fix: preserve session_id across previous_response_id chains in /v1/responses#10059
Merged
Conversation
…sponses The /v1/responses endpoint generated a new UUID session_id for every request, even when previous_response_id was provided. This caused each turn of a multi-turn conversation to appear as a separate session on the web dashboard, despite the conversation history being correctly chained. Fix: store session_id alongside the response in the ResponseStore, and reuse it when a subsequent request chains via previous_response_id. Applies to both the non-streaming /v1/responses path and the streaming SSE path. The /v1/runs endpoint also gains session continuity from stored responses (explicit body.session_id still takes priority). Adds test verifying session_id is preserved across chained requests.
ulasbilgen
pushed a commit
to ulasbilgen/hermes-adhd-agent
that referenced
this pull request
May 1, 2026
…sponses (NousResearch#10059) The /v1/responses endpoint generated a new UUID session_id for every request, even when previous_response_id was provided. This caused each turn of a multi-turn conversation to appear as a separate session on the web dashboard, despite the conversation history being correctly chained. Fix: store session_id alongside the response in the ResponseStore, and reuse it when a subsequent request chains via previous_response_id. Applies to both the non-streaming /v1/responses path and the streaming SSE path. The /v1/runs endpoint also gains session continuity from stored responses (explicit body.session_id still takes priority). Adds test verifying session_id is preserved across chained requests.
aj-nt
pushed a commit
to aj-nt/hermes-agent
that referenced
this pull request
May 1, 2026
…sponses (NousResearch#10059) The /v1/responses endpoint generated a new UUID session_id for every request, even when previous_response_id was provided. This caused each turn of a multi-turn conversation to appear as a separate session on the web dashboard, despite the conversation history being correctly chained. Fix: store session_id alongside the response in the ResponseStore, and reuse it when a subsequent request chains via previous_response_id. Applies to both the non-streaming /v1/responses path and the streaming SSE path. The /v1/runs endpoint also gains session continuity from stored responses (explicit body.session_id still takes priority). Adds test verifying session_id is preserved across chained requests.
02356abc
pushed a commit
to 02356abc/hermes-agent
that referenced
this pull request
May 14, 2026
…sponses (NousResearch#10059) The /v1/responses endpoint generated a new UUID session_id for every request, even when previous_response_id was provided. This caused each turn of a multi-turn conversation to appear as a separate session on the web dashboard, despite the conversation history being correctly chained. Fix: store session_id alongside the response in the ResponseStore, and reuse it when a subsequent request chains via previous_response_id. Applies to both the non-streaming /v1/responses path and the streaming SSE path. The /v1/runs endpoint also gains session continuity from stored responses (explicit body.session_id still takes priority). Adds test verifying session_id is preserved across chained requests.
gweeteve
pushed a commit
to gweeteve/hermes-agent
that referenced
this pull request
Jun 2, 2026
…sponses (NousResearch#10059) The /v1/responses endpoint generated a new UUID session_id for every request, even when previous_response_id was provided. This caused each turn of a multi-turn conversation to appear as a separate session on the web dashboard, despite the conversation history being correctly chained. Fix: store session_id alongside the response in the ResponseStore, and reuse it when a subsequent request chains via previous_response_id. Applies to both the non-streaming /v1/responses path and the streaming SSE path. The /v1/runs endpoint also gains session continuity from stored responses (explicit body.session_id still takes priority). Adds test verifying session_id is preserved across chained requests.
