Pick up 5 low-risk upstream fixes (post-1e92490)#18
Merged
Conversation
…ling through to LLM (ultraworkers#2994) claw permissions list / claw permissions allow <tool> / claw permissions deny <tool> all fell through to the prompt/LLM path because parse_subcommand had no arm for "permissions". The single-word bare form was already intercepted by bare_slash_command_guidance, but any form with rest.len() > 1 bypassed the single-word guard and landed in the _other => CliAction::Prompt branch. Fix: add a "permissions" arm in parse_subcommand that returns a structured guidance Err so all multi-word forms get the same exit:1 + JSON error as the bare single-word form, without any LLM call or session creation. Verified: all invocation forms (bare, list, read-only, workspace-write, allow/deny <tool>) exit 1 with kind:unknown guidance JSON. Zero sessions.
… thinking blocks Five interrelated fixes from parallel Hephaestus sessions: 1. fix(repl): display assistant text after spinner (ultraworkers#2981, ultraworkers#2982, ultraworkers#2937) - Added final_assistant_text() call after run_turn spinner completes - REPL now shows response text like run_prompt_json does 2. fix(compact): handle Thinking content blocks (ultraworkers#2985) - Added ContentBlock::Thinking variant throughout compact summarizer - Prevents panic when /compact encounters thinking blocks 3. fix(prompt): provider-aware model identity (ultraworkers#2822) - New ModelFamilyIdentity enum (Claude vs Generic) - Non-Anthropic models no longer say 'I am Claude' - model_family_identity_for() detects provider and sets identity 4. fix(openai): preserve DeepSeek reasoning_content (ultraworkers#2821) - Stream parser now captures reasoning_content from OpenAI-compat - Emits ThinkingDelta/SignatureDelta events for reasoning models - Thinking blocks included in conversation history for re-send 5. feat(runtime): Thinking block support across codebase - AssistantEvent::Thinking variant in conversation.rs - ContentBlock::Thinking in session serialization - Thinking-aware compact summarization - Tests for thinking block ordering and content Closes ultraworkers#2981, ultraworkers#2982, ultraworkers#2937, ultraworkers#2985, ultraworkers#2822, ultraworkers#2821
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
3 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
Cherry-picks 5 low-risk upstream commits from
ultraworkers/claw-codeagainst the merge-basea389f8d. Selected for clean conflict-free merging and value to this fork; avoided the moderate-risk6db68a2(worker_boot.rs +319 lines) which deserves an isolated diff review first.6cc5f32fix(permissions): return guidance for multi-word forms instead of falling through to LLM (ultraworkers#2994)39a2d409885d72a88d864601d04dfix: REPL display, /compact panic, identity leak, DeepSeek reasoning, thinking blocks (+1099 lines)The OpenAI pair (
9885d72+a88d864) is particularly relevant to this fork's LMStudio / OpenAI-compat backend usage. The +1099-line REPL bundle (601d04d) auto-merged cleanly across 15 files includingruntime/src/lib.rs,tools/src/lib.rs, andrusty-claude-cli/src/main.rs. None of the picks touched the fork's hardening surface (.claw.jsonfiles at root andrust/,runtime/src/permissions/,crates/runtime/src/oauth/).Test plan
cargo check --workspace --all-targets— clean in 26s.cargo test --workspace— all crates pass except 9 pre-existing failures inrusty-claude-cliarg-parsing tests. Verified those same 9 failures reproduce onmainwithout any picks applied — picks introduce zero regressions. The pre-existing failures are about the parser walking up to the hardened.claw.json(defaultMode: "default") and resolving toWorkspaceWriteinstead of the expectedReadOnly— unrelated to this work, will be filed separately./compactno longer panics on Thinking blocks.🤖 Generated with Claude Code