Popular: Data updated November 21, 2026

Categories

Internet1,421
Communication329
Audio & video938
Graphics & design566
Office & productivity1,184
Developer tools3,288
AI tools610
Security & privacy408
System tools3,194
Games545
Education & science242
Network & IT294

CodeWhale 0.8.65 download

Coding agent for DeepSeek models that runs in your terminal

Hunter Bown AI assistants & LLMs #33 AI assistants & LLMs
This is an older version. The current version is 0.10.2. CodeWhale 0.10.2 · Released:

Installer files 0.8.65

ArchitectureTypeScopeFile sizeDownloadSHA256
64-bit Portable — — github.com VirusTotal

Link and SHA256 come from the Windows Package Manager community manifest. Compare the hash of the downloaded file before running it.

Release notes

Added
- Provider/model/route resolution (EPIC #2608). Canonical provider, model, offering, and route types with a single RouteResolver that produces a resolved ReadyRouteCandidate (endpoint, wire protocol, model id, context limit, price) for every switch (#3458, #3084, #3384). The executing client is now constructed from the resolved candidate rather than re-derived from config (#3384). A committed, network-free Models.dev-shaped catalog gives models real context windows and pricing, with a secret-free live cache (#3497, #3498, #3385). Offering pricing with provenance is projected onto candidates (#3501, #3085), and route limits feed a route-aware context-budget service (#3508, #3523, #3086).
- Fleet execution substrate (EPIC #3154). Fleet profile types and config (#3469), durable manager resume, workspace agent-profile loading resolved into the worker runtime (#3367), loadout intent carried in task specs (#3512), and receipts that persist the resolved route for inspection (#3154, #3166). Worker status is folded into the unified /fleet surface and exposed through the Runtime API.
- Provider surfaces. A /provider readiness dashboard with reasoning readiness, an experimental/supported maturity marker, and an "open models for this provider" action (#3083, #2984, #3485); cross-provider /model search with scroll and provider type-ahead (#3484, #3075); inline <think> reasoning-stream routing with per-provider overrides (#3222); usage telemetry normalized into canonical token classes including Responses cache-miss and reasoning tokens (#2961, #3509); and remote MCP OAuth login with bearer/header auth precedence (#3527).
- More providers and routes. User-defined OpenAI-compatible custom providers via [providers.<name>] (#1519); a DeepSeek Anthropic-compatible route (#2963, #3449); a Qianfan route (#3425); Zhipu folded into Z.ai with equal-treatment model normalization (#3539); DashScope/Together fixtures.
- Localized mode picker and composer indicators. The /mode picker prompt, mode names, and hints, plus the composer's Vim mode indicator, now render in all seven shipped locales (model-facing mode labels stay English). Harvested from #2239 by @gordonlu.
- Website and automation. A runtime/integrations page, provenance and mirror-trust copy, a fact-drift CI gate, a published install script, and a weekly community digest archive on codewhale.net (#3419, #3421, #3415, #3482, #3420); per-automation mode/shell/trust/approval settings (#3467).
- Model reference browser. A read-only /modeldb command (aliases model-reference, modelref) opens a pager over the bundled catalog — every model's factual context window, max output, modality, and price, grouped by provider/kind. Labels only: it never selects, routes, or tiers a model (#3205, #2300).
- Transcript presets. A /config preset <name> [--save] mechanism with a first calm preset — calm mode, calm tool collapse, comfortable spacing, and low motion — presentation-only and evidence-preserving (#3478).
- Model capability profiles. A typed model_profile module separates intrinsic model facts from resolved provider-route capability, so compact routes defer heavier nonessential tools while standard/full routes keep the eager tool surface (#3451, #3365).
- Live provider catalog refresh. A secret-free /models live-fetch layer (401/403/404/429 mapped to typed outcomes) feeds the catalog cache; the API key authorizes the request but is never persisted into the delta or cache (#3385).
Changed
- Config modularization (#3311). ProviderKind (#3505), harness posture (#3507), and provider default seeds (#3503) moved into dedicated modules, and the config.rs monolith split into clean leaf modules (paths, search, model/base-URL constants, sub-agent limits) behind a pub use facade. AppMode helpers were centralized (#3510), and mode-vs-permission policy is now derived through a single base_policy_for_mode resolver instead of scattered mutation (#3386, advisory review-intent behavior preserved).
- Leaner tool surface. Dropped task_shell_* from the active set and folded tool_search_* (#3463); ablated the in-turn loop_guard and encoded reasoning dispositions (#3462); added the Orchestration disposition to the constitution.
- Routing. Provider/model switches and the capability-aware fallback chain resolve through RouteResolver; reasoning effort is normalized for the resolved provider; the fallback chain now skips providers that lack auth (#2574); and context window and memory-pressure come from the resolved route (#3086).
- UX. Approval modal gained a group divider and selected-row caret (#3515); picker scroll/type-ahead and selection contrast hardened (#3500); the README was rewritten as an architecture end-cap (#3087); and repo agent guidance was de-hardcoded to live truth.
- Fleet identity and defaults. Fleet workers now enter with an explicit "summoned Fleet member" operating contract, setup/profile prompts keep the default model behavior as same-route inheritance, and generated worker instructions avoid leaking recursive topology that only the orchestrator needs.
- Legacy swarm cleanup. Removed the obsolete /swarm core command/menu registration so /fleet is the product surface, while /subagents remains a compatibility shortcut to worker status.
- Running-state animation. Tool cards and background-task rows now share one faster braille spinner cadence, so Bash/background work reads consistently alive across the transcript and sidebar.
- Restored contributor credit. Threaded machine-readable credit (docs/CONTRIBUTORS.md + .github/AUTHOR_MAP) for earlier merged work that shipped without it, including the /jobs cancel-all action and the npm retry-timeout hint (#1538) by @jieshu666, and the community ACP adapter reference by @rockeverm3m.
Fixed
- Release hygiene. The strict cargo clippy --workspace --all-targets --locked -- -D warnings gate passes; npm run build no longer dirties the generated web facts; the site sets metadataBase; the community digest page parses each record independently and localizes its chrome; and cargo audit is clean with the starlark-transitive unmaintained advisories documented.
- Routing and mode correctness. Ordinary prompt text is no longer interpreted as a mode switch (#3387, #3491); model candidates are scoped to the active provider; Together-owned DeepSeek routes are accepted (#3426); insecure http:// custom endpoints raise an advisory warning (#1519); and the Fleet setup planner's role/model selection now drives the generated profile.
- Runtime stability. MCP connection drops are explicit (#3524), HTTP API calls reuse a shared MCP pool (#3532), and per-agent sub-agent mailbox telemetry is throttled to cut UI lag (#3454).
- YOLO background-shell approvals. A background shell command no longer pops an approval modal in YOLO mode. classify_risk marks all shell commands destructive, so the auto-review safety floor held every background shell for review, and the ForcePrompt site never checked auto_approve — only background commands surfaced it, since foreground shells take the Interactive origin and skip that branch.
- Bash approval modal fit. The shell approval modal now labels Bash commands directly, avoids repeating command/workdir in the impact summary, wraps long commands, and switches to compact controls on short terminals so the decision keys stay visible.
- Custom-provider picker rows. Concrete [providers.<name>] entries now appear in the provider picker (id, endpoint, auth readiness, wire protocol, current model) instead of only the generic placeholder; auth readiness honors per-entry key/env/metadata/no-auth/loopback.
- Passive MCP tool discovery. Runtime API-owned stdio MCP processes are no longer spawned from passive /v1/apps/mcp/tools requests; live discovery remains available through ?connect=true. doctor now warns on relative-path stdio MCP commands without cwd.

