This branch:
* Avoid flushing DB when not necessary
* Filter events for which we perfom an `upsert` into the DB
* Add a dedicated update function of the `thread:updated_at` that is
lighter
This should significantly reduce the DB lock contention. If it is not
sufficient, we can de-sync the flush of the DB for `updated_at`
This PR adds a durable trace linkage for each turn by storing the active
trace ID on the rollout TurnContext record stored in session rollout
files.
Before this change, we propagated trace context at runtime but didn’t
persist a stable per-turn trace key in rollout history. That made
after-the-fact debugging harder (for example, mapping a historical turn
to the corresponding trace in datadog). This sets us up for much easier
debugging in the future.
### What changed
- Added an optional `trace_id` to TurnContextItem (rollout schema).
- Added a small OTEL helper to read the current span trace ID.
- Captured `trace_id` when creating `TurnContext` and included it in
`to_turn_context_item()`.
- Updated tests and fixtures that construct TurnContextItem so
older/no-trace cases still work.
### Why this approach
TurnContext is already the canonical durable per-turn metadata in
rollout. This keeps ownership clean: trace linkage lives with other
persisted turn metadata.
## Summary
- record a realtime close developer message when a new realtime session
replaces an active one
- assert the replacement marker through the mocked responses request
path
---------
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Charles Cunningham <ccunningham@openai.com>
## Summary
This PR includes the session's local date and timezone in the
model-visible environment context and persists that data in
`TurnContextItem`.
## What changed
- captures the current local date and IANA timezone when building a turn
context, with a UTC fallback if the timezone lookup fails
- includes current_date and timezone in the serialized
<environment_context> payload
- stores those fields on TurnContextItem so they survive rollout/history
handling, subagent review threads, and resume flows
- treats date/timezone changes as environment updates, so prompt caching
and context refresh logic do not silently reuse stale time context
- updates tests to validate the new environment fields without depending
on a single hardcoded environment-context string
## test
built a local build and saw it in the rollout file:
```
{"timestamp":"2026-02-26T21:39:50.737Z","type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"<environment_context>\n <shell>zsh</shell>\n <current_date>2026-02-26</current_date>\n <timezone>America/Los_Angeles</timezone>\n</environment_context>"}]}}
```
Summary:
- read conversation summaries and cwd info from the state DB when
possible so we no longer rely on rollout files for metadata and avoid
extra I/O
- persist CLI version in thread metadata, surface it through summary
builders, and add the necessary DB migration hooks
- simplify thread listing by using enriched state DB data directly
rather than reading rollout heads
Testing:
- Not run (not requested)
Summary
- add Cursor/ThreadsPage conversions so state DB listings can be mapped
back into the rollout list model
- make recorder list helpers query the state DB first (archived flag
included) and only fall back to file traversal if needed, along with
populating head bytes lazily
- add extensive tests to ensure the DB path is honored for active and
archived threads and that the fallback works
Testing
- Not run (not requested)
<img width="1196" height="693" alt="Screenshot 2026-02-03 at 20 42 33"
src="https://github.com/user-attachments/assets/826b3c7a-ef11-4b27-802a-3c343695794a"
/>
### What
add wiring for `phase` field on `ResponseItem::Message` to lay
groundwork for differentiating model preambles and final messages.
currently optional.
follows pattern in #9698.
updated schemas with `just write-app-server-schema` so we can see type
changes.
### Tests
Updated existing tests for SSE parsing and hydrating from history
Add a `.sqlite` database to be used to store rollout metatdata (and
later logs)
This PR is phase 1:
* Add the database and the required infrastructure
* Add a backfill of the database
* Persist the newly created rollout both in files and in the DB
* When we need to get metadata or a rollout, consider the `JSONL` as the
source of truth but compare the results with the DB and show any errors