Commit Graph

117 Commits

Author SHA1 Message Date
Hunter B 13cabac077 docs(config): clarify provider path suffix support
Records that #2506/#2508 are superseded by the safer #2558 path_suffix implementation, credits the original #1874 report and follow-up PR review trail, and documents that suffix overrides only affect chat completions while model and beta paths keep built-in routing.
2026-06-03 23:56:40 -07:00
Hunter Bown fc8ad7b3a8 feat(project): enrich repo constitution (invariants, branch policy, escalation)
Per the layered-authority clarification (base myth → global Constitution → repo
constitution = local law → task packet → runtime policy), extend
.codewhale/constitution.json beyond authority+verification with optional:

- protected_invariants — repo invariants the agent must not break
- branch_policy — branch/release policy in effect
- escalate_when — conditions to stop and escalate to the user

All optional; rendered as concise model-facing prose. The global Brother Whale
identity anchor and Constitution in prompts/base.md are unchanged (verified
untouched on this branch). Dogfood constitution.json filled with CodeWhale's
real invariants (prefix-cache byte-stability, transcript replay, stable Rust,
cli/tui parity), branch policy (codex/v0.8.53), and escalation rules. Docs note
the layered hierarchy.

cargo test -p codewhale-tui --bins → 3946 passed; clippy clean.
2026-06-03 12:16:06 -07:00
Hunter Bown 9d9616e898 feat(project): deprecate WHALE.md; add .codewhale/constitution.json authority layer
Splits repo-level guidance into two clear artifacts and deprecates the
confusing WHALE.md concept (overlapped with AGENTS.md):

- AGENTS.md is the canonical cross-agent project-instructions file.
- .codewhale/constitution.json is the CodeWhale-specific repo authority /
  prioritization policy (when local sources conflict, which to trust first; what
  to verify before claiming done). Rendered into the system prompt as a
  higher-authority <codewhale_repo_constitution> block; takes precedence over a
  legacy WHALE.md.

WHALE.md migration (compat-preserving):
- AGENTS.md now ranks above WHALE.md in both project and global discovery; with
  both present, AGENTS.md wins.
- WHALE.md is still read as a legacy fallback, but now emits a deprecation
  warning and is never created or recommended (init.rs no longer suggests it).
- Discovery/docs updated; the global CodeWhale Constitution in prompts/base.md
  is unaffected (different thing).

constitution.json:
- New RepoConstitution (serde, all fields optional, unknown fields ignored,
  schema_version checked). Discovered at .codewhale/constitution.json in the
  workspace or any parent up to the git root. Malformed JSON warns, never panics.
- Loaded after the auto-generate fallback so it can't be clobbered.

.gitignore: ignore .codewhale/ contents at any depth EXCEPT the committed
constitution.json (a directory exclude can't be negated, so **/.codewhale/* +
negation). init.rs writes the same pattern for new repos. Dogfood: this repo's
.codewhale/constitution.json added.

find_git_root made pub(crate) and reused (no duplicate loader).

Tests: AGENTS-over-WHALE precedence, WHALE legacy-read-with-warning,
constitution render + system-block surfacing, malformed-constitution warning,
gitignore-keeps-constitution. cargo test -p codewhale-tui --bins → 3946 passed;
clippy clean.

Targets codex/v0.8.53.
2026-06-03 12:12:34 -07:00
Hunter B 14c882be53 fix(provider): expose siliconflow-cn registry coverage 2026-06-03 02:51:42 -07:00
Hunter B 54446e6c07 fix(release): stabilize v0.8.52 2026-06-03 02:39:45 -07:00
AresNing 8981d5c5fd feat: add subagent lifecycle hooks
Add subagent lifecycle hooks for better control over subagent initialization and teardown.
2026-06-02 20:48:09 -07:00
Hunter Bown 06612495fc chore(release): prep v0.8.51 — Arcee provider, cycle removal, UI fixes
Release-preparation checkpoint for v0.8.51 (workspace + npm bumped to 0.8.51).

