Repository navigation
memory: make incremental view maintenance evidence-grounded - #3289
Hillary Mutisya (hillary-mutisya) merged 5 commits into
Conversation
Bind bounded completeness reviews to accepted evidence and preserve recovery when later sources resolve gaps or ambiguity. Validate and repair actual informational output, retain explicit no-gap state, and keep topic citation contracts exact. Add explicitly confirmed additive separation with protected overview content, durable child/index recovery and source-privacy guards. Extend live-only campaign tooling with maintenance metrics, actual citation receipts and blinded review preparation without manufacturing independent approval. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Preserve restricted topic-reconciliation routing and choice-only Wiki decisions alongside revision-bound review, deferred recovery, actual-output diagnostics and confirmed additive separation. Keep v25 live observations explicitly historical and invalidate combined decision-policy identities rather than attributing old results to new models. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Include the additive separation tool in the advertised protocol surface. Serve distinct synthesis, factual-check and semantic-review responses in the project brief loopback fixture, and verify completed review without extra calls on index retry. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
Fixed the failing MCP tests in 923c91b.
Validation on Windows / Node 26.13.0 / pnpm 11.9.0:
No review comments or threads were present at the latest refresh. Monitoring CI and feedback for the pushed head; CI results remain pending until the new run completes. |
|
Follow-up CI triage: the original MCP failures now pass on both Linux and Windows Node versions. The new run's sole underlying failure is the unchanged macOS Node 26 root-script storage-write benchmark ( The benchmark assumes ideal two-document grouping, while the unchanged ingestion coordinator intentionally flushes after a 25 ms admission window. A late member can therefore produce an additional group under runner load. All four storage-write benchmark tests pass locally. I requested one targeted rerun of the failed macOS job and its downstream checks; no assertions, timing policy or thresholds were changed. CI remains pending until that attempt completes. |
|
Final verification for head
The bounded monitoring window has ended. The fix is pushed and the local working tree is clean. |
7920501
into
main
Summary
Why
Initial informational builds could bypass actual-output factual checks, topic summaries could reject citations that had actually been supplied, and generic prompt instructions produced unnecessary caveats or incomplete downstream contracts. An early ambiguity or sparse source set also needs to remain recoverable when later evidence clarifies the article.
This change separates factual support, purpose-relative completeness, freshness and approval. It does not turn model confidence, API success or a saved article into independently established quality.
Behavior and compatibility
separateViewoperations areread,preview,confirmandcancel. Preview creates no child; confirmation must match that exact persisted proposal. Automatic splitting remains disabled.Reviewer guide
Validation
pnpm run buildfromts: passed.origin/mainon10e124f08cc7e52a072c0722cb2786a3ece6f2a7: lint checked 40 changed source files, violations 281 -> 281; above-threshold cyclomatic/cognitive complexity 0 -> 0; circular dependencies 210 -> 210; debt checked 74 changed files, with no newly skipped tests (0 -> 0).The focused commands use existing runners:
Author-run v25 live development observations (before base integration)
These are development observations, not an independently approved benchmark, a first-pass reliability improvement, or evidence that ranking/topic quality meets calibrated thresholds. The temporal rerun required five bounded repairs; its predecessor required two. Raw payloads, local stores, model requests and reviewer custody are intentionally excluded from this PR.
These observations predate the later choice-only Wiki and restricted topic-reconciliation changes integrated from main. They do not constitute a live rerun or qualification of the combined decision policy.
Risks and follow-up