LCORE-1572: Integrate conversation compaction into the query flow#1796

Open

max-svistunov wants to merge 20 commits into

lightspeed-core:mainfrom

max-svistunov:lcore-1572-integrate-compaction-query-flow

Commits on May 26, 2026

LCORE-1572: add conversation compaction and wire it into /v1/query
max-svistunov
committed
LCORE-1572: unit tests for conversation compaction core and /v1/query
max-svistunov
committed
LCORE-1572: apply conversation compaction in the A2A endpoint
max-svistunov
committed
LCORE-1572: apply conversation compaction in the streaming_query endpoint
max-svistunov
committed
LCORE-1572: tests for the streaming compaction gate
max-svistunov
committed
LCORE-1572: apply conversation compaction in the /v1/responses endpoint
max-svistunov
committed
LCORE-1572: tests for /v1/responses compacted-turn storage
max-svistunov
committed
LCORE-1572: update spec doc to the as-built compaction design
max-svistunov
committed
LCORE-1572: fix needs_compaction_path docstring (pydocstyle D400)
max-svistunov
committed
LCORE-1572: build compacted input as typed messages (silence Pydantic warning)
max-svistunov
committed
LCORE-1572: raise instead of assert on the drained compaction result
max-svistunov
committed
LCORE-1572: wire persisted recursive fold (R3) via the summary cache
max-svistunov
committed
LCORE-1572: address CodeRabbit review — list-form input tokens + clarity rename
max-svistunov
committed
LCORE-1572: persist compacted streaming turns with structure (CodeRabbit #4)
max-svistunov
committed
LCORE-1572: do not initialize the conversation cache when compaction is disabled
max-svistunov
committed