Added:
- Arcee AI direct provider: [providers.arcee], ARCEE_API_KEY/BASE_URL/MODEL,
  CLI auth, provider + model picker, registry. Default direct-API model is
  trinity-large-thinking (reasoning, 262K ctx/out); preview + mini selectable.
  Cloudflare-WAF-safe opening turn (benign read-only tool surface, system-prompt
  payload splitting) and reasoning_content replay on tool-call turns.
- Expanded model catalog (qwen3.6 flash/plus/max-preview, Xiaomi MiMo v2.5
  chat/ASR/TTS); provider-aware model picker with per-provider saved models.

Changed:
- Auto-compaction is percentage- and model-aware
  (compaction_threshold_for_model_at_percent; default 80%; auto-enable for
  <=256K windows, opt-in for 1M models).
- Provider/gateway HTTP errors sanitized (HTML/WAF interstitials collapsed,
  401/403 split into authentication vs authorization).

Removed:
- The session cycle / checkpoint-restart system: /cycles, /cycle, /recall,
  recall_archive tool, cycle_manager, cycle-handoff prompt, sidebar cycle lines,
  EngineConfig.cycle / Event::CycleAdvanced / seam cycle thresholds.

Fixed:
- Orphaned assistant 'blue dot' role glyph on whitespace-only turns.
- Sidebar mouse-wheel scroll leaking into the transcript.
- Sidebar hover tooltip overlap + warning-orange styling.
- README Constitution description corrected to match prompts/base.md.
- Repaired release-blocking unit/integration tests after the refactors.

Preflight: cargo fmt clean, workspace builds, 3903 tui tests pass (1 known
flaky MCP SSE test under parallel load, passes in isolation).
2026-06-02 17:36:18 -07:00
Hunter B e54a0a500b feat(provider): add direct arcee support 2026-06-02 08:51:39 -07:00
cyq 73cd721665 feat(tui): add mention browser completions 2026-06-01 17:33:41 -07:00
cyq 3b5727f283 fix(tui): prefer codewhale settings path 2026-06-01 16:17:43 -07:00
Hunter Bown 3d5edfee80 test(config): cover legacy workspace shell opt-in
Refs #2523
2026-06-01 15:30:47 -07:00
cyq 7dfec0ed4a fix(config): honor workspace shell opt-in 2026-06-01 15:30:14 -07:00
Hunter Bown bb64018a15 feat(tui): add configurable auto-compact threshold
Refs #1722

Preserves auto_compact as opt-in, adds the saved threshold setting, keeps the 500K hard floor, and wires Ctrl+L as a manual compaction shortcut for context-pressure recovery.

Harvested from PR #1723 by @aboimpinto

Co-authored-by: Paulo Aboim Pinto <aboimpinto@gmail.com>
2026-06-01 14:09:49 -07:00
greyfreedom 3df018994f feat(config): load typed ask permissions file
(cherry picked from commit fb77cf1e0946a061376e5e9a8fc9422dddd98419)
2026-06-01 05:43:26 -07:00
Hunter B e9eea70445 release: v0.8.48 — liveness watchdog fix, Qwen 3.7 removal, provider/docs sync
- Fix false 'Turn stalled' during long active turns with running tools.
  Add turn_last_activity_at tracking and active-tool awareness to
  reconcile_turn_liveness(). Three new tests cover the fix.

- Remove Qwen 3.7 Max OpenRouter preset from registry, picker, docs,
  and tests. Qwen 3.7 Max is a hosted model; the preset will return
  when an open-weight Qwen 3.7 release ships. MiniMax M3 remains as
  a full 1M-context multimodal route.

