Adds Moonshot/Kimi provider support with Kimi CLI OAuth reuse and review fixes for secure refresh writes, model completion, CLI auth, and secret-store behavior.
* 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>
Includes cancellable file_search/list_dir behavior, deterministic sub-agent whale-species nicknames, and an honest /balance command scaffold for the provider-billing work. Reviewed the overlapping file-search cancellation contribution in #2044 from @h3c-hexin; that PR's Windows failure was unrelated to the cancellation code, and the contributor context is preserved here.
- composer_history: raise deadline to 10s on Windows for writer thread
- prompts: make memory_guidance tier-order assertion CRLF-agnostic
- gitattributes: enforce LF line endings for include_str!() prompt files
Regression from the v0.8.44 release changes — the writer thread batching
and the updated constitutional tier ordering in memory_guidance.md both
uncovered Windows-only test flakes.
migrate_config_if_needed() copies config.toml on first launch.
Called in run_interactive after config creation. Non-fatal,
never overwrites an existing primary config.
#1981: DelegateCard now shows readable roles (scout, builder,
reviewer, etc.) instead of raw agent_type strings, and uses the
completion summary as the primary detail when available. Raw
agent_ids are truncated to 8 chars as secondary detail.
#834: PlanPromptView now renders the plan explanation and steps
(when update_plan was called) before the action options. Uses
PlanSnapshot from the shared plan state.
#1638: Session picker auto-opens on clean startup when saved
sessions exist and no --resume/--continue/--fresh was specified.
No new TuiOptions field needed — uses existing resume_session_id.
When the model is busy but not actively streaming text (waiting on
tool results, sub-agents, or shell commands), Enter now tries to steer
the message into the current turn rather than silently queueing it.
If steering fails, the message falls back to queuing.
During active streaming, Enter still queues to avoid interrupting
in-flight reasoning. Ctrl+Enter forces Steer in all busy states.
#1600: 'r' keybinding in session picker for inline rename.
Enter inline rename mode, type new title, Enter to confirm, Esc to cancel.
Updates the saved session metadata and refreshes the picker list.
#1787: checklist_write, checklist_update, update_plan now trigger
immediate Work sidebar refresh (previously only todo_write did).
npm install -g codewhale now also provides the codew command.
Calls run('codewhale') — same download-and-forward pattern as
the existing codewhale.js and codewhale-tui.js wrappers.
Permanent short-form shim — forwards silently to codewhale.
Six fewer keystrokes, no deprecation warning. Ships alongside
codewhale and the legacy deepseek alias.
- Doctor: add 'State Root' section showing active root, legacy status,
and dual-root detection
- Doctor (text + JSON): use codewhale_config resolver for config path
- deepseek_home_dir(): now resolves to CodeWhale home
- composer_stash: writes to ~/.codewhale/composer_stash.jsonl
- merge_project_config: checks .codewhale/ before .deepseek/
- Text/config paths default to .codewhale/ not .deepseek/
#2011: migrate app state to ~/.codewhale
- Add CodeWhalePaths: codewhale_home(), legacy_deepseek_home(),
resolve_state_dir(), ensure_state_dir() in codewhale-config
- Config: resolve_config_path supports CODEWHALE_CONFIG_PATH env,
default_config_path prefers ~/.codewhale/config.toml
- Project overlay: checks .codewhale/config.toml before .deepseek/
- Sessions: default_sessions_dir uses resolve_state_dir with fallback
- Workspace trust: writes to CodeWhale home via ensure_state_dir
- Init: ensure_deepseek_gitignored adds both .codewhale/ and .deepseek/
- .gitignore: adds .codewhale/
#2010: session artifact hygiene
- /save without path now writes to managed sessions dir instead of cwd
- Boot-time session prune via cleanup_old_sessions (MAX_SESSIONS=50)
- sessions_dir() public accessor for checkpoint path resolution
Fix: load_recent_checkpoint now uses manager.sessions_dir() instead
of hardcoding ~/.deepseek/sessions/checkpoints/
Restructured the homepage so "What it actually is" sits directly before
"100-to-1", putting the spine back-to-back. Cut the redundant "Open
model platform" section (duplicated the provider chip list), the
fabricated "34k+ Stars / 98+ Contributors" cells in the Join block
(now uses real version / providers / license from facts.generated),
defensive "DeepSeek is not deprecated" copy, the speculative Unsloth
roadmap line, the stale hardcoded 2026-05-24 eyebrow, the margin
glyph, and a couple of hero pills. Today's Dispatch moves below the
diagram as a single editorial column (the live ticker already covers
recent activity). Contribute page drops the arbitrary "Section 05"
eyebrow and the double-language h1; recursive-harness intro mirrors
the homepage spine. EN/ZH parity preserved (6 sections home, 5
contribute, identical CTA structure).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Fixes the macOS test failure on PR #1988 and the contributor-credit
gate from scripts/release/check-versions.sh.
cell_has_detail_target() was matching HistoryCell::Thinking, which
caused the activity footer to append " · ⌥+V raw" to thinking cells
that have no separate raw detail target. The detail-card flow only
exists for tool / sub-agent cells; thinking renders its own raw text
inline. Removing Thinking from the match arm restores the behavior the
existing
activity_footer_hint_surfaces_visible_thinking_without_raw_tool_hint
test asserts.
The CHANGELOG.md 0.8.43 section now credits the 30 contributors added
to README acknowledgements in this cycle, satisfying the README-vs-
CHANGELOG cross-check in check-versions.sh. crates/tui/CHANGELOG.md is
re-synced so the matching guard passes.
Verified locally on macOS:
- cargo fmt --all -- --check : clean
- cargo clippy --workspace --all-targets --all-features --locked -D warnings : clean
- cargo test --workspace --all-features --locked : 41 suites, 0 failed
- ./scripts/release/check-versions.sh : Version state OK
- ./scripts/release/publish-crates.sh dry-run : all 14 crates OK
- cargo build --release --locked : clean
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- npm/codewhale/README.md: remove DeepSeek-first language
- docs/INSTALL.md: scoop install codewhale (not deepseek-tui)
- Wire decision card overlay rendering in main render loop
- Decision cards now appear centered on transcript when active
Before the turn breaks at the thinking-only checkpoint, drain
any sub-agent completions that arrived between the last hold
check and now. If a child finished while we were running the
final status check, surface its sentinel immediately rather
than delaying it to the next turn.
- Thinking cells now qualify as detail targets alongside tools and sub-agents
- Space key on empty composer toggles the focused cell's collapsed state
- Status message confirms expand/collapse action
- Builds on existing collapsed_cells HashSet from mouse context menu
kitty