mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-07 07:58:09 +00:00
3b20b48473
* feat(interactions): continue requires_continuation long decodes with continuation_token hops A foreground Interactions request stops at Google's per-hop output cap with status requires_continuation and a continuation_token. litellm now re-posts the request with previous_interaction_id and continuation_token until the status moves on, merging the hops into one interaction (last id, every hop's steps, summed usage with initial_input_tokens from hop 1), for non-streaming and streaming calls. continuation_token is accepted as a request param, and requires_continuation is a known status for billing. * refactor(gemini interactions): validate streaming chunks with model_validate * fix(interactions): keep the held completion across stream hops, stop on a repeated continuation_token, follow the spec redirect * fix(interactions): add grounding_tool_count per tool type, stop on any seen continuation_token, keep streaming past a [DONE] frame when a hop is pending * ci(interactions): point the spec canary at aistudio.google.com, where Google moved the Interactions OpenAPI spec * test(interactions): scripted Google ends each long decode hop with a [DONE] frame * refactor(interactions): pass requires_continuation and continuation_token through instead of looping hops in the proxy The caller drives the continuation, the same as against Google directly. /interactions accepts continuation_token in place of input so a resume request needs no input. * test(proxy): assert the accepted /interactions bodies pass the required-param check * fix(proxy): keep the router default fallback for input on /interactions, continuation_token stands in for it --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| auto-close-duplicates.yml | ||
| check-schema-sync.yml | ||
| codeql.yml | ||
| codspeed.yml | ||
| compat-matrix-image.yml | ||
| conventional-commits.yml | ||
| cost-map-guard.yml | ||
| cost-map-pins-recheck.yml | ||
| create-rc-branch.yml | ||
| create-release-branch.yml | ||
| duplicate_issue_check.yml | ||
| e2e_record_replay.yml | ||
| guard-fork-dependencies.yml | ||
| image-scan.yml | ||
| interactions-spec-canary.yml | ||
| issue-keyword-labeler.yml | ||
| issue_classifier.yml | ||
| issue_fixed_comment.yml | ||
| issue_label_claude_code.yml | ||
| issue_label_sync.yml | ||
| linear-release.yml | ||
| mutation-test.yml | ||
| osv-scan.yml | ||
| publish-lint-base-counts.yml | ||
| scorecard.yml | ||
| spend-logs-guard.yml | ||
| stale.yml | ||
| sync-schema.yml | ||
| test-e2e-redis-chaos.yml | ||
| test-integration.yml | ||
| test-linting.yml | ||
| test-mcp-dependency-resolution.yml | ||
| test-merge-smoke.yml | ||
| test-rust-db.yml | ||
| test-rust.yml | ||
| test-terraform-modules.yml | ||
| test-terraform-provider.yml | ||
| test-unit.yml | ||
| test-vscode-extension.yml | ||
| zizmor.yml | ||