- Sync root CHANGELOG to crates/tui/CHANGELOG for crates.io packaging.
  Update docs/CONFIGURATION.md, docs/PROVIDERS.md, and README to
  reflect the Qwen 3.7 removal. Regenerate web facts timestamp.
2026-05-31 21:45:31 -07:00
Hunter B 2bd77edc15 Fix provider model selection and stream completion 2026-05-31 21:15:40 -07:00
Hunter B 2b69f4e041 chore: polish codewhale home defaults 2026-05-31 19:22:12 -07:00
Hunter B a9a4213d39 fix(tui): make startup update checks configurable 2026-05-31 17:06:20 -07:00
Hunter B d6baf20721 Migrate file secrets to codewhale home 2026-05-31 15:30:35 -07:00
Hunter B f72f609293 feat: make file mention completion tunable 2026-05-31 13:29:28 -07:00
Hunter Bown 5a80556eb2 feat(models): add recent large OpenRouter models (#2461) 2026-05-31 11:26:25 -07:00
ningjingkun 4146ec617e fix(hooks): harden message_submit review cases 2026-05-31 04:39:51 -07:00
ningjingkun 467e2cbfff feat(hooks): allow message_submit to transform submitted text 2026-05-31 04:39:51 -07:00
Hunter Bown 26e2de86f0 docs: align configuration paths with codewhale home (#2413)
Harvested from #2400 with thanks to @axobase001.\n\nAligns the configuration docs around CODEWHALE_HOME while preserving the DEEPSEEK_HOME legacy alias and spelling out how legacy checkpoints can still be scanned during cleanup.\n\nCloses #2322.
2026-05-31 02:39:53 -07:00
Lee-take 4861bb2797 Add SiliconFlow provider support
Add SiliconFlow as an additive OpenAI-compatible hosted provider across config, secrets, CLI, agent registry, TUI runtime, picker, and docs.

Credit: based in part on the SiliconFlow provider direction from #1864 by @qychen2001, extended here with broader registry, documentation, and test coverage on current main.
2026-05-31 00:00:38 -07:00
Hunter B 12c9cd4193 Merge main into Baidu search provider 2026-05-30 22:39:13 -07:00
AdityaG 3f4c4496f2 feat: add Xiaomi MiMo provider
Adds native xiaomi-mimo provider configuration, auth/env aliases, model registry entries, TUI request handling, tests, and docs. Keeps credentials in existing provider-scoped config/env/keyring paths and uses placeholders only in docs.
2026-05-30 22:16:01 -07:00
jimmyzhuu e227efbd80 docs: document baidu search backend 2026-05-30 10:52:27 +08:00
Hunter Bown cdec3e8192 Merge branch 'build/v0.8.47' into integration/v0.8.47-unified 2026-05-26 16:41:10 -05:00
Hunter Bown 7cbeb3d809 Merge branch 'work/issue-2132-ddg-default' into integration/v0.8.47-unified 2026-05-26 16:40:53 -05:00
Hunter Bown aeaf91d589 feat(web_search): switch default backend from Bing to DuckDuckGo (#2132)
- Make DuckDuckGo the default search provider with Bing fallback
- Update tool description, config docs, TOOL_SURFACE, doctor output
- Update all search default tests and references
- Bing remains selectable via [search] provider = "bing"
2026-05-26 16:37:53 -05:00
Hunter Bown 2b8f3bf3dd docs: add provider registry reference and refresh provider lists (#2201)
- Add docs/PROVIDERS.md placeholder reference in README and CONFIGURATION.md
- Update provider lists to include moonshot, openrouter, novita
- Add MOONSHOT_API_KEY/KIMI_API_KEY env var docs
- Update default_text_model entries for all providers
- Change legacy deepseek-cn alias to deepseek
- Add CODEWHALE_PROVIDER as preferred env var name
2026-05-26 16:37:33 -05:00
Hunter Bown 236ad4137d feat: harvest 6 community PRs for v0.8.47
Harvested and vetted — no malware, no external deps, no injection:
- #1859 (@harvey2011888): loop guard now reports Failed on halt
- #1870 (@victorcheng2333): honour DEEPSEEK_YOLO env on startup
- #1935 (@IIzzaya): replace [x] with [✓] completion markers
- #1837 (@PurplePulse): fix macOS title centering (pin to top)
- #1967 (@cyq1017): show base_url in /config view
- #1906 (@knqiufan): copy transcript without visual-wrap newlines

Also fix cycle_manager archive_dir_for to use resolve_state_dir
so recall_archive tests pass with the migrated sessions path.

