Commit Graph

2654 Commits

Author SHA1 Message Date
Hunter B efcf299712 feat(models): add Kimi K2.7 Code defaults 2026-06-12 05:43:38 -07:00
Hunter B de9a0131cf test(tools): avoid approximate constant lint 2026-06-12 05:36:15 -07:00
Hunter B 0986cabb1d feat(tui): add context source map report
Add an explicit /context report|json|summary source-map surface while preserving plain /context as the existing inspector.

Expose the same diagnostic map through doctor --context-json for headless checks. The report uses the existing compaction token heuristic and labels counts as conservative estimates rather than exact provider billing.

Modified harvest from PR #3150 by @idling11.

Co-authored-by: idling11 <8055620+idling11@users.noreply.github.com>
2026-06-12 03:20:59 -07:00
Hunter B 6e9baaa988 refactor(tui): group completion search state
Introduce a small SearchContext for workspace completion walks so the related search state moves together and the helper signatures no longer need too-many-arguments allowances.

Also keeps the nearby hotbar test clippy-clean under the all-targets TUI gate.

Modified harvest from PR #3128 by @Hmbown.

Co-authored-by: Hmbown <101357273+Hmbown@users.noreply.github.com>
2026-06-12 03:05:56 -07:00
Hunter B c95122fb43 chore(deps): update reqwest rustls and clap_complete
Updates the lockfile-only Dependabot PRs for reqwest 0.13.4, rustls 0.23.40, and clap_complete 4.6.5 while keeping unrelated resolver drift out of the release branch.

Refs #3001.

Refs #3002.

Refs #3003.
2026-06-12 03:01:16 -07:00
Hunter B 757ffefc46 test(tools,release): cover execution subjects and mirror URLs
Harvests focused coverage from #3114, #3116, #3124, and #3127.

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>

Co-authored-by: Hmbown <101357273+Hmbown@users.noreply.github.com>
2026-06-12 02:54:46 -07:00
Hunter B 1bb17cfced test(release,tools): extend helper coverage
Harvests focused coverage from #3110, #3111, #3113, #3123, #3125, and #3126.

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>

Co-authored-by: Hmbown <101357273+Hmbown@users.noreply.github.com>
2026-06-12 02:53:47 -07:00
Hunter B c766aab406 test(tools): cover missing field constructor
Harvests focused coverage from #3133.

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>

Co-authored-by: Hmbown <101357273+Hmbown@users.noreply.github.com>
2026-06-12 02:51:04 -07:00
Hunter B 936848f3a8 test(release): cover release channel query helpers
Harvests release helper coverage from #3130, #3131, #3132, and #3134 without adding a serial-test dependency.

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>

Co-authored-by: Hmbown <101357273+Hmbown@users.noreply.github.com>
2026-06-12 02:50:35 -07:00
Hunter B e27d63a55a chore(tui): remove unused prompt persistence module
Harvests the dead-code cleanup from #3135.

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>

Co-authored-by: Hmbown <101357273+Hmbown@users.noreply.github.com>
2026-06-12 02:48:57 -07:00
Hunter B f5104467db test(release): cover release base URL env overrides
Harvests the release URL coverage from #3137 without adding a serial-test dependency.

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>

Co-authored-by: Hmbown <101357273+Hmbown@users.noreply.github.com>
2026-06-12 02:46:01 -07:00
Hunter B 3aa7131ebf test(tools): cover ToolError constructors
Harvests focused coverage from #3136 and #3138.

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>

Co-authored-by: Hmbown <101357273+Hmbown@users.noreply.github.com>
2026-06-12 02:44:27 -07:00
Hunter B b1c94b3f02 perf(skills): sync registry entries concurrently
Use bounded ordered concurrency for /skills sync so registry downloads no longer serialize one skill at a time while preserving deterministic outcome order.

Harvested from PR #3139.

Co-authored-by: Hmbown <101357273+Hmbown@users.noreply.github.com>

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
2026-06-12 02:41:18 -07:00
Hunter B d50dfd4827 fix(hooks): require workspace trust for project hooks
Gate .codewhale/hooks.toml behind user-owned workspace trust, mirroring the project-local MCP trust boundary while preserving shell-command hook semantics.

Harvested from PR #3140.

Co-authored-by: Hmbown <101357273+Hmbown@users.noreply.github.com>

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
2026-06-12 02:38:56 -07:00
Hunter B 119285f056 fix(runtime): batch thread detail item reads
Avoid an N+1 item-directory scan when loading runtime thread details by grouping persisted items for all turns in one pass.

Harvested from PR #3141.

Co-authored-by: Hmbown <101357273+Hmbown@users.noreply.github.com>

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
2026-06-12 02:35:39 -07:00
Hunter B 2f717d3345 fix(tui): accept compact SSE data fields
Accept SSE data frames with either `data: {...}` or `data:{...}` in Chat Completions, Responses, and Anthropic stream readers.

Harvested from PR #3152.

