sub-agents, the headless `exec` path, Agent Fleet,
 and Runtime relate. These concepts had drifted into *two* parallel "worker"
 systems. The fix is to make the **Runtime worker run** the durable execution

docs/CHANGELOG_ARCHIVE.md

@@ -3431,7 +3431,7 @@ Welcome — and thank you.
   unsupported platforms don't fail the whole `npm install`.
 
 ### Docs
-- New [`docs/INSTALL.md`](docs/INSTALL.md) — every supported platform,
+- New [`INSTALL.md`](INSTALL.md) — every supported platform,
   prebuilt vs. `cargo install` vs. manual download, cross-compiling x64 → ARM64
   Linux with `cross` or `gcc-aarch64-linux-gnu`, and a troubleshooting section
   covering the common `Unsupported architecture`, `MISSING_COMPANION_BINARY`,

docs/CONFIGURATION.md

@@ -1787,7 +1787,7 @@ If you are upgrading from older releases:
 - `reasoning_stream_style` (string, optional provider-table key): override how streaming reasoning is separated from answer text for the active provider route. Use `separate_field` for `reasoning_content` / `reasoning` deltas, `inline_tags` for gateways that stream `<think>...</think>` inside `delta.content`, or `none` to render incoming content exactly as answer text.
 - `[providers.<name>.auth]` (table, optional): provider-scoped auth source metadata. `source = "command"` stores a command argv plus optional `timeout_ms`; `source = "secret"` stores a `secret_id`. This slice lets provider readiness, `/provider`, and doctor JSON report the auth source class without exposing command argv output or secret values; executing commands and resolving external secret material is handled by the follow-up resolver work.
 - `insecure_skip_tls_verify` (bool, optional provider-table key): legacy compatibility key, disabled by default. When true on the active provider table, provider clients reject the configuration instead of skipping TLS certificate verification. Use `SSL_CERT_FILE` for corporate or private CA bundles; `codewhale doctor` reports stale uses of this setting.
-- `default_text_model` (string, optional): defaults to `deepseek-v4-pro` for DeepSeek and `deepseek-anthropic`, `gpt-5.6` for OpenAI, `grok-4.6` for xAI, `deepseek-ai/deepseek-v4-pro` for NVIDIA NIM, `deepseek-ai/deepseek-v4-flash` for AtlasCloud, `deepseek-reasoner` for Wanjie Ark, `DeepSeek-V4-Pro` for Volcengine Ark, `deepseek/deepseek-v4-pro` for OpenRouter and Novita, `mimo-v2.5-pro` for Xiaomi MiMo, `accounts/fireworks/models/deepseek-v4-pro` for Fireworks, `deepseek-ai/DeepSeek-V4-Pro` for SiliconFlow and DeepInfra, `trinity-large-thinking` for Arcee AI, `kimi-k2.7-code` for Moonshot, `MiniMax-M3` for MiniMax, `GLM-5.3` for Z.ai, `step-3.7-flash` for StepFun, `ernie-4.0-turbo-8k` for Qianfan, `fugu` for Sakana AI, `deepseek-ai/DeepSeek-V4-Pro` for SGLang/vLLM, `deepseek-coder:1.3b` for local Ollama, and `gpt-oss:120b` for Ollama Cloud. Hugging Face and Together AI both default to `deepseek-ai/DeepSeek-V4-Pro`; `openai-codex` defaults to `gpt-5.6`; `anthropic` defaults to `claude-sonnet-4-6`; `openmodel` defaults to `deepseek-v4-flash`. Current public DeepSeek IDs are `deepseek-v4-pro` and `deepseek-v4-flash`, both with 1M context windows, 384K max output, and thinking mode enabled by default. DeepSeek's live pricing/model page now labels the Pro backend `DeepSeek-V4-Pro-0813`; the callable API ID remains `deepseek-v4-pro`, so Codewhale does not send the backend label or the Claude Code-specific `deepseek-v4-pro[1m]` selector. DeepSeek retires `deepseek-chat` and `deepseek-reasoner` on July 24, 2026; direct first-party routes migrate both to `deepseek-v4-flash`, with omitted reasoning settings preserving their former non-thinking (`off`) and thinking (`high`) intent. Explicit `reasoning_effort` wins, and provider-owned ids on Wanjie Ark, aggregators, self-hosted runtimes, and custom endpoints are not globally rewritten. SiliconFlow retains its own mapping: `deepseek-reasoner` and `deepseek-r1` select its Pro model while `deepseek-chat` and `deepseek-v3` select Flash. Provider-specific mappings translate `deepseek-v4-pro` / `deepseek-v4-flash` to each provider's model ID where supported. OpenRouter also recognizes recent large IDs such as `arcee-ai/trinity-large-thinking`, `minimax/minimax-m3`, `minimax/minimax-m2.7`, `xiaomi/mimo-v2.5-pro`, `qwen/qwen3.6-flash`, `qwen/qwen3.6-35b-a3b`, `qwen/qwen3.6-max-preview`, `qwen/qwen3.6-27b`, `qwen/qwen3.6-plus`, `qwen/qwen3.7-max`, `google/gemma-4-31b-it`, `moonshotai/kimi-k2.7-code`, `moonshotai/kimi-k2.6`, `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free`, and `nvidia/nemotron-3-ultra-550b-a55b`; direct Arcee uses bare IDs such as `trinity-large-thinking` and `trinity-large-preview`; direct Moonshot recognizes `kimi-k3`, `kimi-k2.7-code`, and `kimi-k2.6`. The exact Kimi Code endpoint recognizes bare `k3` for K3 and `kimi-for-coding` for K2.7; those membership IDs are distinct from the direct Moonshot IDs and are never rewritten across routes. Direct MiniMax recognizes `MiniMax-M3` and the documented M2.x chat model IDs; direct Z.ai recognizes `GLM-5.3` (the default), `GLM-5.2`, `GLM-5.1`, and `GLM-5-Turbo`, and OpenRouter recognizes the matching `z-ai/glm-5.1`, `z-ai/glm-5.2`, `z-ai/glm-5.3`, and `z-ai/glm-5-turbo` IDs — `GLM-5.3` has been live on the Z.ai Coding Plan since 2026-08-13; it inherits its catalog metadata from `GLM-5.2` until Z.ai publishes distinct 5.3 numbers and carries no price, and an explicit `GLM-5.2` selection keeps its own id; direct Sakana recognizes `fugu` and `fugu-ultra-20260615`; direct Xiaomi MiMo recognizes chat IDs `mimo-v2.5-pro`, `mimo-v2.5-pro-ultraspeed`, and `mimo-v2.5`, while TTS IDs are selected through `codewhale speech` / `tts`. Generic `openai`, `atlascloud`, `wanjie-ark`, `xiaomi-mimo`, `arcee`, `moonshot`, `minimax`, `openmodel`, `zai`, `stepfun`, `qianfan`, `sakana`, local Ollama, and Ollama Cloud model IDs are passed through unchanged after known aliases are normalized. OpenRouter and SiliconFlow provider configs with a custom `base_url` also preserve explicit model values, which lets OpenAI-compatible gateways accept bare model IDs. Use `/models` or `codewhale models` to discover live IDs from your configured endpoint. `CODEWHALE_MODEL` overrides this for a single process; `DEEPSEEK_MODEL` is the legacy alias.
+- `default_text_model` (string, optional): defaults to `deepseek-v4-pro` for DeepSeek and `deepseek-anthropic`, `gpt-5.6` for OpenAI, `grok-4.6` for xAI, `deepseek-ai/deepseek-v4-pro` for NVIDIA NIM, `deepseek-ai/deepseek-v4-flash` for AtlasCloud, `deepseek-reasoner` for Wanjie Ark, `DeepSeek-V4-Pro` for Volcengine Ark, `deepseek/deepseek-v4-pro` for OpenRouter and Novita, `mimo-v2.5-pro` for Xiaomi MiMo, `accounts/fireworks/models/deepseek-v4-pro` for Fireworks, `deepseek-ai/DeepSeek-V4-Pro` for SiliconFlow and DeepInfra, `trinity-large-thinking` for Arcee AI, `kimi-k2.7-code` for Moonshot, `MiniMax-M3` for MiniMax, `GLM-5.3` for Z.ai, `step-3.7-flash` for StepFun, `ernie-4.0-turbo-8k` for Qianfan, `fugu` for Sakana AI, `deepseek-ai/DeepSeek-V4-Pro` for SGLang/vLLM, `deepseek-v4-flash` for local Ollama, and `gpt-oss:120b` for Ollama Cloud. Hugging Face and Together AI both default to `deepseek-ai/DeepSeek-V4-Pro`; `openai-codex` defaults to `gpt-5.6`; `anthropic` defaults to `claude-sonnet-4-6`; `openmodel` defaults to `deepseek-v4-flash`. Current public DeepSeek IDs are `deepseek-v4-pro` and `deepseek-v4-flash`, both with 1M context windows, 384K max output, and thinking mode enabled by default. DeepSeek's live pricing/model page now labels the Pro backend `DeepSeek-V4-Pro-0813`; the callable API ID remains `deepseek-v4-pro`, so Codewhale does not send the backend label or the Claude Code-specific `deepseek-v4-pro[1m]` selector. DeepSeek retires `deepseek-chat` and `deepseek-reasoner` on July 24, 2026; direct first-party routes migrate both to `deepseek-v4-flash`, with omitted reasoning settings preserving their former non-thinking (`off`) and thinking (`high`) intent. Explicit `reasoning_effort` wins, and provider-owned ids on Wanjie Ark, aggregators, self-hosted runtimes, and custom endpoints are not globally rewritten. SiliconFlow retains its own mapping: `deepseek-reasoner` and `deepseek-r1` select its Pro model while `deepseek-chat` and `deepseek-v3` select Flash. Provider-specific mappings translate `deepseek-v4-pro` / `deepseek-v4-flash` to each