Co-authored-by: victorcheng2333 <victorcheng2333@users.noreply.github.com>
Co-authored-by: IIzzaya <IIzzaya@users.noreply.github.com>
Co-authored-by: PurplePulse <PurplePulse@users.noreply.github.com>
Co-authored-by: cyq1017 <cyq1017@users.noreply.github.com>
Co-authored-by: knqiufan <knqiufan@users.noreply.github.com>
2026-05-26 14:34:21 -05:00
Zhao Xiaohong ee03d1fd80 feat(web): add Metaso as a web search provider (metaso.cn) (#2059)
Adds Metaso AI Search as a new SearchProvider option alongside Bing,
DuckDuckGo, Tavily, and Bocha.

Co-authored-by: Zhao Xiaohong <zhaoxiaohong@metasota.ai>
2026-05-26 10:31:09 -05:00
Hunter Bown 2a41102e0c feat: defer low-value native tools by default, reduce catalog tokens 73% (#2076) 2026-05-26 10:08:09 -05:00
Hunter Bown c47ed896dc fix: DeepSeek-first v0.8.45 — CODEWHALE_* env aliases, remove public Kimi/Moonshot promotion
Closes #2164 (superseded).
2026-05-26 06:03:10 -05:00
Hunter Bown 228372935e chore(release): prepare v0.8.45
Harvested from PR #2118 by @Hmbown.

Includes Kimi/Moonshot OAuth, v0.8.45 release prep, the Codex/ChatGPT OAuth removal, open-source-first model defaults, and the safe green PR batch merged into main before the release branch refresh.
2026-05-25 18:45:36 -05:00
Hunter Bown a6bd5ac08b v0.8.45: add voice input, RLM session objects, and slash recovery fix (#2047)
* feat(tui): add command palette voice input

* feat(rlm): expose active session objects

* fix(tui): do not restore slash commands as retry drafts

* fix(config): expose voice input settings rows

* fix: sync ActiveTurnState.auto_approve when remember is set

When a user checks 'Remember for this tool' and approves a tool call,
remember_thread_auto_approve() only persisted thread.auto_approve to disk
but did not update the in-memory ActiveTurnState for the current turn.
This meant subsequent tool calls within the same turn would still require
manual approval, making the remember checkbox appear non-functional.

Now remember_thread_auto_approve() also sets
ActiveTurnState.auto_approve = true, so active_turn_flags() returns
the correct value and the approval_decision() logic auto-approves
remaining tool calls in the current turn.

(cherry picked from commit 2ccf048c8984d61e3341a4304d0796a1f965d3e7)

* test(runtime): cover remembered auto approve on active turn

---------

Co-authored-by: Ben Gao <bengao168@msn.com>
2026-05-24 22:19:50 -05:00
Hunter Bown 8a0c875d75 docs: clarify Fin and model auto-routing
- Separate model auto-routing from Plan/Agent/YOLO TUI modes across all
  READMEs and docs/MODES.md
- Introduce Fin as the fast thinking-off deepseek-v4-flash seam for
  routing, summaries, RLM child calls, and coordination work
- Document /goal as current session tracking (not a TUI mode), with note
  that a future Goal work surface should stay distinct from --model auto
- Extend deprecation shim timeline from 'one release cycle' to
  through v0.8.x in REBRAND.md and npm READMEs
- Fix selection_to_text test to expect inline thinking preview
  (short completed thinking now renders inline without Ctrl+O
  affordance)
2026-05-24 00:37:53 -05:00
Hunter Bown a3acdbe70b docs(brand): rename to codewhale across READMEs and docs
Sweep brand mentions of `DeepSeek TUI` / `deepseek-tui` / bare
`deepseek` (the dispatcher binary) across all user-facing docs to
the new `codewhale` brand. The DeepSeek **provider** integration is
left untouched throughout: env vars (`DEEPSEEK_*`), model IDs
(`deepseek-v4-pro`, `deepseek-v4-flash`, `deepseek-chat`,
`deepseek-reasoner`), the `api.deepseek.com` host, the
`~/.deepseek/` config dir, and the `--provider deepseek` argument
value all keep the legacy spelling.

