Use responses request helpers for compact requests#20719
Closed
aibrahim-oai wants to merge 1 commit into
Closed
Conversation
Contributor
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: a721d35abe
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Collaborator
Author
|
@codex review this |
Contributor
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 1741be7789
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| request.store = None; | ||
| request.stream = None; | ||
| request.include = None; | ||
| request.client_metadata = None; |
Contributor
There was a problem hiding this comment.
Preserve installation ID on compact requests
compact_conversation_history now clears request.client_metadata before calling /responses/compact, but no replacement x-codex-installation-id header is added on this path. build_responses_identity_headers() only carries subagent/parent/window IDs, so compact calls lose installation attribution that the previous implementation sent. This can break per-install telemetry/quota/accounting for compaction traffic.
Useful? React with 👍 / 👎.
This was referenced May 2, 2026
Make /responses/compact reuse the shared responses request construction and serialization path, then adapt only the fields rejected by the compact endpoint. Preserve compact-specific headers and add remote compact parity coverage across auth modes. Co-authored-by: Codex <noreply@openai.com>
0ae33ff to
e3626db
Compare
aibrahim-oai
added a commit
that referenced
this pull request
May 6, 2026
## Why `/responses/compact` should preserve the request-affinity fields that apply to the active auth mode. ChatGPT-auth compact requests need the effective `service_tier`, and compact requests for every auth mode need the stable `prompt_cache_key`, so compaction does not quietly lose routing or cache behavior that normal sampling already has. This follows the request-parity direction from #20719, but keeps the net change focused on the compact payload fields needed here. ## What changed - Add `service_tier` and `prompt_cache_key` to the compact endpoint input payload. - Build the remote compact payload from the existing responses request builder output so `Fast` still maps to `priority` when compact sends a service tier. - Pass the turn service tier into remote compaction, but only include it in compact payloads for ChatGPT-backed auth. - Keep `prompt_cache_key` on compact payloads for all auth modes. - Add request-body diff snapshot coverage in `core/tests/suite/compact_remote.rs` for: - API-key auth reusing `prompt_cache_key` while omitting `service_tier` even when `Fast` is configured. - ChatGPT auth reusing both `service_tier` and `prompt_cache_key`. - Drive the snapshot coverage through five varied turns: plain text, multi-part text, tool-call continuation, image+text input, local-shell continuation, and final-turn reasoning output. ## Verification - Added insta snapshots for compact request-body parity against the last normal `/responses` request after five varied turns. - Not run locally per repo guidance; relying on GitHub CI for test execution. --------- Co-authored-by: Codex <noreply@openai.com>
cconger
pushed a commit
that referenced
this pull request
May 6, 2026
## Why `/responses/compact` should preserve the request-affinity fields that apply to the active auth mode. ChatGPT-auth compact requests need the effective `service_tier`, and compact requests for every auth mode need the stable `prompt_cache_key`, so compaction does not quietly lose routing or cache behavior that normal sampling already has. This follows the request-parity direction from #20719, but keeps the net change focused on the compact payload fields needed here. ## What changed - Add `service_tier` and `prompt_cache_key` to the compact endpoint input payload. - Build the remote compact payload from the existing responses request builder output so `Fast` still maps to `priority` when compact sends a service tier. - Pass the turn service tier into remote compaction, but only include it in compact payloads for ChatGPT-backed auth. - Keep `prompt_cache_key` on compact payloads for all auth modes. - Add request-body diff snapshot coverage in `core/tests/suite/compact_remote.rs` for: - API-key auth reusing `prompt_cache_key` while omitting `service_tier` even when `Fast` is configured. - ChatGPT auth reusing both `service_tier` and `prompt_cache_key`. - Drive the snapshot coverage through five varied turns: plain text, multi-part text, tool-call continuation, image+text input, local-shell continuation, and final-turn reasoning output. ## Verification - Added insta snapshots for compact request-body parity against the last normal `/responses` request after five varied turns. - Not run locally per repo guidance; relying on GitHub CI for test execution. --------- Co-authored-by: Codex <noreply@openai.com>
Oreoxp
pushed a commit
to Oreoxp/codex-cli
that referenced
this pull request
May 7, 2026
## Why `/responses/compact` should preserve the request-affinity fields that apply to the active auth mode. ChatGPT-auth compact requests need the effective `service_tier`, and compact requests for every auth mode need the stable `prompt_cache_key`, so compaction does not quietly lose routing or cache behavior that normal sampling already has. This follows the request-parity direction from openai#20719, but keeps the net change focused on the compact payload fields needed here. ## What changed - Add `service_tier` and `prompt_cache_key` to the compact endpoint input payload. - Build the remote compact payload from the existing responses request builder output so `Fast` still maps to `priority` when compact sends a service tier. - Pass the turn service tier into remote compaction, but only include it in compact payloads for ChatGPT-backed auth. - Keep `prompt_cache_key` on compact payloads for all auth modes. - Add request-body diff snapshot coverage in `core/tests/suite/compact_remote.rs` for: - API-key auth reusing `prompt_cache_key` while omitting `service_tier` even when `Fast` is configured. - ChatGPT auth reusing both `service_tier` and `prompt_cache_key`. - Drive the snapshot coverage through five varied turns: plain text, multi-part text, tool-call continuation, image+text input, local-shell continuation, and final-turn reasoning output. ## Verification - Added insta snapshots for compact request-body parity against the last normal `/responses` request after five varied turns. - Not run locally per repo guidance; relying on GitHub CI for test execution. --------- Co-authored-by: Codex <noreply@openai.com>
dkropachev
