cleveragents/cleveragents-core
4
0
Fork 3
Code Issues 6.0k Pull Requests 115 Actions Packages Projects Releases Wiki Activity

feat(acms): integrate FAISS into ACMS vector backend protocol #1165

Merged
aditya merged 1 commits from feature/m6-faiss-acms-backend into master 2026-03-30 13:40:25 +00:00
Conversation 4 Commits 1 Files Changed 6
+1048 -14
aditya commented 2026-03-26 13:14:54 +00:00
Member
Copy Link
Copy Source

Summary

  • add FAISS-backed ACMS read/write adapters on top of the shared VectorStoreService and wire them through the DI container with config-driven fallback to in-memory stubs when FAISS is unavailable
  • add Behave coverage for indexing, scoped similarity search, removal, config-driven embeddings, and DI resolution, plus ASV coverage for ACMS vector search latency
  • address review feedback by keeping the branch scoped to FAISS backend work and replacing the loose vector-store cache typing with explicit FAISS store protocols instead of Any

Validation

  • TEST_PROCESSES=9 nox -s lint
  • TEST_PROCESSES=9 nox -s typecheck
  • TEST_PROCESSES=9 nox -s unit_tests -- features/faiss_vector_backend.feature
  • TEST_PROCESSES=9 nox -s coverage_report -- features/faiss_vector_backend.feature (feature scenarios passed; repo-wide 97% coverage is not meaningful on a single-feature subset)

Notes

  • Rebased on the latest master before force-pushing the review fixes.
  • ASV measurements for the new benchmark were approximately 0.0001066s / 0.0001235s for project search and 0.0000844s / 0.0000965s for scoped similarity search on 250 / 1000 documents.
  • The issue's 10M-corpus benchmark acceptance checkbox remains unchecked because this environment validated the benchmark implementation and representative timings, but did not empirically execute a 10M embedding corpus run.

Closes #871

## Summary - add FAISS-backed ACMS read/write adapters on top of the shared `VectorStoreService` and wire them through the DI container with config-driven fallback to in-memory stubs when FAISS is unavailable - add Behave coverage for indexing, scoped similarity search, removal, config-driven embeddings, and DI resolution, plus ASV coverage for ACMS vector search latency - address review feedback by keeping the branch scoped to FAISS backend work and replacing the loose vector-store cache typing with explicit FAISS store protocols instead of `Any` ## Validation - `TEST_PROCESSES=9 nox -s lint` - `TEST_PROCESSES=9 nox -s typecheck` - `TEST_PROCESSES=9 nox -s unit_tests -- features/faiss_vector_backend.feature` - `TEST_PROCESSES=9 nox -s coverage_report -- features/faiss_vector_backend.feature` (feature scenarios passed; repo-wide 97% coverage is not meaningful on a single-feature subset) ## Notes - Rebased on the latest `master` before force-pushing the review fixes. - ASV measurements for the new benchmark were approximately `0.0001066s` / `0.0001235s` for project search and `0.0000844s` / `0.0000965s` for scoped similarity search on 250 / 1000 documents. - The issue's 10M-corpus benchmark acceptance checkbox remains unchecked because this environment validated the benchmark implementation and representative timings, but did not empirically execute a 10M embedding corpus run. Closes #871
aditya added this to the v3.6.0 milestone 2026-03-26 13:15:04 +00:00
aditya added the
Type
Feature
 label 2026-03-26 13:15:12 +00:00
aditya requested review from freemo 2026-03-26 13:17:11 +00:00
aditya force-pushed feature/m6-faiss-acms-backend from 9518ac3e44 to 68c5319e9c 2026-03-26 13:21:04 +00:00 Compare
freemo commented 2026-03-27 17:14:01 +00:00
Owner
Copy Link
Copy Source

Code Review Note

Unable to review — the branch feature/m6-faiss-acms-backend was not found on the remote. Please verify the branch exists and has been pushed.

## Code Review Note **Unable to review** — the branch `feature/m6-faiss-acms-backend` was not found on the remote. Please verify the branch exists and has been pushed.
freemo approved these changes 2026-03-30 04:21:49 +00:00
Dismissed
freemo left a comment
Owner
Copy Link
Copy Source

Review: APPROVED with Comments

Solid FAISS integration with config-driven fallback.

Notes

  1. Isolate unrelated changes: wrapping.py semgrep comment changes and E2E Robot key-skip additions are tangential. Per CONTRIBUTING.md §Atomic Commits, these should be separate commits.
  2. _cache type annotation changed from dict[int, FAISS] to dict[int, Any] — loses type safety. Restore the proper annotation.
  3. Good: Thread-safe design, graceful in-memory fallback, argument validation, BDD tests + ASV benchmark.
## Review: APPROVED with Comments Solid FAISS integration with config-driven fallback. ### Notes 1. **Isolate unrelated changes**: `wrapping.py` semgrep comment changes and E2E Robot key-skip additions are tangential. Per CONTRIBUTING.md §Atomic Commits, these should be separate commits. 2. **`_cache` type annotation changed** from `dict[int, FAISS]` to `dict[int, Any]` — loses type safety. Restore the proper annotation. 3. **Good**: Thread-safe design, graceful in-memory fallback, argument validation, BDD tests + ASV benchmark.
freemo commented 2026-03-30 05:15:38 +00:00
Owner
Copy Link
Copy Source

Day 50 Planning — Branch availability required.