Anti-scope items deliberately left as the legacy `deepseek-tui`:

- Homebrew tap and formula (`Hmbown/homebrew-deepseek-tui`,
  `brew install deepseek-tui`, `scoop install deepseek-tui`). The
  tap rename ships separately.
- Docker image (`ghcr.io/hmbown/deepseek-tui`). Image-tag rename
  ships separately.
- CNB mirror namespace (`cnb.cool/deepseek-tui.com/DeepSeek-TUI`).
  Third-party hosted path.
- Security contact email (`security@deepseek-tui.com`).
- GitHub repo URL (`Hmbown/DeepSeek-TUI`).

New artifact:

- `docs/REBRAND.md` documents what changed, what didn't, the
  deprecation window, and migration commands for npm / Cargo /
  Homebrew / manual installs.

CHANGELOG entries:

- Root `CHANGELOG.md` and `crates/tui/CHANGELOG.md` both gain a
  new `[Unreleased]` section describing the rename and the one-
  release deprecation window. Historical entries are untouched.

Issue templates:

- `.github/ISSUE_TEMPLATE/bug_report.md` and `feature_request.md`
  refer to "codewhale" / `codewhale --version` instead of the old
  brand name in their environment fields.

The rebrand sweep was driven by a perl script with bulk patterns
(`deepseek-tui` -> `codewhale-tui`, `DeepSeek TUI` -> `codewhale`,
bare `deepseek` -> `codewhale` with provider/model/host/env-var/
config-path negative lookbehind/lookahead) followed by targeted
reverts for the anti-scope items above. Output was visually
reviewed file-by-file before committing.

Verified:

- `cargo check --workspace --all-targets --locked` — pass.
- `cargo test --workspace --all-features --locked` — pass (no
  test source touched here; suite stayed green to confirm no
  doc-from-string assertions broke).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-23 11:25:48 -05:00
Hunter Bown ad122fd6f8 feat(subagents): make step API timeout configurable 2026-05-21 00:45:04 +08:00
Hunter Bown 8597afc076 feat(provider): add Wanjie Ark support 2026-05-21 00:02:02 +08:00
Hunter Bown a3f88bf6cf fix(search): default web search to bing (#1619)
Summary:
- add Bing as explicit default web_search provider
- keep explicit DuckDuckGo configuration supported
- update docs/help/config examples

Validation: CI green before merge.
2026-05-14 03:31:15 -05:00
Hunter Bown d5c45d962d chore(release): prepare v0.8.36
Squash merge of work/v0.8.36-cache-hygiene into main.

All preflight gates passed: version-drift/check/lint/test (3073 pass, 0 fail) / CodeQL / GitGuardian / npm-smoke. Preparing the v0.8.36 release tag.
2026-05-14 00:31:18 -05:00
Hunter Bown 1af37e3fab Add DeepSeek-native bundled workflow skills 2026-05-13 00:53:44 -05:00
Hunter Bown ccfece77e3 Merge remote-tracking branch 'origin/pr/1534' into work/v0.8.34
# Conflicts:
#	crates/tui/src/commands/config.rs
#	crates/tui/src/commands/mod.rs
#	crates/tui/src/palette.rs
#	crates/tui/src/settings.rs
#	crates/tui/src/tui/app.rs
#	crates/tui/src/tui/color_compat.rs
#	crates/tui/src/tui/widgets/footer.rs
2026-05-12 23:58:39 -05:00
Hunter Bown a4637fe7d1 fix(settings): reduce motion in VTE flicker terminals
Harvested from PR #1527 by @axobase001.

