Separate model-native context metadata from provider-effective runtime capability so OpenAI API gpt-5.5 stays at its documented 1.05M window while the openai-codex OAuth route budgets preflight, recovery, capacity checks, prompt text, and TUI context indicators against the Codex-family 400K envelope.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Home hero (web/app/[locale]/page.tsx): multi-model, community-first,
'intent outranks everything' framing; replace DeepSeek-only positioning.
- Add 'See how it decides' section + thinking-trace.tsx: surfaces real
reasoning traces (Article II/V citations) paired with the decision each
produced — proof, not assertion, that the constitution operates.
- docs/CONTRIBUTORS.md: chronological collapsible bands (forward-track ->
recurring/historical -> v0.8.48). Rebuilt by byte-copying verified HEAD
content; handle diff confirms zero contributor drops.
- Localize README.zh-CN / ja-JP / vi to mirror the new English README
(multi-model, community-first, constitution in its own section, concise
Thanks linking to docs/CONTRIBUTORS.md).
Make agent_eval return a running projection by default so follow-up steering does not wait for child model calls. Keep checkpoint resume blocking by default unless block=false is explicit.
Teach /agent, /swarm, prompts, and docs to poll workers nonblocking and reserve block:true for deliberate terminal waits. Add Ctrl+S as a reliable queued-message send path before falling back to draft stash.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
State the v0.8.60 direction plainly: sub-agent is role and UX vocabulary, while durable detached work should use the fleet-backed worker lifecycle.
Document the current agent_open path as compatibility until retry, receipt, and ledger semantics are unified with Fleet.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Shorten the README around the product path, provider support, install flow, docs index, and community contribution entry points.
Move the long contributor credit ledger into docs/CONTRIBUTORS.md so public credit remains visible without overwhelming the README.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Document the portable SKILL.md compatibility boundary for Claude Code plugin bundles and keep /skill install from silently flattening plugin archives that carry multiple skills plus plugin.json runtime metadata.
Reported by @AiurArtanis in #2743.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds a compile-only JavaScript/TypeScript authoring path that extracts a JSON-compatible workflow({...}) object, lowers it to the existing WorkflowSpec IR, and runs the Rust validation gate before execution.
Includes a branch/reduce .workflow.js example and a short authoring design note comparing YAML/JSON, Starlark, JavaScript, and TypeScript. The compiler rejects effectful JavaScript constructs instead of executing workflow source as a second runtime.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Z.ai's current GLM-5.2 coding-agent docs confirm actual thinking efforts high and max, with ultracode mapped to max. Its Chat Completion API documents thinking.type, thinking.clear_thinking, and reasoning_content rather than a raw reasoning_effort scalar, so direct Z.ai requests now use the documented thinking object and preserve reasoning_content for coding-agent continuity.
Also accepts ultracode as a max-effort alias across settings, routing, and Responses mapping.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds Ctrl+P and Ctrl+N as Emacs-style alternatives for slash-command autocomplete navigation while keeping the global Ctrl+P file picker from stealing focus when the slash menu is open.
Harvested from PR #3196 by @1Git2Clone.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds a verifiable dogfood smoke that drives several concurrent exec-style
workers (three healthy + one injected-failure that emits an error event and
exits non-zero) through the real host adapter, asserting distinct terminal
pass/fail outcomes — no external services, no model calls, no codewhale binary.
Documents the automated CI smoke vs the manual `codewhale fleet run` path in
the dogfood spec, and is honest that the manager run-loop cutover to drive real
FleetExecutor workers is still in progress.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds docs/AGENT_RUNTIME.md: one headless runtime, three launchers (TUI turn,
`codewhale exec`, Agent Fleet); sub-agent == fleet worker == nested/launched run
of the same runtime; the isolation+events+compact-projection lag fix; the single
recursion axis; and the one event vocabulary. Answers #2972 (how much Claude
Code convergence): converge on shape (headless runtime, isolated sub-agents,
event-driven fanout, skills, receipts), keep CodeWhale branding + multi-provider
+ the local-first fleet distinct, and never fork execution semantics per surface.
Cross-linked from FLEET.md.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Refs #3163.
Adds the @codewhale/runtime-sdk workspace with typed fleet Runtime API helpers, protocol-shaped TypeScript declarations, JSON/SSE event fixture handling, and typed RuntimeCapabilityError failures for create/event-stream endpoints that the Rust API has not exposed yet.
Documents the SDK contract in docs/RUNTIME_API.md and wires npm workspace verification through npm test --workspace @codewhale/runtime-sdk.
Refs #1310.
Adds the direct minimax provider slot, auth/config/env bindings, model aliases, docs, and picker/status surfaces. MiniMax requests now set reasoning_split and preserve reasoning_details history so thinking stays out of answer text.
Also updates Moonshot/Kimi reasoning classification for the Kimi Code route so reasoning_content streams into Thinking cells instead of inline prose.
Harvests #3052 onto the v0.8.59 release branch. Noninteractive CLI launches default to concise output discipline unless config, env, or --verbosity overrides it; interactive TUI launches remain normal by default.
Also forwards CODEWHALE_VERBOSITY as the primary env bridge while keeping DEEPSEEK_VERBOSITY for compatibility, documents the setting, and records @cyq1017 credit in both changelogs.
Harvests PR #3013 by @cyq1017 and PR #3053 by @angus-guo. Legacy deepseek/deepseek-tui binaries now return migration steps instead of trying to self-update through a missing codewhale binary, and the README/rebrand docs carry the same upgrade path.
Co-authored-by: cyq1017 <61975706+cyq1017@users.noreply.github.com>
Co-authored-by: gus <217034332+angus-guo@users.noreply.github.com>
Harvests the explainability slice from PR #2971 without changing the public HookEvent constructor shape. Runtime API approval.required frames now carry matched_rule metadata when an execpolicy rule caused the prompt.
Co-authored-by: greyfreedom <11493871+greyfreedom@users.noreply.github.com>
Harvest #2895 for the v0.8.59 release lane. SiliconFlow CN now reads its own providers.siliconflow_cn / providers.siliconflow-CN table and falls back to providers.siliconflow only when api_key, base_url, or model are unset.
Maintainer amendments wire the TUI fallback paths, provider config get/set/unset/redaction surfaces, env override routing, model normalization, tests, and changelog credit.
Fixes#2893.
Reported-by: Artenx <18120598+Artenx@users.noreply.github.com>
Harvest #3009 for the v0.8.59 release lane. Adds a paired Terminal-Bench harness for CodeWhale and Codex, a Codex Harbor adapter, generated-result ignore protection, and benchmark docs.
Maintainer amendments keep explicit zero-valued metrics, regenerate parent task names, write refreshed summaries in regenerate mode, and allow transcript paths outside the repo.
Fixes#2952.
Hunter B