Commit Graph
6 Commits
Author SHA1 Message Date
Abhinav b64de2f3ad Use the originating model when recording conversation history (#44243)
## Why

History recording used the model captured at turn start, so switching models within a turn could apply stale image preparation and tool-output truncation rules.

## What changed

Pass explicit model metadata through conversation recording. Record model responses and tool results using their originating step's settings, and capture the current model for pending input recorded during startup interruption or task completion.

## Testing

Add regression coverage for tool results across a model switch, explicit model selection for plain and annotated history, and image input retained during interruption and completion. Extend model-switching tests to verify that prepared media and item identity survive switching back to a multimodal model in live, resumed, and forked threads.

GitOrigin-RevId: 5bc750c30c334acb9b802cb80fdea01daffa84a1
2026-09-09 17:46:00 +00:00
rka-oai 0e9a2bae52 Enable clock tools for persistent reasoning turns (#40942)
## What changed

- Default the current-time reminder and interruptible `clock.sleep` tool on for
  turns using persistent reasoning effort.
- Preserve explicit `features.current_time_reminder` settings and managed
  requirements, and gate reminder recording on the resolved feature state.

## Testing

- Cover configured, persistent, ordinary-effort, explicitly disabled, and
  managed-disabled clock setups.
- Verify review turns do not expose clock tools or current-time reminders.

GitOrigin-RevId: 4ff8805807ceeef374abd962b1d9e7c37f1fbd83
2026-08-26 18:06:12 +00:00
rka-oai adccb464d0 [codex] impl delivery_mode: current time reminders on response boundaries (#30033)
## Summary
- track user-like input and tool-output boundaries in current-time
reminder state
- gate reminder injection when delivery_mode is
after_user_or_tool_output
- preserve interval debounce and forced reminders after context-window
changes

## Why
Training can request reminders only after user or tool-output items
while keeping the existing canonical pre-inference history-injection
path.

## Validation
- just test -p codex-core
current_time_reminders_can_follow_only_user_or_tool_outputs
- just test -p codex-core
current_time_reminders_follow_time_interval_and_persist_in_history
- just test -p codex-core
current_time_reminder_is_refreshed_after_compaction
- just fix -p codex-core
2026-06-25 19:28:50 +00:00
rka-oai cc78903379 [codex] current time reminder interval to be set to 0 (#30029)
A zero interval lets callers request a reminder at every
otherwise-eligible inference boundary.

## Validation
- just test -p codex-core load_config_resolves_current_time_reminder
2026-06-25 18:30:53 +00:00
rka-oai 9fe689783d [core] debounce current-time reminders by elapsed time (#29659)
## Summary
- rename `reminder_interval_model_requests` to
`reminder_interval_seconds`
- read the configured time provider before every model request and
inject a reminder only after the configured number of seconds has
elapsed
- preserve immediate first delivery and forced delivery after compaction
changes the context window

## Tests
- `just test -p codex-core current_time_reminder`
2026-06-23 10:13:27 -07:00
rka-oai 752ed90d78 current time reminders impl for system clock (varlatency 2/n) (#28824)
Stacked on #28822.

## Summary

- add a host-injectable current-time provider with a built-in system
implementation
- record UTC developer reminders in history immediately before due model
requests
- keep cadence state per session and force a refresh after compaction

This does NOT include the app server client <-> server clock logic. This
PR is only for the reminder message & system clock that will be used in
prod.

## Testing

- `just test -p codex-core varlatency_`
- `just clippy -p codex-core -p codex-app-server -p codex-mcp-server -p
codex-thread-manager-sample`
- `just fmt`
2026-06-18 19:18:42 +00:00