openai/codex
1
0
Fork 0
mirror of https://github.com/openai/codex.git synced 2026-11-06 20:20:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

Expose assistant content token counts in completion notifications (#59041)

Browse Source 
## What changed

Add optional `contentTokenCount` metadata to `item/completed` notifications, carrying the producer-supplied token count for each completed assistant message in default and plan modes. Counts include any sampled footer and are `null` when unavailable.

Keep this telemetry separate from stored thread items and omit it from subsequent model requests. Update the protocol schemas and generated TypeScript and Python types.

## Testing

Add coverage for per-message counts, including zero, in default and plan modes; missing and malformed metadata; backward-compatible notification decoding; and exclusion from subsequent model requests.

GitOrigin-RevId: 35973037a42650fa2d7569da8e88cb81215cf971
This commit is contained in:
aojiao-oai
2026-11-03 02:26:29 +00:00
committed by copyberry
parent e839b828fb
commit 16ddd538bd
48 changed files with 443 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files
sdk/python/src/openai_codex/generated/v2_all.py
+8
View File
@@ -12804,6 +12804,14 @@ class ItemCompletedNotification(BaseModel):
description="Unix timestamp (in milliseconds) when this item lifecycle completed.",
),
]
content_token_count: Annotated[
int | None,
Field(
alias="contentTokenCount",
description="Native content tokens for the completed assistant message, including a sampled footer. Null when unavailable. Completion telemetry is not part of the stored thread item.",
ge=0,
),
] = None
item: ThreadItem
thread_id: Annotated[str, Field(alias="threadId")]
turn_id: Annotated[str, Field(alias="turnId")]