- Reused the Responses replay lifecycle policy for V1 and V2 compaction input.
- Covered persisted native history and converted assistant replay items.
Fixes#7742
- Applied response.metadata turn-state/models-etag refreshes while draining Codex V2 compaction WebSocket events.
- Deferred the update until the WebSocket attempt succeeds so a discarded attempt cannot leak turn state.
- Added coverage for a mid-turn compaction refreshing x-codex-turn-state.
Fixes#7198
- Buffered WebSocket compaction events until terminal completion.
- Discarded buffered events when transport failure triggers an SSE replay.
- Added coverage for failure after a partial compaction output item.
Fixes#7198
- Reused the live Codex provider session for WebSocket-first V2 compaction.
- Fell back to SSE V2 on WebSocket transport failure before the existing V1 fallback.
- Propagated the configured WebSocket preference through manual, automatic, and advisor compaction paths.
- Added transport reuse and fallback regression coverage.
Fixes#7198
After an OpenAI remote compaction, prepareCompaction decided whether to
keep the provider-native replay boundary or re-expand its originals by
asking whether *any* compaction candidate (every role model plus the
largest-context available model) shared the payload's provider. In a
multi-role setup where a role such as modelRoles.smol stays on OpenAI,
the check passed forever, so a session switched to a non-OpenAI active
model kept a placeholder-only summary and never recovered the compacted
span for the rest of the session.
Judge reusability against the active model — the one that assembles the
request context every turn — instead of the candidate set. When the
active model cannot replay the payload, re-expand the originals into a
portable local summary, matching the self-healing already present for
single-provider migrations.
Fixes#6343
- Introduced `stringifyJson` helper to preserve bigint precision by serializing them as decimal strings.
- Replaced native `JSON.stringify` across compaction and session management modules to prevent serialization errors when handling bigint values in tool arguments.
- Added regression tests in `agent` and `coding-agent` packages to ensure bigint tool arguments remain intact through compaction and persistence flows.
- Force `reasoning.context` to `all_turns` in OpenAI Codex requests when `responsesLite` is enabled.
- Include `reasoning.encrypted_content` in the `include` header for lite responses.
- Update request transformation logic to ensure these fields are populated even when reasoning effort is not explicitly set.
- Enabled Codex Responses Lite for GPT-5.6 models by integrating model discovery flags and wire contract updates.
- Implemented request transformations for streaming and remote compaction, including header injection and image detail stripping.
- Introduced sequential-cutoff logic and atomic reasoning summary events for concurrent stream processing.
- Added comprehensive test suites to validate remote compaction, image handling, and reasoning summary delivery.
- Sent remoteCompaction.model or requestModelId in chat-completions remote compaction requests instead of the local catalog id.
- Covered both direct requestRemoteCompaction formatting and end-to-end openai-completions compaction with wire model ids.
Fixes#4630
- Sent OpenAI-compatible chat messages when compaction.remoteEndpoint targets /chat/completions while preserving the existing custom summarizer payload elsewhere.
- Added regressions for direct wire formatting and end-to-end openai-completions compaction against a configured chat endpoint.
Fixes#4630
- Added regression test in `remote-compaction` to verify that concurrent v2 compaction preparation correctly reuses preserved history and avoids redundant re-expansion.
- Added mock-backend verification in `session-storage` to ensure that failed atomic title updates do not rollback newer optimistic state.
- Updated `sql-session-storage` expectations to account for the preserved fixed-width title slot header in session files.
- Expanded `remote-compaction` fetch header validation to include `x-client-request-id` assertion.
- Introduced V2 streaming remote compaction for OpenAI-compatible models, enabling full conversation history forwarding and reducing data loss from local trimming.
- Added comprehensive support for sessionId, promptCacheKey, and automatic retry mechanisms to improve compaction reliability and accuracy.
- Updated agent, catalog, and configuration schemas to manage V2 streaming settings, model metadata, and model-specific context window constraints.
- Extended freeform tool patch support for Azure OpenAI and Codex models and refined assistant-side history preservation across providers.
Azure Responses remote compaction was enabled by shouldUseOpenAiRemoteCompaction
but requestOpenAiRemoteCompaction still built OpenAI-style requests:
Authorization: Bearer plus a URL without api-version. Azure Responses uses an
api-key header and api-version query parameter, so normal Azure configs failed
and fell back to local summarization.
Derive Azure compact URLs from the Azure Responses base URL/resource-name
configuration, append api-version, and send api-key headers while preserving
custom headers. Existing OpenAI and Codex request shapes are unchanged.
Added a regression test that opts into azure-openai-responses compaction and
asserts the compact URL, api-key auth, absence of Authorization, custom header
preservation, and configured compaction model payload.
Fixes#3104
- Added provider/model remoteCompaction metadata and models.yml propagation.\n- Routed configured OpenAI-compatible compaction endpoints for custom providers.\n- Added compactionModel as a summary-only model selector that leaves the active session model unchanged.\n\nFixes #3104
- Replaced Azure and OpenAI provider calls with `postOpenAIStream` flow.
- Fixed stream error handling by retaining status, headers, and body on failures.
- Fixed stream parsing by handling raw JSON SSE frames and `[DONE]` events.
- Added `OpenAIHttpError` with parsed messages and timeout-aware retry behavior.
- Added remote-compaction tests for timeout, abort, and 500-fallback behavior.
- Centralized catalog and registry handling on `ModelSpec` and `buildModel`, resolving compatibility at model build time.
- Removed runtime compatibility detectors and switched provider request flows to direct `model.compat` reads.
- Added compat fields (`supportsReasoningParams`, `alwaysSendMaxTokens`, `strictResponsesPairing`, `whenThinking`).
- Persisted explicit compatibility overrides through `compatConfig` in discovery and cache merge paths.
- Added optional FetchImpl fields to compaction, proxy, AI, coding-agent, and mnemopi options.
- Threaded injected fetch implementations through OAuth, discovery, and search/LLM request flows.
- Removed exported hookFetch utility and its package entrypoint from utils.
- Replaced global-fetch test monkeypatching with per-test FetchImpl mocks across test suites.
- Updated `buildOpenAiNativeHistory` to maintain known and custom tool-call ID sets incrementally while appending provider payload history.
- Rebuilt call-ID state when a full-snapshot payload replaced history so stale outputs were no longer emitted after reset.
- Added compaction regression tests for codex provider payload call-ID registration and stale-result dropping.
- Scope.
- Summary.
- Type.
- Relocated compaction, branch-summarization, pruning, and utils from coding-agent to packages/agent/src/compaction.
- Moved OpenAI remote compaction helpers from packages/ai to the new compaction module.
- Added handoff.ts with extractHandoffDocument, createHandoffContext, and renderHandoffPrompt helpers.
- Exposed new entries.ts with standalone SessionEntry types so coding-agent no longer owns them.
roboomp