feat: RuntimeTool trait with go/ts/rust execution backends (#1822)#1
Open
aboimpinto wants to merge 129 commits into
Open
feat: RuntimeTool trait with go/ts/rust execution backends (#1822)#1aboimpinto wants to merge 129 commits into
aboimpinto wants to merge 129 commits into
Conversation
…osts On Linux, `arboard::Clipboard::new()` opens a blocking connect() to the X11 Unix socket. When no X server is running (headless, WSL2 without WSLg), the call hangs indefinitely. Because raw mode and the alternate screen are already active at that point, Ctrl+C no longer generates SIGINT and the event loop hasn't started yet — leaving the user with a blank screen and no way to exit. Move clipboard initialization from `ClipboardHandler::new()` (called synchronously during App construction) to a lazy `ensure_clipboard()` that runs on first read/write with a 500 ms timeout. If the X11 connection doesn't respond in time, the handler stays in fallback mode and `write_text` falls through to the existing OSC 52 / pbcopy / PowerShell paths.
…on Windows Only DEEPSEEK_LOG_LEVEL should gate verbose CLI output. RUST_LOG controls the tracing subscriber independently (file logging). On Windows stderr is not redirected to the log file, so coupling the two causes tracing log messages to leak into the TUI alt-screen, corrupting the display. Closes Hmbown#1774
…mbown#1714) The CLI --model handoff only exports DEEPSEEK_MODEL, which apply_env_overrides funneled into the DeepSeek-only root default_text_model slot. default_model() then treated it as a normalizable weak default and fell back to a DeepSeek/provider default for an unrecognized custom model on a non-DeepSeek provider, so e.g. --provider openai --model MiniMax-M2.7 silently sent a DeepSeek model to the endpoint. Route DEEPSEEK_MODEL into the active provider's model slot for non-DeepSeek providers (mirroring the existing OPENAI_MODEL branch), and return an explicit non-DeepSeek-alias model verbatim from default_model(). DeepSeek/DeepSeekCN behavior is unchanged. Adds a regression test next to openai_provider_accepts_custom_model_and_base_url. Refs Hmbown#1714, Hmbown#1739, Hmbown#1736.
Address gemini-code-assist review on PR Hmbown#1740 (MEDIUM, clarity): the non-DeepSeek else-branch match listed ApiProvider::Deepseek / DeepseekCN arms that are logically unreachable (handled by the if branch above). Collapse to a single 'Deepseek | DeepseekCN => unreachable!(...)' arm so the intent is explicit for future maintainers. No behavior change. Refs Hmbown#1714.
…rovider (Hmbown#1739) should_replay_reasoning_content_for_provider() returned false whenever provider_accepts_reasoning_content(provider) was false (true for ApiProvider::Openai) without checking the model. This single gate feeds both build_for_provider (include_reasoning) and sanitize_thinking_mode_messages, so a DeepSeek reasoning model on the generic openai provider (DeepSeek-compatible endpoint) had all reasoning_content stripped -> the DeepSeek thinking-mode API 400s ('reasoning_content in the thinking mode must be passed back'). This is the over-aggressive half of ac01b22 (fix Hmbown#1542). Gate the early return on the model too: !provider_accepts_reasoning_content(provider) && !requires_reasoning_content(model). Known DeepSeek reasoning models replay regardless of provider; genuine non-DeepSeek models on openai still strip (effort=off still wins). Hmbown#1542 not regressed (provider_accepts_reasoning_content untouched). Two pre-existing client.rs tests asserted the buggy case (deepseek-v4-pro on Openai -> dropped); retargeted to gpt-4o to preserve their Hmbown#1542 intent without encoding the bug. New positive/negative coverage in chat.rs. Refs Hmbown#1739, Hmbown#1694, Hmbown#1542, Hmbown#1736.
…Hmbown#1743) Address gemini-code-assist review on PR Hmbown#1743: - HIGH: should_replay_reasoning_content_for_provider was made model-aware in the previous commit, but handle_chat_completion_stream still computed is_reasoning_model = requires_reasoning_content(model) && provider_accepts_reasoning_content(provider). On the openai provider + a DeepSeek model that was false during SSE parsing, so reasoning tokens were stored as content (not reasoning_content) and the next request still 400'd -- the fix was incomplete. Extract is_reasoning_model_for_stream() and route the stream call site through it; add an equivalence test locking it to the replay predicate so the two paths can't drift. - MEDIUM: rename generic_openai_provider_drops_deepseek_reasoning_content -> generic_openai_provider_drops_reasoning_content_for_non_deepseek_models (now uses gpt-4o; old name was misleading). Non-DeepSeek models on any provider are unaffected (Hmbown#1542 not regressed). Refs Hmbown#1739, Hmbown#1694, Hmbown#1542.