provider's model ID where supported. OpenRouter also recognizes recent large IDs such as `arcee-ai/trinity-large-thinking`, `minimax/minimax-m3`, `minimax/minimax-m2.7`, `xiaomi/mimo-v2.5-pro`, `qwen/qwen3.6-flash`, `qwen/qwen3.6-35b-a3b`, `qwen/qwen3.6-max-preview`, `qwen/qwen3.6-27b`, `qwen/qwen3.6-plus`, `qwen/qwen3.7-max`, `google/gemma-4-31b-it`, `moonshotai/kimi-k2.7-code`, `moonshotai/kimi-k2.6`, `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free`, and `nvidia/nemotron-3-ultra-550b-a55b`; direct Arcee uses bare IDs such as `trinity-large-thinking` and `trinity-large-preview`; direct Moonshot recognizes `kimi-k3`, `kimi-k2.7-code`, and `kimi-k2.6`. The exact Kimi Code endpoint recognizes bare `k3` for K3 and `kimi-for-coding` for K2.7; those membership IDs are distinct from the direct Moonshot IDs and are never rewritten across routes. Direct MiniMax recognizes `MiniMax-M3` and the documented M2.x chat model IDs; direct Z.ai recognizes `GLM-5.3` (the default), `GLM-5.2`, `GLM-5.1`, and `GLM-5-Turbo`, and OpenRouter recognizes the matching `z-ai/glm-5.1`, `z-ai/glm-5.2`, `z-ai/glm-5.3`, and `z-ai/glm-5-turbo` IDs — `GLM-5.3` has been live on the Z.ai Coding Plan since 2026-08-13; it inherits its catalog metadata from `GLM-5.2` until Z.ai publishes distinct 5.3 numbers and carries no price, and an explicit `GLM-5.2` selection keeps its own id; direct Sakana recognizes `fugu` and `fugu-ultra-20260615`; direct Xiaomi MiMo recognizes chat IDs `mimo-v2.5-pro`, `mimo-v2.5-pro-ultraspeed`, and `mimo-v2.5`, while TTS IDs are selected through `codewhale speech` / `tts`. Generic `openai`, `atlascloud`, `wanjie-ark`, `xiaomi-mimo`, `arcee`, `moonshot`, `minimax`, `openmodel`, `zai`, `stepfun`, `qianfan`, `sakana`, local Ollama, and Ollama Cloud model IDs are passed through unchanged after known aliases are normalized. OpenRouter and SiliconFlow provider configs with a custom `base_url` also preserve explicit model values, which lets OpenAI-compatible gateways accept bare model IDs. Use `/models` or `codewhale models` to discover live IDs from your configured endpoint. `CODEWHALE_MODEL` overrides this for a single process; `DEEPSEEK_MODEL` is the legacy alias.
 - TelecomJS uses `deepseek-v4-pro` only as a conservative pre-refresh fallback. Once its key-scoped `/models` catalog is available, the picker uses those live rows; Codewhale omits unsupported reasoning request fields on this route.
 - `reasoning_effort` (string, optional): `off`, `low`, `medium`, `high`, `max`, `xhigh`, or `ultracode`; defaults to the configured UI tier. DeepSeek Platform receives top-level `thinking` / `reasoning_effort` fields. Ollama Cloud's OpenAI-compatible Chat Completions route preserves its documented `none` / `low` / `medium` / `high` / `max` ladder (`off` is sent as `none`; `xhigh` and `ultracode` normalize to `max`). Direct xAI `grok-4.6` on exact `https://api.x.ai/v1` receives top-level `reasoning_effort = "low" | "medium" | "high" | "xhigh"`; `off` normalizes to `high`, `max`/`ultracode` to `xhigh`, and `auto` leaves the field omitted so xAI's documented default `high` applies. A custom xAI-compatible `base_url` does not inherit that dialect. Direct Moonshot `kimi-k3` on exact `https://api.moonshot.ai/v1` is always-thinking and receives only top-level `reasoning_effort = "low" | "high" | "max"`; `off` normalizes to `low`, and `medium` to `high`. Kimi Code membership `k3` on exact `https://api.kimi.com/coding/v1` instead receives nested `thinking.effort`, and its `off` setting also normalizes to enabled `low`. Normal dispatched `auto` uses Codewhale's auto-reasoning selector and sends a concrete route-normalized tier; only an omitted reasoning setting leaves the provider default in control. Neighboring gateways and model/endpoint combinations retain the generic Moonshot contract. OpenAI Codex normalizes stale `off` to `low` and sends `max` / `ultracode` as Responses `xhigh`. Z.ai receives documented `thinking` controls and treats enabled thinking as the GLM coding high/max lane. NVIDIA NIM receives equivalent settings through `chat_template_kwargs`.
 - `verbosity` (string, optional): `normal` or `concise`. `normal` keeps the

docs/FLEET.md

@@ -1,5 +1,7 @@
 # Agent Fleet
 
+> 阅读简体中文版：[zh_hans/FLEET.md](zh_hans/FLEET.md)
+
 Agent Fleet is the local-first roster and member-selection layer for durable
 multi-worker runs. It does not execute or authorize work. After Fleet resolves
 who should participate, the delegated coordinator launches a headless

docs/GUIDE.md

@@ -46,7 +46,9 @@ runtime model.
 ## 2. First Launch
 
 Install Codewhale with the path that fits your machine. Release installers
-provide the same runtime under the `codewhale` and `codew` command names.
+provide the same runtime under the `codewhale` and `codew` command names, and
+every supported install path ships the `codewhale` dispatcher with the
+`codewhale-tui` runtime built in.
 
 ```bash
 # npm

docs/HOOKS.md

@@ -1,4 +1,5 @@
 # Hooks
+> 阅读简体中文版：[zh_hans/HOOKS.md](zh_hans/HOOKS.md)
 
 Hooks run a shell command when the Codewhale **TUI** reaches a lifecycle
 point. They are plain processes: they receive context through environment
@@ -166,7 +167,7 @@ configured instead (the backend owns its base environment, and your
 | `{ type = "all", conditions = [...] }` | every nested condition | every event |
 | `{ type = "any", conditions = [...] }` | at least one nested condition | every event |
 
-Two rules keep conditions from lying:
+Three rules keep conditions from lying:
 
 - **`exit_code` needs a real exit code.** It matches only when the event
   actually observed a process exit code — `tool_call_after`, or `on_error` for
@@ -405,8 +406,8 @@ aborted".
 Codewhale's ambient environment. Its environment is built as:
 
 1. a sanitized fixed allowlist of parent variables — `PATH`, `HOME`, `USER`,
-   `LANG` and the other `LC_*`/locale entries, `TERM`, `SHELL`, `TMPDIR`, the
-   Windows system and MSVC toolchain entries — and nothing else. Variables
+   `LANG` and the other `LC_*`/locale entries, `TERM`, `SHELL`, `TMPDIR`,
+   proxy variables, color/terminal entries such as `NO_COLOR`, `CARGO_HOME`/`RUSTUP_HOME`/`RUSTUP_TOOLCHAIN`, the Windows system and MSVC toolchain entries, and other platform keys (the full list lives in `crates/tui/src/child_env.rs`) — and nothing else. Variables
    outside that allowlist, including anything that looks like a secret, are
    dropped;
 2. then the `KEY=VALUE` pairs your `shell_env` hooks produced, applied on top.

docs/INSTALL.md

@@ -1,5 +1,7 @@
 # Installing Codewhale
 
+> 阅读简体中文版：[zh_hans/INSTALL.md](zh_hans/INSTALL.md)
+
 This page covers every supported install path and the most common
 "it didn't install" failures, including **Linux ARM64** and other less
 common platforms.

docs/KEYBINDINGS.md

@@ -1,5 +1,7 @@
 # Keybindings
 
+> 阅读简体中文版：[zh_hans/KEYBINDINGS.md](zh_hans/KEYBINDINGS.md)
+
 This is the source-of-truth catalog of every keyboard shortcut the TUI recognizes. Bindings are grouped by **context** — the focus or modal state they fire in. A binding listed under "Composer" only takes effect when the composer is focused; one under "Transcript" only when the transcript has focus; and so on.
 
 Global key chords are not yet user-configurable — tracked for a future release (#436, #437). Hotbar slot actions are configurable with `[[hotbar]]` and `/hotbar`; the Hotbar activation chord remains `Alt-1` through `Alt-8`.

docs/MCP.md

@@ -1,5 +1,7 @@
 # MCP (External Tool Servers)
 
+> 阅读简体中文版：[zh_hans/MCP.md](zh_hans/MCP.md)
+
 codewhale can load additional tools via MCP (Model Context Protocol). MCP servers can be local stdio processes that the TUI starts, or remote URL-based servers that speak Streamable HTTP with legacy SSE fallback.
 
 Browsing note:

docs/MODES.md

@@ -1,5 +1,7 @@
 # Modes and Permission Postures
 
+> 阅读简体中文版：[zh_hans/MODES.md](zh_hans/MODES.md)
+
 Codewhale has three related concepts:
 
 - **TUI mode**: what kind of visible interaction you're in (Plan/Work/Operate).