mirror of
https://github.com/pchuan98/codex.git
synced 2026-07-01 00:31:56 +08:00
core: persist initial context window metadata (#29519)
## Why PR #29494 made context-window IDs visible to the model by wrapping the token-budget window payload in `<context_window>`, but rollout JSONL consumers still could not see the initial window identity by tailing the session file. Compacted rollout items carry window IDs only after compaction has happened, so a session with no compaction had no durable JSONL record for window 0. This change gives tailing consumers a stable initial-window record at session creation time. ## What Changed - Added `session_meta.context_window.window_id` for the initial context-window identity. - `CreateThreadParams` now requires `initial_window_id: String`, so thread-store callers cannot accidentally create new threads without window-0 metadata. - Live thread creation derives the persisted initial window ID from the same `AutoCompactWindowIds` used to initialize `SessionState`, keeping runtime state and JSONL metadata aligned. - Rollout reconstruction uses `session_meta.context_window.window_id` as the initial-window fallback and derives `window_number = 0`, `first_window_id = window_id`, and `previous_window_id = None` internally. - Fork reconstruction intentionally uses the same rollout reconstruction path; consumers that need to distinguish copied initial-window metadata can use the rollout `thread_id`. - Legacy compactions without `window_number` still use compaction-count fallback accounting instead of being reset to window 0 by the initial-window fallback. - Compacted rollout metadata still takes precedence once compaction records exist, preserving the richer chain fields there. ## JSONL Shape Real rollout JSONL is one object per line. This example is expanded for readability, but shows the new initial `session_meta.context_window` record followed by the existing compacted rollout item shape that also carries window IDs: ```jsonl { "timestamp": "2026-06-22T12:00:00.000Z", "type": "session_meta", "payload": { "session_id": "<THREAD_ID>", "id": "<THREAD_ID>", "timestamp": "2026-06-22T12:00:00.000Z", "cwd": "/repo", "originator": "codex", "cli_version": "0.0.0", "source": "cli", "model_provider": "<MODEL_PROVIDER>", "context_window": { "window_id": "<INITIAL_WINDOW_ID>" } } } ... { "timestamp": "2026-06-22T12:34:56.000Z", "type": "compacted", "payload": { "message": "<COMPACTION_SUMMARY>", "replacement_history": [ "..." ], "window_number": 1, "first_window_id": "<INITIAL_WINDOW_ID>", "previous_window_id": "<INITIAL_WINDOW_ID>", "window_id": "<NEXT_WINDOW_ID>" } } ``` The nested `context_window` object is intentional: it gives rollout consumers a stable namespace for context-window metadata while only writing the non-derivable initial `window_id`. For the initial window, `window_number`, `first_window_id`, and `previous_window_id` are derived internally instead of being written to the rollout. ## Verification - `just test -p codex-protocol` - `just test -p codex-rollout recorder_materializes_on_flush_with_pending_items` - `just test -p codex-core reconstruct_history` - `just test -p codex-core record_initial_history_reconstructs_forked_transcript` - `just test -p codex-thread-store` - `just test -p codex-state` - `just test -p codex-app-server thread_read_returns_summary_without_turns` - `just test -p codex-rollout persistence_metrics`
This commit is contained in:
@@ -215,6 +215,7 @@ impl ExternalAgentSessionImporter {
|
||||
},
|
||||
dynamic_tools: Vec::new(),
|
||||
multi_agent_version: Some(MultiAgentVersion::V1),
|
||||
initial_window_id: uuid::Uuid::now_v7().to_string(),
|
||||
metadata: ThreadPersistenceMetadata {
|
||||
cwd: Some(cwd.clone()),
|
||||
model_provider: model_provider.clone(),
|
||||
|
||||
@@ -202,6 +202,7 @@ fn create_fake_rollout_with_source_and_parent_thread_id(
|
||||
dynamic_tools: None,
|
||||
memory_mode: None,
|
||||
multi_agent_version: None,
|
||||
context_window: None,
|
||||
};
|
||||
let payload = serde_json::to_value(SessionMetaLine {
|
||||
meta,
|
||||
@@ -289,6 +290,7 @@ pub fn create_fake_rollout_with_text_elements(
|
||||
dynamic_tools: None,
|
||||
memory_mode: None,
|
||||
multi_agent_version: None,
|
||||
context_window: None,
|
||||
};
|
||||
let payload = serde_json::to_value(SessionMetaLine {
|
||||
meta,
|
||||
|
||||
@@ -131,6 +131,7 @@ async fn get_conversation_summary_by_thread_id_reads_pathless_store_thread() ->
|
||||
base_instructions: BaseInstructions::default(),
|
||||
dynamic_tools: Vec::new(),
|
||||
multi_agent_version: None,
|
||||
initial_window_id: Uuid::now_v7().to_string(),
|
||||
metadata: ThreadPersistenceMetadata {
|
||||
cwd: None,
|
||||
model_provider: "test-provider".to_string(),
|
||||
|
||||
@@ -157,6 +157,7 @@ async fn thread_delete_with_non_local_thread_store_does_not_create_local_persist
|
||||
base_instructions: BaseInstructions::default(),
|
||||
dynamic_tools: Vec::new(),
|
||||
multi_agent_version: None,
|
||||
initial_window_id: Uuid::now_v7().to_string(),
|
||||
metadata: ThreadPersistenceMetadata {
|
||||
cwd: Some(codex_home.path().to_path_buf()),
|
||||
model_provider: "mock_provider".to_string(),
|
||||
|
||||
@@ -1367,6 +1367,7 @@ async fn seed_pathless_store_thread(
|
||||
base_instructions: BaseInstructions::default(),
|
||||
dynamic_tools: Vec::new(),
|
||||
multi_agent_version: None,
|
||||
initial_window_id: Uuid::now_v7().to_string(),
|
||||
metadata: ThreadPersistenceMetadata {
|
||||
cwd: None,
|
||||
model_provider: "test-provider".to_string(),
|
||||
|
||||
@@ -2072,6 +2072,7 @@ stream_max_retries = 0
|
||||
dynamic_tools: None,
|
||||
memory_mode: None,
|
||||
multi_agent_version: None,
|
||||
context_window: None,
|
||||
};
|
||||
std::fs::write(
|
||||
&rollout_path,
|
||||
|
||||
@@ -218,6 +218,7 @@ async fn thread_unarchive_preserves_pathless_store_metadata() -> Result<()> {
|
||||
base_instructions: BaseInstructions::default(),
|
||||
dynamic_tools: Vec::new(),
|
||||
multi_agent_version: None,
|
||||
initial_window_id: Uuid::now_v7().to_string(),
|
||||
metadata: ThreadPersistenceMetadata {
|
||||
cwd: None,
|
||||
model_provider: "test-provider".to_string(),
|
||||
|
||||
Reference in New Issue
Block a user