Co-authored-by: wgeeker <169752135+wgeeker@users.noreply.github.com>
2026-06-12 02:31:31 -07:00
Hunter B c1a48492b6 fix(codex): keep Responses reasoning shape provider-native
Codex Responses requests now clamp legacy minimal effort to low and carry a regression test that the request body uses reasoning.effort without DeepSeek thinking or chat-completions reasoning_effort fields.
2026-06-12 02:27:59 -07:00
Hunter B 8c690cb7bf fix(update): guide legacy deepseek users to codewhale
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>
2026-06-12 02:22:10 -07:00
Hunter B 3de1d35c37 feat(tui): dispatch hotbar slots from number keys
Harvests PR #3056 by @reidliu41, keeping overlays in control of number keys, reclaiming Alt+1 through Alt+8 for hotbar dispatch, and updating the help/footer shortcut copy.

Co-authored-by: reidliu41 <61492567+reidliu41@users.noreply.github.com>
2026-06-12 02:19:15 -07:00
Hunter B 74a4a91204 feat(i18n): localize config editor labels
Harvests PR #2919 by @gordonlu, preserving Codex-aware reasoning effort display while localizing the config editor chrome and default placeholders.

Co-authored-by: gordonlu <3125629+gordonlu@users.noreply.github.com>
2026-06-12 02:12:58 -07:00
Hunter B b0b7317688 fix(tui): normalize Codex reasoning effort labels 2026-06-12 02:07:39 -07:00
Hunter B 6511de3359 feat(i18n): localize config section labels
Harvests PR #2918 by @gordonlu, preserving English search terms for localized config sections and scopes.

Co-authored-by: gordonlu <3125629+gordonlu@users.noreply.github.com>
2026-06-12 01:59:47 -07:00
Hunter B fb53dc1866 chore(tui): satisfy release clippy gate 2026-06-12 01:50:52 -07:00
Hunter B c9339a6abf test(i18n): cover remaining tool family labels
Adds the release-note credit for PR #2901 and extends the no-English-leak test to delegate, think, and generic tool labels.

Co-authored-by: gordonlu <3125629+gordonlu@users.noreply.github.com>
2026-06-12 01:49:16 -07:00
Hunter B 81b84f3f88 Merge PR #2901: localize ToolFamily labels 2026-06-12 01:47:27 -07:00
Hunter B 10e41b1153 feat(runtime): expose matched approval rule metadata
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>
2026-06-12 01:46:41 -07:00
Hunter B c16a32150e fix(tui): accept macOS command modifier for control shortcuts
Harvests the macOS shortcut fix from PR #2943 for the #2938 release lane, but scopes the SUPER-as-control mapping to the affected task/background and sidebar-focus shortcuts so Cmd+C/Cmd+V keep their existing platform behavior.

Co-authored-by: idling11 <8055620+idling11@users.noreply.github.com>
2026-06-12 01:43:10 -07:00
Hunter B 862cb2e394 fix(exec): preserve auto model handoff
Harvests the narrow CLI/TUI exec model propagation fix from PR #3148 while honoring the CodeWhale model env alias before the legacy DeepSeek model handoff.

Co-authored-by: hongchen1993 <269377208+hongchen1993@users.noreply.github.com>
2026-06-12 01:38:39 -07:00
Hunter B 18bbbed2db chore(release): sync TUI changelog slice 2026-06-12 01:35:04 -07:00
Hunter B d3d22339cc test(prompt): pin runtime prompt stand-still rule
Keep the #3061 runtime-policy wording covered so lone <runtime_prompt> turns remain explicitly barred from starting edits, shell commands, git commits, or sub-agent launches without user input.

Report-by: yekern <13691766+yekern@users.noreply.github.com>
2026-06-12 01:34:25 -07:00
Hunter B a46d9c012e fix(cli): track provider source for TUI fallback
Adapt PR #3011 so unsupported interactive providers report their actual source and config-sourced unsupported providers fall back to DeepSeek without forwarding a stale keyring secret.

Co-authored-by: cyq1017 <61975706+cyq1017@users.noreply.github.com>
2026-06-12 01:30:23 -07:00
cyq1017 0d4f2b6e73 docs(prompt): clarify Constitution trust framing
Harvest #3008 for the v0.8.59 release lane. The base prompt now clarifies that beginning with an A means baseline trust, not a literal response-format instruction.

Fixes #2950.
2026-06-12 01:23:42 -07:00
New2Niu bfdd26879e fix(cli): bound self-update HTTP waits
Harvest #3006 for the v0.8.59 release lane. The self-update HTTP client now uses a five-minute timeout so blocked or very slow GitHub release downloads fail instead of hanging indefinitely.
2026-06-12 01:22:26 -07:00
idling11 da943be7de fix(config): split SiliconFlow CN provider config
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>
2026-06-12 01:21:27 -07:00
idling11 0cd8bcde1b feat(bench): add CLI comparison harness
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.
2026-06-12 01:15:00 -07:00
Hunter B f99fff969a release: harden v0.8.59 readiness lane
Integrate the v0.8.59 release-readiness aggregate: command-boundary grouping, Responses schema hardening, Codex reasoning tiers, goal lifecycle/runtime sync, sub-agent stall guards, activity metadata rows, and provider metadata/auth fixes.

