Commit Graph

7 Commits

  • feat: better UX during refusal (#5260)
    <img width="568" height="169" alt="Screenshot 2025-10-16 at 18 28 05"
    src="https://github.com/user-attachments/assets/f42e8d6d-b7de-4948-b291-a5fbb50b1312"
    />
  • fix: apply_patch shell_serialization tests (#4786)
    ## Summary
    Adds additional shell_serialization tests specifically for apply_patch
    and other cases.
    
    ## Test Plan
    - [x] These are all tests
  • bug: sandbox denied error logs (#4874)
    Check on STDOUT / STDERR or aggregated output for some logs when sanbox
    is denied
  • chore: refactor tool handling (#4510)
    # Tool System Refactor
    
    - Centralizes tool definitions and execution in `core/src/tools/*`:
    specs (`spec.rs`), handlers (`handlers/*`), router (`router.rs`),
    registry/dispatch (`registry.rs`), and shared context (`context.rs`).
    One registry now builds the model-visible tool list and binds handlers.
    - Router converts model responses to tool calls; Registry dispatches
    with consistent telemetry via `codex-rs/otel` and unified error
    handling. Function, Local Shell, MCP, and experimental `unified_exec`
    all flow through this path; legacy shell aliases still work.
    - Rationale: reduce per‑tool boilerplate, keep spec/handler in sync, and
    make adding tools predictable and testable.
    
    Example: `read_file`
    - Spec: `core/src/tools/spec.rs` (see `create_read_file_tool`,
    registered by `build_specs`).
    - Handler: `core/src/tools/handlers/read_file.rs` (absolute `file_path`,
    1‑indexed `offset`, `limit`, `L#: ` prefixes, safe truncation).
    - E2E test: `core/tests/suite/read_file.rs` validates the tool returns
    the requested lines.
    
    ## Next steps:
    - Decompose `handle_container_exec_with_params` 
    - Add parallel tool calls
  • chore: sandbox refactor 2 (#4653)
    Revert the revert and fix the UI issue
  • chore: sanbox extraction (#4286)
    # Extract and Centralize Sandboxing
    - Goal: Improve safety and clarity by centralizing sandbox planning and
    execution.
      - Approach:
    - Add planner (ExecPlan) and backend registry (Direct/Seatbelt/Linux)
    with run_with_plan.
    - Refactor codex.rs to plan-then-execute; handle failures/escalation via
    the plan.
    - Delegate apply_patch to the codex binary and run it with an empty env
    for determinism.