Co-authored-by: axobase001 <dengzhuoran9@gmail.com>
2026-05-12 23:39:44 -05:00
Hunter Bown 485ba7bbd4 chore(release): finish v0.8.33 polish 2026-05-12 22:03:47 -05:00
Hunter Bown 99c6b22e83 chore(release): v0.8.33 — sub-agent and RLM renovation with persistent sessions
- Persistent RLM sessions (rlm_open/rlm_eval/rlm_close) with bounded REPL helpers
- Fork-aware sub-agent sessions (agent_open/agent_eval/agent_close) with handle_read
- Shared handle_read storage with slice/range/count/JSONPath projections
- Slash-command routing: /rlm, /agent, /relay (/接力) for handoff prompts
- Sidebar renamed to "Work" tab, consistent across Plan/Agent/YOLO modes
- Tool papercuts: file_search excludes, grep_files strings, fetch_url JSON,
  edit_file fuzz, exec_shell merged stdout/stderr, revert_turn no-op reject
- CLI reasoning-effort honoured on non-auto exec routes (#1511 @h3c-hexin)
- Edit-file replacement boundaries clarified (#1516)
- Pandoc output validated before probing (#1523)
- Running turns steerable/repaintable (#1533, #1537)
- Tasks/Activity Detail calmer under load
- npm retry timeout hint (#1538 @reidliu41)
- Issue templates improved (#1525 @reidliu41)
- Shell: kill process group to prevent UI freeze (#828 @CrepuscularIRIS)
- TUI: ignore leaked SGR mouse reports in composer (#1421 @reidliu41)
- Footer: keep chips within available width (#1417 @Wenjunyun123)
- Session picker: scope Ctrl+R to current workspace (#1395 @LinQ)
- Removed stale competitive-analysis doc
- Prompts/docs teach only new tool names
2026-05-12 19:54:08 -05:00
Hunter Bown 8f33e4bd48 feat(providers): add AtlasCloud as a first-class provider
AtlasCloud (https://atlascloud.ai) hosts the V4 family on its own
DeepSeek-compatible endpoint at `https://api.atlascloud.ai/v1`, and
several contributors had been running it through the
OpenAI-compatible passthrough with manual `base_url` / model
overrides. Selecting `provider = "atlascloud"` in
`~/.deepseek/config.toml` (or via `DEEPSEEK_PROVIDER=atlascloud`)
now wires up:

- documented `DEFAULT_ATLASCLOUD_BASE_URL` /
  `DEFAULT_ATLASCLOUD_MODEL` defaults so a fresh install needs
  only the api_key
- a `[providers.atlascloud]` config block with the same fields
  every other named provider exposes (api_key / base_url / model
  / http_headers)
- `ATLASCLOUD_API_KEY` env var path, including the secrets test
  cleanup loop so per-test env hygiene continues to work
- the provider-picker / `/provider` slash command entries so the
  provider is reachable from the runtime UI, not just config
- the env-driven `*_BASE_URL` override branch so users who pin a
  proxy can still flip it without editing config.toml

Trust-boundary pins held: AtlasCloud is opt-in (default remains
DeepSeek), no API keys are hardcoded, the api_key resolution flows
through the same `secrets` crate path every other provider uses,
and the provider-config base_url stays settable per environment.

Resolved 3-way merge conflicts in `crates/secrets/src/lib.rs` (env
cleanup loop) and `crates/tui/src/config.rs` (per-provider
base_url match arm + `provider_passes_model_through` predicate)
so the contributor's AtlasCloud branch coexists with the v0.8.x
provider expansion already on `main`. Added the missing match arm
in `validate_provider_base_url` so the non-exhaustive-pattern
check passes after the new variant lands.

Harvested from PR #1436 by @lucaszhu-hue

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-12 00:40:43 -05:00