Credit surfaces are captured in the changelogs for Paulo, Nightt, yekern, and the Devin/Hunter integration work.

Co-authored-by: aboimpinto <1231687+aboimpinto@users.noreply.github.com>

Co-authored-by: nightt5879 <87569709+nightt5879@users.noreply.github.com>
2026-06-12 01:07:11 -07:00
Hunter B a9808cc111 fix: runtime-prompt stand-still guard and closed launch-gate handling (#3061/#3095)
Clarify in the frozen runtime policy reference that a lone <runtime_prompt>
tag must not trigger new tool/git/sub-agent work without user input or a
pending handoff.

Log and degrade gracefully when the interactive fanout semaphore is closed
instead of silently dropping backpressure.

Document v0.8.59 release spine in CHANGELOG [Unreleased].

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-11 19:43:05 -07:00
Hunter B e1a5f5c464 fix(tui): defensive mouse-report sanitizer and move provider-wait logging off render path
Strip SGR mouse coordinate tails even when mouse capture is disabled, covering
orphaned terminal reporting state after crashes or focus races (#3063/#3067).

Move provider-wait incident logging from footer render to the main tick loop
so stall diagnostics do not fire on every redraw (#3095 harvest note).

Co-authored-by: Hunter Bown <101357273+Hmbown@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-11 19:41:31 -07:00
Hunter Bown 385a07f32a feat(tui): queue interactive fanout launches behind a visible launch gate (#3095)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-06-11 19:41:20 -07:00
Hunter Bown e617e3e618 feat(tui): make provider wait observable with route, idle budget, and fanout preflight state
The >30s stall reason now reports provider/model and idle-vs-budget
seconds instead of a bare 'waiting for model', explicitly marks a
planned-but-unlaunched fanout as 0 running, and logs a once-per-turn
structured provider-wait incident when a fanout plan is pending.

Part of #3095

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-06-11 19:41:18 -07:00
Hunter Bown 8091513ebc fix(tui): emit interrupted sub-agent lifecycle event and reconcile stale running cards
API-timeout interruptions now publish MailboxMessage::Interrupted so
delegate/fanout cards leave the running state, and AgentList snapshot
reconciliation syncs any card slot that missed its terminal envelope.

Fixes #3080

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-06-11 19:41:00 -07:00
Claude 0181493c79 release: v0.8.58 — native Anthropic provider, hooks v2 JSON decisions, clickable sidebar, provider-aware subagent routing, model-fact prompt templating
Co-Authored-By: Claude <noreply@anthropic.com>
https://claude.ai/code/session_018zaP8vUfTAsrE38L6h6fw5
2026-06-10 23:06:44 -07:00
Hunter Bown ce39b111cd Merge PR #3054 from Hmbown: native Anthropic Messages API adapter
feat(client): native Anthropic Messages API adapter — cache_control, thinking blocks, tool streaming (#3014)
2026-06-10 22:46:01 -07:00
Claude d940b7821c Merge origin/main into v0.8.58-3014-anthropic-adapter — keep #3024 Moonshot/Ollama dialect arms plus the #3014 Anthropic native-shaping arms in all three reasoning tiers; keep the #3014 Anthropic capability early-return while honoring the #3023 removal of the Openai/Atlascloud/Moonshot one; union claude + bare-id max_output rows 2026-06-11 05:45:51 +00:00
Hunter Bown f87245ff5f Merge PR #3034 from Hmbown: constitution refactor, Codex fixes, sidebar improvements
v0.8.58: Constitution refactor, Codex fixes, sidebar improvements
2026-06-10 22:39:31 -07:00
Claude 06f49af69f Merge origin/main into v0.8.58-constitution — carry the #3025 model-fact placeholders ({context_window_note}/{subagent_economics}/{model_thinking_note}/{model_characteristics}) into constitution.md per the prompt-layer coordination note; union sidebar tests and add TaskPanelEntry.kind to #3028 test literals 2026-06-11 05:39:19 +00:00
Hunter Bown 5b47a2e3e0 Merge PR #3048 from Hmbown: parameterize model-specific facts in the base prompt
feat(prompts): parameterize model-specific facts — context window, pricing, thinking
2026-06-10 22:30:08 -07:00
Hunter Bown 186ebbb116 Merge PR #3050 from Hmbown: wire reasoning-effort for Atlascloud, Moonshot, Ollama dialects
fix(reasoning): wire reasoning-effort for Atlascloud, Moonshot, Ollama
2026-06-10 22:30:00 -07:00
Hunter Bown a6d5824cee Merge PR #3047 from Hmbown: model-based capability lookups for Moonshot/OpenAI/Atlascloud + bare-id registry rows
fix(providers): use model-based lookups for Moonshot/OpenAI/Atlascloud/Ollama capability
2026-06-10 22:29:52 -07:00
Hunter Bown 78ed3768bf Merge PR #3046 from Hmbown: add Moonshot/Kimi to reasoning-content provider and model gates
fix(reasoning): add Moonshot/Kimi to reasoning-content provider and model support
2026-06-10 22:29:44 -07:00