…own#1727) When a model streams a turn with only a reasoning block (empty content, no tool_calls -- e.g. gpt-oss via ollama's harmony->OpenAI shim mapping to reasoning_content), has_sendable_assistant_content is false: the if-only persist branch was skipped, NO event was emitted, and the turn fell through to break. The UI spinner hung with no reply and no error. Add an else-if at the same persist site that, only on a clean end (tool_uses empty, turn_error.is_none(), not cancelled), warns and emits an Event::status notice telling the user the turn ended and they can retry. No assistant message is persisted (prior behavior preserved); no retry/re-prompt/placeholder policy is added (out of scope). Guard ordering extracted into a pure should_emit_thinking_only_status() helper with a unit test, matching the existing should_hold_turn_for_subagents style. Maintainer audit Hmbown#1736 confirms Hmbown#1727 is not shipped in v0.8.39 and release-blocking. Refs Hmbown#1727, Hmbown#1736.
…own#1742) Address gemini-code-assist review on PR Hmbown#1742 (MEDIUM): the status was emitted at the assistant-persist site, but the same turn can still CONTINUE for pending steers or sub-agent completions -- the user would see a spurious 'turn ended without output' notice immediately before the turn resumed. Capture thinking_only_no_sendable at the persist site (no emission there) and decide at the end of the tool_uses.is_empty() path, just before the terminal break -- reachable only when there were no pending steers, no sub-agent completions, and we were not holding for running children. Extend should_emit_thinking_only_status with steers_pending and holding_for_subagents (false if either), recomputed live at the decision point as defense-in-depth. Unit test updated with the two new no-emit cases. Refs Hmbown#1727.
…#1691) git commit -m "feat: complete sub-pages" failed on Windows with 'pathspec sub-pages" did not match' because the quoted -m message was split on spaces. Root cause is not a tokenizer bug: CommandSpec::shell() builds 'cmd /C "chcp 65001 >/dev/null & <command>"' and std::process::Command applies MSVCRT escaping (" -> \"); cmd.exe does not use MSVCRT parsing, so the quoting is destroyed and git receives feat:/complete/sub-pages" as separate pathspecs. The Unix sh -c path was already correct. Add a cfg-split push_shell_args() replacing cmd.args() at the 3 std spawn sites in shell.rs. On Windows, for the cmd /C <payload> shape only, pass /C and payload via CommandExt::raw_arg so the string reaches cmd.exe verbatim (as a terminal does); other programs keep normal escaping. Non-Windows is a faithful pass-through (byte-for-byte unchanged). portable_pty path intentionally untouched (out of scope). The Unix path is provably unchanged (tested); the Windows raw_arg runtime correctness is only verifiable on a Windows runner -- flagged in the PR for Windows CI verification per the Hmbown#1736 Windows policy. Refs Hmbown#1691, Hmbown#1736.
…bown#1744) Address gemini-code-assist review on PR Hmbown#1744 (two MEDIUM): - cmd detection used program.eq_ignore_ascii_case("cmd"), which fails for a full path (C:\Windows\System32\cmd.exe) or a .exe suffix, so the raw_arg quoting fix would not apply. Use Path::file_stem() instead (fully-qualified std::path::Path -> no unused import off-Windows). - Strengthen the Windows block of issue_1691_quoted_commit_message_round_trips to assert argv content equals spec.args, not just arg count, so the raw_arg payload (quotes preserved, no extra escaping) is actually verified. sandbox/mod.rs already asserts content -- left untouched. Windows paths are cfg-gated (compile-checked on macOS, executed on Windows CI). macOS build + clippy clean. Refs Hmbown#1691.
Plain Home and End now navigate within the current line instead of jumping to the absolute start/end of the entire input. Ctrl+A and Ctrl+E remain as absolute start/end shortcuts. - Add move_cursor_line_start() / move_cursor_line_end() to App - Wire Home -> move_cursor_line_start(), End -> move_cursor_line_end() - On single-line input the new methods behave identically to the absolute versions (no behaviour change) - End on a newline character skips to the end of the next line - 14 tests covering multiline, singleline, and edge cases
Per gemini-code-assist review on Hmbown#1749: End on a newline character should stay at the end of the current line (idempotent), not skip to the next line. Removes the non-standard skip-past-newline logic and updates the associated tests.
…ll reasons, decision cards
- 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
…wn#1961) 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.
- 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
…ntributors Fixes the macOS test failure on PR Hmbown#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>
release: prepare v0.8.43
… on Linux parity check
aboimpinto
force-pushed
the
feat/runtime-tool-pr
branch
6 times, most recently
from
1b28185 to
c7003fa
Compare
Adds RuntimeTool trait shared across all execution backends and the dotnet_execution tool for running C# scripts via .NET SDK.
aboimpinto
force-pushed
the
feat/runtime-tool-pr
branch
from
fed6b95 to
7778736
Compare
Adds RuntimeTool trait shared across all execution backends and the dotnet_execution tool for running C# scripts via .NET SDK.
aboimpinto
force-pushed
the
feat/runtime-tool-pr
branch
from
b8c2420 to
96554bd
Compare
aboimpinto
force-pushed
the
feat/runtime-tool-pr
branch
2 times, most recently
from
25ce4f5 to
e90621d
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
7 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds the RuntimeTool trait and three new code-execution backends: go_execution, ts_execution, and rust_execution.
Changes
ustc\ compile-then-run with secure temp directories
Testing
All four runtimes produce identical output for the same cross-runtime test (github_repo_info):
Depends on
Closes Hmbown#1822