Back to the room

Pass 3 of 3 · Deep dive of PHAROSPass 1 · OverviewPass 2 · How it works

Code Observatory / History

What changed, commit by commit.

Selected decisions from the Git history. Dates and sizes come from the commits. A reason appears only where the commit itself records one.

GIT HISTORY Every entry links its commit at the repository. This is a selection, not the whole log.

PHAROS at 975a38dMIT license

15 milestones

  1. service

    The knowledge-management product is removed

    Annotations, authority, scholarly, quality, collections and auth modules were deleted, along with unused Celery tasks. 25,792 lines left the tree, and the commit states that PHAROS is now a focused code-intelligence backend.

    f9858586 refactor: Phase 2 — amputate Neo Alexandria 91 files, +147 −25,792

  2. service

    Module boundaries become a CI gate

    Shared utilities moved to app/shared, cross-module imports were cut, and the commit message reports zero isolation violations with the CI gate made hard.

    d566d715 refactor: Phase 3 — module isolation + Resource column surgery 13 files, +167 −75

  3. interface

    A real MCP server

    PHAROS mounted a native streamable-HTTP MCP server at /mcp, exposing retrieve_context and four graph and search tools at this commit. Existing REST endpoints were left as they were.

    572e754c feat(mcp): speak real MCP — streamable-HTTP server (plan 001) 8 files, +594 −9

  4. indexing

    Today's core: chunk-level indexing and hybrid retrieval

    A new app/codeintel replaced the old repository path. The commit records why: an audit found the old pipeline embedded every symbol but stored only the first symbol's vector, returned the first function of each file, and duplicated rows on re-ingest. Blob-SHA source verification and the conservative call graph first appear here.

    fced62c0 codeintel: chunk-level indexing, hybrid retrieval and context assembly 44 files, +6,054 −0

  5. storage

    Migrations squashed, code index schema added

    The migration chain was squashed into a baseline, with a second revision adding the tables and indexes the new core needs: repositories state, chunk columns, code_edges and ingestion_jobs, plus HNSW and GIN indexes on PostgreSQL.

    3620ffbe db: explicit drivers, honour DATABASE_URL, squash migrations 64 files, +1,331 −279

  6. interface

    Two tokens, and working MCP on the new core

    Authentication became one middleware with admin and read bearer tokens, compared in constant time and failing closed. The read token is limited to GETs and listed read-only POSTs.

    f8d37f02 api: scoped M2M auth, /api/v1 code-intelligence endpoints, working MCP 12 files, +1,776 −1,689

  7. evaluation

    Retrieval gets a benchmark

    The first retrieval benchmark report was added, with its modes, latency and storage measurements.

    7c17c196 bench: retrieval quality, latency, throughput and storage measurements 14 files, +13,017 −22

  8. service

    Free deployment with CPU embeddings

    A blueprint was added for a free in-process worker with CPU ONNX embeddings.

    0b017297 Merge pull request #2 from ram-tewari/deploy/new-prod-onnx 10 files, +255 −14

  9. retrieval

    Granite embeddings and dense by default

    Phase 1 changed the embedding model, the text that gets embedded, the default mode and the parsers. Choices were made on development sets, then measured once on two locked test sets.

    a9a80a38 Merge pull request #3 from ram-tewari/retrieval-phase1 55 files, +62,932 −138

  10. service

    Query embedding can run off the host

    The edge-onnx backend was added: the API asks a separate machine to embed queries and falls back to its own model when that machine is unreachable.

    838154ee Merge pull request #5 from ram-tewari/edge-query-embedding 10 files, +384 −4

  11. evaluation

    The memory evaluation is locked first

    The protocol and its task sets were committed before any memory code existed, fixing the primary measure in advance.

    91059434 Merge pull request #8 from ram-tewari/phase2-eval-protocol 6 files, +6,248 −1

  12. evaluation

    Memory fails its locked evaluation

    The run failed its primary source-file recall gate and its precision gate at 55% audited. Repository Q&A improved as a secondary result.

    bbe807e6 Merge pull request #13 from ram-tewari/phase2-locked-run 9 files, +22,891 −4

  13. evaluation

    Memory claims must prove themselves

    Counted claims gained tallies that the grounding check re-verifies, in response to the 55% result. Its precision on new data remains unmeasured.

    43d5bd3d Merge pull request #14 from ram-tewari/phase2-evidence 10 files, +774 −101

  14. evaluation

    The second evaluation stops with no verdict

    A second run was stopped at 66 of 80 tasks. The report gives partial numbers and no verdict. This is the commit every source link on this site is pinned to.

    975a38d5 Merge pull request #18 from ram-tewari/phase2-v2-partial 8 files, +38,983 −7