Skip to content

docs: refresh README + CHANGELOG for 2026-05-15 postgres cutover complete - #81

Merged
jphein merged 1 commit into
mainfrom
docs/refresh-readme-cutover-state
May 15, 2026
Merged

docs: refresh README + CHANGELOG for 2026-05-15 postgres cutover complete#81
jphein merged 1 commit into
mainfrom
docs/refresh-readme-cutover-state

Conversation

@jphein

@jphein jphein commented May 15, 2026

Copy link
Copy Markdown
Collaborator

Summary

README header was stale; CHANGELOG was last touched at `[3.3.5] — 2026-05-09`. This PR refreshes both to reflect that the substrate cutover finished, the fork moved to `techempower-org`, and 8/9 bench suites pass on the new backend.

What was stale

Before After
Repo identity "jphein fork of milla-jovovich/mempalace" "techempower-org fork of MemPalace/mempalace"
Shield links jphein/mempalace techempower-org/mempalace
Production palace "~160K-drawer palace behind palace-daemon (jphein/palace-daemon)" "273K-drawer Postgres + pgvector + Apache AGE palace behind palace-daemon (techempower-org)"
Fork-ahead commits ~14 ~434
Substrate section "implementation in flight on `feat/pgvector-age-impl`" "shipped on `main` and serving production traffic"
Storage layer (four layers) "running … migration on the in-flight branch" "on `main` as of 2026-05-15"
Plan-B trigger 2026-06-08 superseded — cutover happened on our timeline

CHANGELOG `[Unreleased]` adds

  • Postgres + pgvector + AGE production cutover
  • Hybrid retrieval (`candidate_strategy="hybrid"`)
  • `symbol_header_prefix` kwarg on `chunk_text`
  • n=200 git-derived probe set + generator + `--probes` flag in `chunk_strategy_ablation`
  • `verify_rrf_ftcode5k.py` + `verify_rrf_3way.py` (3-way RRF on n=200: +0.0841 MRR vs best solo)
  • 8/9 bench suites pass, JSON captured
  • pgvector lazy-index race fix at `4566f8a`
  • `EmbeddingFunction.embed_query` doc warning (PR #80)
  • Cherry-pick of @nakata-app's upstream #1490
  • Operator follow-ups on #665 and discussion #1384

Out of scope

Three sections still reference "in-flight" / "cherry-pick" framings — those entries are correct historical narrative for what was done (specific commits cherry-picked from upstream PRs at specific dates), so leaving them alone. A future pass can decide whether to reframe as "historical inventory".

Test plan

  • Header reads cleanly top-to-bottom; no broken internal anchors.
  • CHANGELOG renders as Keep-a-Changelog format.
  • Cross-references to the bench JSON + runbook resolve.

🤖 Generated with Claude Code

…lete

README header was stale: said \"JP's fork of milla-jovovich/mempalace\"
(actual upstream is MemPalace/mempalace), pointed at jphein/* shields
and links (we transferred to techempower-org), reported a 160K-drawer
chromadb palace (now 273K-drawer postgres+pgvector+AGE), and described
the substrate cutover as in-flight on feat/pgvector-age-impl (cutover
shipped to main on 2026-05-13–15).

Refreshes:

* Title + author line + shield links → techempower-org
* Production palace size + backend → 273K-drawer postgres
* Substrate section status block → shipped, with refs to the operator
  runbook and bench artifact
* Storage layer bullet → "main as of 2026-05-15; chromadb path still
  works behind MEMPALACE_BACKEND=chroma"

CHANGELOG: new [Unreleased] section above [3.3.5] capturing the
fork-side work that landed 2026-05-14 / 2026-05-15 — postgres cutover,
hybrid retrieval (vector ∪ BM25 ∪ graph), symbol_header_prefix kwarg,
n=200 git-derived probe set, RRF verifier (2-way + 3-way), bench
captures, the pgvector lazy-index race fix, the EmbeddingFunction
.embed_query doc note, and the @nakata-app MemPalace#1490 cherry-pick.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Copilot AI review requested due to automatic review settings May 15, 2026 07:45

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot encountered an error and was unable to review this pull request. You can try again by re-requesting a review.

@jphein
jphein merged commit af3794c into main May 15, 2026
3 of 4 checks passed
@jphein
jphein deleted the docs/refresh-readme-cutover-state branch May 15, 2026 07:53
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants