ดาวน์โหลด CodeWhale 0.8.66

Added
- Added codewhale doctor / codewhale doctor --json legacy-state diagnostics that compare known ~/.deepseek state paths with their ~/.codewhale counterparts and flag unmigrated or dual-root data (#3727).
- Added Sakana AI Fugu as a first-class OpenAI-compatible provider with sakana/fugu aliases, FUGU_API_KEY / SAKANA_API_KEY discovery, provider-picker wiring, model completions, and provider docs. Harvested from #3748 by @lerugray.
- Added WhaleFlow-to-Fleet launch-shape validation: the default Fleet workflow contract allows up to 100 total agents and 5 recursive rings, requires bounded loops/expands before launch, and preserves per-slot model selection.
- Added a read-only /config ask-rules view for the resolved permissions.toml path, file status, rule count, and configured tool/command/path ask rules. Merged from #3569 by @greyfreedom.
- Added provider-level context_window overrides so OpenAI-compatible gateways and self-hosted providers can budget against their real model context window (#3545).
- Added the native codew shim to release archives, Windows installer inputs, local release-asset preparation, and checksum verification so manual installs receive the same short command that Cargo installs build.
- Added OpenModel as a first-class Anthropic Messages provider, with config, CLI, provider picker, docs, and registry coverage. Harvested from #3585 by @noaft.
- Added WeCom Bridge deployment and security documentation, with shipped runtime/bridge commands and approval-timeout environment guidance. Harvested from #3640 by @pkeging.
- Added a token/cache/cost scorecard command for offline release gating, baseline regression checks, and per-turn cost visibility (#3388). Stream-JSON exec metadata now also reports conservative input_analysis and visible_final_answer_chars, so benchmark harnesses can measure transcript growth and final-answer bloat without guessing (#2956, #2957).
- Added a release evidence ledger for v0.8.66 and opened the external ACP registry submission for CodeWhale after validating the published codewhale@0.8.65 ACP auth handshake against the upstream registry checker (#3192).
- Added a typed [verifier] config table for the verifier-preview lane, with enabled and the shipped verdict_policy = "hunt" mapping documented and validated (#2093).
- Added Hotbar Alt+1–Alt+8 quick-slot switching with decision-card key disambiguation, plus an introductory card that explains and can dismiss the Hotbar (#3796, #3788).
- Release/docs hygiene: guarded public install/version snippets and the npm codewhaleBinaryVersion pointer against drift, made check-docs/check-facts fail on stale snippets or unmapped providers, and stopped sync-changelog from dropping a release when only [Unreleased] exists (#3767, #3768, #3769, #3770, #3771, #3772).
Changed
- Deferred Auto mode from the user-facing mode picker, cycle, hotbar, /mode command, and runtime-thread mode overrides until it has a distinct prompt and auto-review behavior; existing auto mode text now folds back to Agent instead of selecting a hollow mode, and approval modal copy no longer implies the current mode is YOLO (#3730, #3733).
- Clarified the Fleet setup surface and docs so Fleet is treated as the durable sub-agent configuration layer while WhaleFlow is the agent-authored orchestration plan that selects and monitors Fleet slots.
- Slimmed the default Constitution prompt while keeping its required structural anchors under regression coverage, reducing the static prompt footprint for cache-sensitive turns (#2953).
- Made the approval prompt inline and bottom-anchored instead of a full-screen takeover, so context and controls stay visible while a tool awaits a decision (#3799).
- The Hotbar is now hidden by default until explicit setup opt-in (#3807); the interactive Agent shell also defaults to approval-gated on with a shared baseline (#3756).
- Mode authority now resolves approval prompts through a single authority source instead of per-surface checks (#3795).
Fixed
- Surfaced legacy state relocation with a user-visible migration notice whenever ~/.deepseek/<state> is moved or copied into ~/.codewhale/<state>, so upgraded users know their data was preserved and where the canonical state now lives (#3726).
- Restored legacy .deepseek/sessions visibility for upgraded installs where an empty ~/.codewhale/sessions directory already existed, by copying missing legacy session entries into the primary CodeWhale session store without overwriting newer data (#3724).
- Calmed approval risk classification for read-only shell commands such as codewhale --version, codewhale --help, and git status --porcelain so the modal no longer labels proven read-only shell as destructive (#3730).
- Added provider/model route columns to /cache turn telemetry so DeepSeek cache-hit regressions can be correlated with Auto route changes (#3738).
- Fixed runtime API approval handling so workspace trust no longer auto-resolves ordinary tool approvals; trust now only participates in full-access retry decisions while YOLO/auto-approve remains the approval bypass (#3736).
- Fixed modal surfaces so the shared view stack paints an opaque backdrop before any overlay, while Plan/request-input popup interiors stay opaque and the Plan confirmation footer keeps action choices visible on narrow terminals (#3732).
- Added a turn-loop Plan-mode guard for file-writing tools and write-capable MCP tools so Plan's "no writes" promise is enforced before approval or execution, not only by the sandbox/catalog layer (#3734).
- Preserved the durable review safety floor for publish-like shell actions in YOLO mode, so cargo publish, npm publish, and tag/release pushes force approval instead of silently auto-approving (#3735).
- Fixed Ctrl+O external-editor freezes where CodeWhale's terminal input pump could keep reading keys while Vim/editor owned the terminal, especially in Windows mintty/cygwin shells. Thanks @buko for the precise repro (#3657).
- Hardened the OHOS dependency drift check against transient Cargo registry EOFs by retrying the dependency graph probe before failing CI.
- Updated the /links provider fallback to the current CodeWhale docs URL and added a Baidu Qianfan docs link. Harvested from #3621 by @noaft.
- Hardened CODEWHALE_TOOL_SURFACE=shell-only for benchmark/exec runs: the shell-only surface hides native tools from the model-visible catalog, and unknown CODEWHALE_TOOL_SURFACE values now warn instead of silently falling back to the full tool surface (#2954).
- Sub-agent fanout and lock hot paths: preserved event-channel headroom for progress events (#3783, thanks @cyq1017), let independent sub-agent starts join a single parallel dispatch batch instead of serializing (#3801), rendered the sub-agent sidebar/ListSubAgents from a read-only snapshot with bounded cleanup (#3803), used nonblocking best-effort sends for ListSubAgents refresh while still awaiting critical events (#3802), moved sub-agent state persistence disk I/O off the manager write lock (#3805), and used try_lock for shell-manager refresh in async UI paths (#3804).
- Provenance: runtime continuations and SubAgentHandoff now inherit standing YOLO authority, while MemoryRecall, ImportedTranscript, and AssistantGenerated inputs remain guarded (#3817).
- Approval honesty: labeled session-scoped approvals accurately instead of "always", and surfaced approval decisions in tool results (#3766).