https://github.com/Hmbown/CodeWhale/blob/HEAD/CHANGELOG.md#0865---2026-06-24

Most popular in AI assistants & LLMs

See all
  1. Claude CodeUnleash Claude’s raw power directly in your terminal. Search million-line codebases instantly. Turn hours-long workflows into a single command. Your tools. Your workflow. Your codebase, evolving at thought speed.
  2. Codex CLICodex CLI is an open‑source local coding agent that runs in your terminal, letting you write, edit, and understand code without leaving the command line.
  3. ChatGPT by lencxChatGPT Desktop Application
  4. GPT4AllGPT4All is a GUI application for loading and interacting with Generative AI models
  5. JanTurn your computer into an AI computer
  6. oh-my-pi⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
  7. T3 CodeT3 Code is a minimal web GUI for coding agents.
  8. WSL ManagerA GUI to quickly manage your WSL2 instances.
  9. CC SwitchA cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode, openclaw & Gemini CLI.
  10. LobeHubAn open-source, modern-design AI chat framework. Supports Multi AI Providers (OpenAI / Claude 4 / Gemini / Ollama / DeepSeek / Qwen), Knowledge Base (file upload / knowledge management / RAG), Multi-Modals (Plugins/Artifacts) and Thinking.

More from Hunter Bown

See all
  • DeepSeek TUICoding agent for DeepSeek models that runs in your terminal

Tags

Share