Egavasyug
pushed a commit
to Egavasyug/hermes-agent
that referenced
this pull request
Jun 10, 2026
…sponses (NousResearch#10059) The /v1/responses endpoint generated a new UUID session_id for every request, even when previous_response_id was provided. This caused each turn of a multi-turn conversation to appear as a separate session on the web dashboard, despite the conversation history being correctly chained. Fix: store session_id alongside the response in the ResponseStore, and reuse it when a subsequent request chains via previous_response_id. Applies to both the non-streaming /v1/responses path and the streaming SSE path. The /v1/runs endpoint also gains session continuity from stored responses (explicit body.session_id still takes priority). Adds test verifying session_id is preserved across chained requests.
waefrebeorn
pushed a commit
to waefrebeorn/slermes
that referenced
this pull request
Jul 2, 2026
…sponses (NousResearch#10059) The /v1/responses endpoint generated a new UUID session_id for every request, even when previous_response_id was provided. This caused each turn of a multi-turn conversation to appear as a separate session on the web dashboard, despite the conversation history being correctly chained. Fix: store session_id alongside the response in the ResponseStore, and reuse it when a subsequent request chains via previous_response_id. Applies to both the non-streaming /v1/responses path and the streaming SSE path. The /v1/runs endpoint also gains session continuity from stored responses (explicit body.session_id still takes priority). Adds test verifying session_id is preserved across chained requests.
liuchanchen
pushed a commit
to liuchanchen/hermes-agent
that referenced
this pull request
Jul 3, 2026
…sponses (NousResearch#10059) The /v1/responses endpoint generated a new UUID session_id for every request, even when previous_response_id was provided. This caused each turn of a multi-turn conversation to appear as a separate session on the web dashboard, despite the conversation history being correctly chained. Fix: store session_id alongside the response in the ResponseStore, and reuse it when a subsequent request chains via previous_response_id. Applies to both the non-streaming /v1/responses path and the streaming SSE path. The /v1/runs endpoint also gains session continuity from stored responses (explicit body.session_id still takes priority). Adds test verifying session_id is preserved across chained requests.
kulikman
pushed a commit
to kulikman/hermes-agent
that referenced
this pull request
Jul 16, 2026
…sponses (NousResearch#10059) The /v1/responses endpoint generated a new UUID session_id for every request, even when previous_response_id was provided. This caused each turn of a multi-turn conversation to appear as a separate session on the web dashboard, despite the conversation history being correctly chained. Fix: store session_id alongside the response in the ResponseStore, and reuse it when a subsequent request chains via previous_response_id. Applies to both the non-streaming /v1/responses path and the streaming SSE path. The /v1/runs endpoint also gains session continuity from stored responses (explicit body.session_id still takes priority). Adds test verifying session_id is preserved across chained requests.
waym0reom3ga
added a commit
to waym0reom3ga/autolycus-agent
that referenced
this pull request
Jul 21, 2026
…sponses (NousResearch#10059) The /v1/responses endpoint generated a new UUID session_id for every request, even when previous_response_id was provided. This caused each turn of a multi-turn conversation to appear as a separate session on the web dashboard, despite the conversation history being correctly chained. Fix: store session_id alongside the response in the ResponseStore, and reuse it when a subsequent request chains via previous_response_id. Applies to both the non-streaming /v1/responses path and the streaming SSE path. The /v1/runs endpoint also gains session continuity from stored responses (explicit body.session_id still takes priority). Adds test verifying session_id is preserved across chained requests.
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.
Summary
Fixes a bug where every
/v1/responsesrequest created a new session on the web dashboard, even whenprevious_response_idwas passed for multi-turn conversation chaining.Root cause: Line 1485 in
api_server.pyunconditionally generatedsession_id = str(uuid.uuid4())for every request. TheResponseStorecorrectly chained conversation history but never stored or restored thesession_id, so each turn got its own session entry inSessionDB.Fix:
session_idalongside the response inResponseStore.put()(both streaming and non-streaming paths)previous_response_idresolves, extract and reuse the storedsession_id/v1/responses(streaming + non-streaming) and/v1/runsendpointsbody.session_idon/v1/runsstill takes priority over stored sessionTest plan
test_previous_response_id_preserves_sessionverifies session_id is identical across chained requestsFiles changed
gateway/platforms/api_server.py— 3 store sites + 2 resolution sitestests/gateway/test_api_server.py— new test