Harvested from #2343 with thanks to @lucaszhu-hue.
Registers AtlasCloud static model rows for Pro and Flash resolution, adds provider-hinted alias coverage, and updates neutral provider docs and env examples while leaving promotional assets/copy out.
Harvested from #2393 with thanks to @wplll.
Strengthens the tool-result dedup regression coverage by exercising repeated medium-sized outputs that are above the dedup threshold but below the truncation budget.
Harvested from #2392 with thanks to @wplll.
Makes project context pack path ordering deterministic across Unix and Windows-style separators while keeping README/config/source entries prioritized before general directory noise.
Harvested from #2402 with thanks to @axobase001.
Keeps `allow_shell` guidance visible for gated shell tools even when missing-tool suggestions exist, removes the nonexistent task_shell_cancel matcher, and broadens regression coverage.
Partially addresses #2328.
Harvested from #2415 with thanks to @axobase001.
Keeps the denser mobile QR renderer and replaces the fixed binding-warning sleep with health polling plus an explicit timeout failure path, so slow starts fail with the useful cause instead of drifting into misleading assertions.
Follow-up to #2403.
Harvested from #2408 with thanks to @axobase001.
Adds regression coverage proving tty:true shell commands receive a controlling terminal, with a longer wait margin so the test is stable on slower CI hosts.
Partially addresses #2372.
Harvested from #2405 with thanks to @axobase001.\n\nCompacts the statusline token chip to use the short label while preserving the existing token detail and adding focused coverage for the rendered label.\n\nPartially addresses #2309.
Harvested from #2406 with thanks to @axobase001.
Adds auto-selected model and reasoning effort to turn metadata while keeping user text isolated in its own content block. Includes the comment cleanup requested in review.
Partially addresses #2380.
Harvested with thanks to @aboimpinto.
Includes the ExternalTool abstraction layer plus follow-up fixes for lossy REPL stdout handling and unquoted unicode git diff paths.
Validation included full CI and focused local checks for non-UTF8 REPL stdout, git_diff, and external_tool behavior.
* feat: add mobile smoke tests and QR code for mobile URL
#2396: Add scripts/mobile-smoke.sh that launches the compiled binary on
loopback ports and verifies the mobile surface through real HTTP requests:
- Token auth (401/200, Bearer, query param, approval 404)
- Insecure mode (no token required)
- Binding warnings (0.0.0.0, LAN URL hint)
Add mobile-smoke job to CI workflow.
#2397: Add --qr flag to 'codewhale serve --mobile' that renders a
terminal QR code for the mobile URL. Uses the LAN IP when available,
falls back to 127.0.0.1. Adds qrcode crate (pure Rust, no C deps).
* fix: address review feedback on mobile smoke tests
- Fix Test Group 3 subprocess capture: use temp file instead of command
substitution to avoid hanging and subshell variable isolation
- Allow BINARY path to be overridden via BINARY env var
- Add libdbus-1-dev system dependency to CI job for ubuntu build
* fix: pass auth header in mobile smoke status helper
* fix: send approval JSON in mobile smoke
---------
Co-authored-by: Hu Qiantao <huqiantao@HudeMacBook-Air.local>
Co-authored-by: Hunter B <hmbown@gmail.com>
* feat: add Claude theme — warm navy & coral palette
Add a new theme aligned with Claude Code's product surface colors:
deep navy surfaces (#181715), cream-tinted text (#faf9f5),
coral accent (#cc785c), and teal secondary (#5db8a6).
Includes cell-level remap pipeline registration and full
WCAG contrast QA compliance.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(theme): address review feedback on Claude theme
- Fix text_dim contrast: #615E58 → #72706A (2.77 → 3.62, passes WCAG AA)
- Fix error_fg/error_border contrast: #C64545 → #E06060 (3.70 → 5.13, passes AA)
- Use amber #E8A55A for accent_action (distinct from accent_primary coral)
- Fix theme_picker test expecting GruvboxDark as last theme
- Remove broken include_str!("../../../web-chat/index.html") reference
left by incomplete web-chat revert
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix: revert version bump, keep theme-only changes
---------
Co-authored-by: Hu Qiantao <huqiantao@HudeMacBook-Air.local>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: Hunter B <hmbown@gmail.com>
* fix(tui): init runtime log before EnterAlternateScreen, add Windows stderr redirect
Two root causes of verbose logging leaking into the TUI alt-screen:
1. EnterAlternateScreen was called BEFORE runtime_log::init(), so any
logging between alt-screen entry and redirect init leaked raw bytes
into the TUI buffer — causing the 'scroll demon' on all platforms.
2. redirect_stderr_to was #[cfg(unix)] only — Windows had no stderr
redirect at all, so every eprintln!/tracing call during the TUI
session wrote directly into the alt-screen buffer.
Fixes:
- Swap order: init runtime_log (with stderr redirect) BEFORE entering
the alt-screen, so the redirect is active from the start.
- Add #[cfg(windows)] redirect_stderr_to using SetStdHandle from the
already-available windows crate, with corresponding Drop impl to
restore the original handle.
Fixes#1909
* fix(tui): handle Windows stderr redirect API types
* docs(tui): update runtime log stderr redirect notes
* fix: propagate SetStdHandle error instead of using .context()
Use .map_err() with a descriptive message and cast target to isize
for the HANDLE constructor, so the error is properly propagated if
SetStdHandle fails.
Co-Authored-By: bot_apk <apk@cognition.ai>
* fix(tui): pass raw Windows stderr handle
* fix: use DuplicateHandle for Windows stderr redirect to avoid handle aliasing
The previous implementation used file.as_raw_handle() directly with
SetStdHandle, causing both _file and the process stderr table entry to
share the same HANDLE. If a third-party library called CloseHandle on
the stderr handle during the TUI session, it would silently invalidate
_file and cause a double-CloseHandle on guard drop.
Now we call DuplicateHandle before SetStdHandle to produce a truly
independent handle for the redirected stderr, mirroring the Unix path's
use of libc::dup. The duplicated handle is tracked in the guard struct
and properly closed on drop after the original stderr is restored.
Co-Authored-By: bot_apk <apk@cognition.ai>
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: bot_apk <apk@cognition.ai>
Merge current origin/main into #2257 and keep the rescue scoped to the balance statusline feature.
Credits #2257 by @HUQIANTAO and the carried #1970 balance work by @MoriTang.
The rescue gates startup, turn-complete, and provider-switch balance fetches on StatusItem::Balance, preserves current main Cargo metadata, and adds the missing Vietnamese balance label.
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.
When the model invokes write/modify/delete tools, extract its preceding
text content as an 'intent summary' and pass it to the approval view.
This gives users context about why a change is being made before they
review what will change.
Changes:
- Add intent_summary field to ApprovalRequired event (events.rs)
- Extract model text from current_text_visible when write tools
are detected in the turn loop (turn_loop.rs)
- Add ApprovalRequest::new_with_intent constructor with
intent_summary parameter (approval.rs)
- Pass intent_summary through TUI event handler to approval view
(ui.rs)
- Render intent summary in approval widget: up to 3 lines of the
model explanation, truncated to available card width, with
i18n labels for zh-Hans locale (widgets/mod.rs)
- Adapt existing tests to new event field (runtime_threads.rs,
ui/tests.rs)
Design decisions:
- Non-blocking: if the model provides no explanation, the approval
still proceeds normally (no extra round-trip or token cost)
- Backward compatible: YOLO mode and approval cache unaffected
- The new() constructor is gated behind #[cfg(test)] since
production code now uses new_with_intent()