codex

Add warning on compact (#6052 )

This PR introduces the ability for `core` to send `warnings` as it can
send `errors. It also sends a warning on compaction.

<img width="811" height="187" alt="image"
src="https://github.com/user-attachments/assets/0947a42d-b720-420d-b7fd-115f8a65a46a"
/>

Ahmed Ibrahim · 2025-10-31 13:27:33 -07:00

c8ebb2a0dc

[exec] Add MCP tool arguments and results (#5899 )

Extends mcp_tool_call item to include arguments and results.

pakrym-oai · 2025-10-29 14:23:57 -07:00

815ae4164a

feat: codex exec writes only the final message to stdout (#4644 )

This updates `codex exec` so that, by default, most of the agent's
activity is written to stderr so that only the final agent message is
written to stdout. This makes it easier to pipe `codex exec` into
another tool without extra filtering.

I introduced `#![deny(clippy::print_stdout)]` to help enforce this
change and renamed the `ts_println!()` macro to `ts_msg()` because (1)
it no longer calls `println!()` and (2), `ts_eprintln!()` seemed too
long of a name.

While here, this also adds `-o` as an alias for `--output-last-message`.

Fixes https://github.com/openai/codex/issues/1670

Michael Bolin · 2025-10-03 16:22:12 +00:00

042d4d55d9

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

jif-oai · 2025-10-03 13:21:06 +01:00

33d3ecbccc

Rename assistant message to agent message and fix item type field naming (#4610 )

Naming cleanup

pakrym-oai · 2025-10-02 15:07:14 -07:00

c405d8c06c

Remove legacy codex exec --json format (#4525 )

`codex exec --json` now maps to the behavior of `codex exec
--experimental-json` with new event and item shapes.

Thread events:
- thread.started
- turn.started
- turn.completed
- turn.failed
- item.started
- item.updated
- item.completed

Item types: 
- assistant_message
- reasoning
- command_execution
- file_change
- mcp_tool_call
- web_search
- todo_list
- error

Sample output:

<details>
`codex exec "list my assigned github issues"  --json | jq`

```
{
  "type": "thread.started",
  "thread_id": "01999ce5-f229-7661-8570-53312bd47ea3"
}
{
  "type": "turn.started"
}
{
  "type": "item.completed",
  "item": {
    "id": "item_0",
    "item_type": "reasoning",
    "text": "**Planning to list assigned GitHub issues**"
  }
}
{
  "type": "item.started",
  "item": {
    "id": "item_1",
    "item_type": "mcp_tool_call",
    "server": "github",
    "tool": "search_issues",
    "status": "in_progress"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "item_1",
    "item_type": "mcp_tool_call",
    "server": "github",
    "tool": "search_issues",
    "status": "completed"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "item_2",
    "item_type": "reasoning",
    "text": "**Organizing final message structure**"
  }
}
{
  "type": "item.completed",
  "item": {
    "id": "item_3",
    "item_type": "assistant_message",
    "text": "**Assigned Issues**\n- openai/codex#3267 – “stream error: stream disconnected before completion…” (bug) – last update 2025-09-08\n- openai/codex#3257 – “You've hit your usage limit. Try again in 4 days 20 hours 9 minutes.” – last update 2025-09-23\n- openai/codex#3054 – “reqwest SSL panic (library has no ciphers)” (bug) – last update 2025-09-03\n- openai/codex#3051 – “thread 'main' panicked at linux-sandbox/src/linux_run_main.rs:53:5:” (bug) – last update 2025-09-10\n- openai/codex#3004 – “Auto-compact when approaching context limit” (enhancement) – last update 2025-09-26\n- openai/codex#2916 – “Feature request: Add OpenAI service tier support for cost optimization” – last update 2025-09-12\n- openai/codex#1581 – “stream error: stream disconnected before completion: stream closed before response.complete; retrying...” (bug) – last update 2025-09-17"
  }
}
{
  "type": "turn.completed",
  "usage": {
    "input_tokens": 34785,
    "cached_input_tokens": 12544,
    "output_tokens": 560
  }
}
```

</details>

pakrym-oai · 2025-09-30 17:21:37 -07:00

7fc3edf8a7

6 Commits