pushed a commit
to dkropachev/codex
that referenced
this pull request
May 10, 2026
## Why `/responses/compact` should preserve the request-affinity fields that apply to the active auth mode. ChatGPT-auth compact requests need the effective `service_tier`, and compact requests for every auth mode need the stable `prompt_cache_key`, so compaction does not quietly lose routing or cache behavior that normal sampling already has. This follows the request-parity direction from openai#20719, but keeps the net change focused on the compact payload fields needed here. ## What changed - Add `service_tier` and `prompt_cache_key` to the compact endpoint input payload. - Build the remote compact payload from the existing responses request builder output so `Fast` still maps to `priority` when compact sends a service tier. - Pass the turn service tier into remote compaction, but only include it in compact payloads for ChatGPT-backed auth. - Keep `prompt_cache_key` on compact payloads for all auth modes. - Add request-body diff snapshot coverage in `core/tests/suite/compact_remote.rs` for: - API-key auth reusing `prompt_cache_key` while omitting `service_tier` even when `Fast` is configured. - ChatGPT auth reusing both `service_tier` and `prompt_cache_key`. - Drive the snapshot coverage through five varied turns: plain text, multi-part text, tool-call continuation, image+text input, local-shell continuation, and final-turn reasoning output. ## Verification - Added insta snapshots for compact request-body parity against the last normal `/responses` request after five varied turns. - Not run locally per repo guidance; relying on GitHub CI for test execution. --------- Co-authored-by: Codex <noreply@openai.com>
AIALRA-0
pushed a commit
to AIALRA-0/codex-turn-engine
that referenced
this pull request
Jun 10, 2026
## Why `/responses/compact` should preserve the request-affinity fields that apply to the active auth mode. ChatGPT-auth compact requests need the effective `service_tier`, and compact requests for every auth mode need the stable `prompt_cache_key`, so compaction does not quietly lose routing or cache behavior that normal sampling already has. This follows the request-parity direction from openai#20719, but keeps the net change focused on the compact payload fields needed here. ## What changed - Add `service_tier` and `prompt_cache_key` to the compact endpoint input payload. - Build the remote compact payload from the existing responses request builder output so `Fast` still maps to `priority` when compact sends a service tier. - Pass the turn service tier into remote compaction, but only include it in compact payloads for ChatGPT-backed auth. - Keep `prompt_cache_key` on compact payloads for all auth modes. - Add request-body diff snapshot coverage in `core/tests/suite/compact_remote.rs` for: - API-key auth reusing `prompt_cache_key` while omitting `service_tier` even when `Fast` is configured. - ChatGPT auth reusing both `service_tier` and `prompt_cache_key`. - Drive the snapshot coverage through five varied turns: plain text, multi-part text, tool-call continuation, image+text input, local-shell continuation, and final-turn reasoning output. ## Verification - Added insta snapshots for compact request-body parity against the last normal `/responses` request after five varied turns. - Not run locally per repo guidance; relying on GitHub CI for test execution. --------- Co-authored-by: Codex <noreply@openai.com>
AIALRA-0
pushed a commit
to AIALRA-0/codex-turn-engine
that referenced
this pull request
Jun 10, 2026
## Why `/responses/compact` should preserve the request-affinity fields that apply to the active auth mode. ChatGPT-auth compact requests need the effective `service_tier`, and compact requests for every auth mode need the stable `prompt_cache_key`, so compaction does not quietly lose routing or cache behavior that normal sampling already has. This follows the request-parity direction from openai#20719, but keeps the net change focused on the compact payload fields needed here. ## What changed - Add `service_tier` and `prompt_cache_key` to the compact endpoint input payload. - Build the remote compact payload from the existing responses request builder output so `Fast` still maps to `priority` when compact sends a service tier. - Pass the turn service tier into remote compaction, but only include it in compact payloads for ChatGPT-backed auth. - Keep `prompt_cache_key` on compact payloads for all auth modes. - Add request-body diff snapshot coverage in `core/tests/suite/compact_remote.rs` for: - API-key auth reusing `prompt_cache_key` while omitting `service_tier` even when `Fast` is configured. - ChatGPT auth reusing both `service_tier` and `prompt_cache_key`. - Drive the snapshot coverage through five varied turns: plain text, multi-part text, tool-call continuation, image+text input, local-shell continuation, and final-turn reasoning output. ## Verification - Added insta snapshots for compact request-body parity against the last normal `/responses` request after five varied turns. - Not run locally per repo guidance; relying on GitHub CI for test execution. --------- Co-authored-by: Codex <noreply@openai.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Why
/responses/compactwas still building its own request payload and shared headers separately from/responses. That made it easy for new request fields or header behavior to land on/responseswithout reaching compaction, even though we want the compact request shape to stay aligned with the normal responses path.The compact endpoint also rejects a small set of
/responsesrequest fields today, so compact should reuse the shared builder and then omit only those unsupported fields before serialization.What changed
ResponsesApiRequestbuilder incore./responses:service_tierand the turn metadata header.codex-apifor both/responsesand/responses/compact.store,stream,include, andclient_metadata.coreintegration test that drives the real helper path, compares the last normal/responsesrequest with the following/responses/compactrequest after five varied turns, and snapshots the whole JSON request-body diff.Verification
core/tests/suite/compact_remote.rsfor varied turn history request parity, including a non-default service tier and compact turn metadata header presence.