Refs #2569
Harvests the safe part of PR #2569 by allowing AtlasCloud provider-hinted namespaced model IDs to route exactly as requested, without freezing a volatile provider model catalog in the static registry.
Co-authored-by: lucaszhu-hue <lucas.zhu@atlascloud.ai>
Support `! <command>` and `!command` in the TUI composer to run shell commands through the existing exec_shell path.
The shortcut keeps normal approval, sandbox, policy, transcript, and work-panel handling, while avoiding model context
pollution from local-only tool results.
Refs #1546
- 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.
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.
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.
- Add env guard with process-global mutex for ALLOW_INSECURE_HTTP tests
- Document LAN vLLM HTTP example in README
- Add config test for reported LAN HTTP endpoint + model resolution
- Guard validate_base_url_security tests against env leak
- 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
Update all three READMEs (en, zh-CN, ja-JP) to use the canonical
~/.codewhale paths for config, skills, and Docker volume mounts, with
legacy ~/.deepseek noted as a compatibility fallback. The state-root
migration has been underway since v0.8.44 — the docs now reflect it.
Replace the dense 85-line 'What Is It' section with a tight 15-line
version using a three-column table:
- Start with trust — the 'A' preamble
- Clear jurisdiction — Constitution with nine tiers of authority
- Recursive improvement — V4 helps write the harness, loop tightens
All three languages (EN, zh-CN, ja-JP) updated. Contributors preserved.
Replace the feature-grid format with a narrative that leads with the
core problem the harness solves: conflicting information at scale.
Frame the Constitution as a formal jurisdiction framework (LLM-as-judge),
describe V4's prefix caching as what makes recursive constitutional
reference practical (open-book test, not closed-book), and explain that
the explicit authority structure enables honest failure feedback.
Cut: memory/handoffs (table stakes), /statusline chip (internal),
theme picker, desktop notifications (clutter).
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.
* 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>
- 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)
Hunter Bown