Commit Graph

7 Commits

Author SHA1 Message Date
jif-oai
268a10f917 feat: add header for task kind (#5142)
Add a header in the responses API request for the task kind (compact,
review, ...) for observability purpose
The header name is `codex-task-type`
2025-10-14 15:17:00 +00:00
Ahmed Ibrahim
90ef94d3b3 Surface context window error to the client (#4675)
In the past, we were treating `input exceeded context window` as a
streaming error and retrying on it. Retrying on it has no point because
it won't change the behavior. In this PR, we surface the error to the
client without retry and also send a token count event to indicate that
the context window is full.

<img width="650" height="125" alt="image"
src="https://github.com/user-attachments/assets/c26b1213-4c27-4bfc-90f4-51a270a3efd5"
/>
2025-10-05 01:40:06 +00:00
jif-oai
69cb72f842 chore: sandbox refactor 2 (#4653)
Revert the revert and fix the UI issue
2025-10-03 11:17:39 +01:00
Ahmed Ibrahim
ed5d656fa8 Revert "chore: sanbox extraction" (#4626)
Reverts openai/codex#4286
2025-10-02 21:09:21 +00:00
jif-oai
b8195a17e5 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.
2025-10-01 12:05:12 +01:00
jif-oai
1fc3413a46 ref: state - 2 (#4229)
Extracting tasks in a module and start abstraction behind a Trait (more
to come on this but each task will be tackled in a dedicated PR)
The goal was to drop the ActiveTask and to have a (potentially) set of
tasks during each turn
2025-09-26 13:49:08 +00:00
jif-oai
250b244ab4 ref: full state refactor (#4174)
## Current State Observations
- `Session` currently holds many unrelated responsibilities (history,
approval queues, task handles, rollout recorder, shell discovery, token
tracking, etc.), making it hard to reason about ownership and lifetimes.
- The anonymous `State` struct inside `codex.rs` mixes session-long data
with turn-scoped queues and approval bookkeeping.
- Turn execution (`run_task`) relies on ad-hoc local variables that
should conceptually belong to a per-turn state object.
- External modules (`codex::compact`, tests) frequently poke the raw
`Session.state` mutex, which couples them to implementation details.
- Interrupts, approvals, and rollout persistence all have bespoke
cleanup paths, contributing to subtle bugs when a turn is aborted
mid-flight.

## Desired End State
- Keep a slim `Session` object that acts as the orchestrator and façade.
It should expose a focused API (submit, approvals, interrupts, event
emission) without storing unrelated fields directly.
- Introduce a `state` module that encapsulates all mutable data
structures:
- `SessionState`: session-persistent data (history, approved commands,
token/rate-limit info, maybe user preferences).
- `ActiveTurn`: metadata for the currently running turn (sub-id, task
kind, abort handle) and an `Arc<TurnState>`.
- `TurnState`: all turn-scoped pieces (pending inputs, approval waiters,
diff tracker, review history, auto-compact flags, last agent message,
outstanding tool call bookkeeping).
- Group long-lived helpers/managers into a dedicated `SessionServices`
struct so `Session` does not accumulate "random" fields.
- Provide clear, lock-safe APIs so other modules never touch raw
mutexes.
- Ensure every turn creates/drops a `TurnState` and that
interrupts/finishes delegate cleanup to it.
2025-09-25 12:16:06 +02:00