The branch feature/m6-faiss-acms-backend was reported as not found on remote since Day 48. This PR integrates FAISS into the ACMS vector backend protocol (v3.6.0).

@freemo — Please push the branch or confirm status. Reviewers assigned.

Day 50 Planning — **Branch availability required.** The branch `feature/m6-faiss-acms-backend` was reported as not found on remote since Day 48. This PR integrates FAISS into the ACMS vector backend protocol (v3.6.0). @freemo — Please push the branch or confirm status. Reviewers assigned.
aditya force-pushed feature/m6-faiss-acms-backend from 68c5319e9c to e618a93563 2026-03-30 10:40:40 +00:00 Compare
aditya dismissed freemo's review 2026-03-30 10:40:40 +00:00
Reason:

New commits pushed, approval review dismissed automatically according to repository settings

aditya commented 2026-03-30 10:41:10 +00:00
Author
Member
Copy Link
Copy Source

Addressed the review notes and force-pushed an updated branch.

Review items resolved:

  1. Removed the unrelated wrapping.py semgrep-annotation edits and the Robot E2E OPENAI_API_KEY skip changes so this PR is scoped only to the FAISS ACMS backend work.
  2. Replaced the loose VectorStoreService cache typing with explicit FAISS store protocols instead of Any, preserving static typing without reintroducing the optional-import issue.
  3. Rebased the branch on the latest master before pushing the fix round.

Validation for this review round:

  • nox -s lint
  • nox -s typecheck
  • nox -s unit_tests
  • nox -s coverage_report
Addressed the review notes and force-pushed an updated branch. Review items resolved: 1. Removed the unrelated `wrapping.py` semgrep-annotation edits and the Robot E2E `OPENAI_API_KEY` skip changes so this PR is scoped only to the FAISS ACMS backend work. 2. Replaced the loose `VectorStoreService` cache typing with explicit FAISS store protocols instead of `Any`, preserving static typing without reintroducing the optional-import issue. 3. Rebased the branch on the latest `master` before pushing the fix round. Validation for this review round: - `nox -s lint` - `nox -s typecheck` - `nox -s unit_tests` - `nox -s coverage_report`
aditya force-pushed feature/m6-faiss-acms-backend from e618a93563 to dde49dfc52 2026-03-30 11:08:11 +00:00 Compare
aditya force-pushed feature/m6-faiss-acms-backend from dde49dfc52 to 1250041356 2026-03-30 11:37:47 +00:00 Compare
aditya force-pushed feature/m6-faiss-acms-backend from 1250041356 to 4b9e5a9836 2026-03-30 12:00:17 +00:00 Compare
aditya force-pushed feature/m6-faiss-acms-backend from 4b9e5a9836 to af2114c043 2026-03-30 12:20:11 +00:00 Compare
aditya scheduled this pull request to auto merge when all checks succeed 2026-03-30 12:25:42 +00:00
aditya force-pushed feature/m6-faiss-acms-backend from af2114c043 to eff446f5e8 2026-03-30 13:19:09 +00:00 Compare
aditya scheduled this pull request to auto merge when all checks succeed 2026-03-30 13:27:11 +00:00
aditya merged commit f03e510a11 into master 2026-03-30 13:40:25 +00:00
aditya deleted branch feature/m6-faiss-acms-backend 2026-03-30 13:40:26 +00:00
Sign in to join this conversation.
Reviewers
No Reviewers
Labels
Clear labels
auto/needs-reevaluation
Controller deferred this PR; awaiting Phase 6+ scope-evaluator or operator re-enablement.
 controller-managed
Auto-agents controller manages this PR/issue (see tools/controller/deploy/RUNBOOK.md). Remove this label to abandon controller management.
 overdue
auto/blocked-by-deps
PR blocked by an open issue dependency. Operator must close the dep (or remove the dependency link) before the merge driver can act. Auto-cleared by merge_drive when no open deps remain.
 auto/ci-timeout
Most recent merge cycle hit CI timeout. Driver excludes this PR while last merge_cycle row is < 30 min old; label persists thereafter as visible history.
 auto/claimed-implementer
Currently being processed by an implementer worker.
 auto/claimed-merge
Currently being processed by the merge driver.
 auto/claimed-reviewer
Currently being processed by a reviewer worker.
 auto/driver-down
Merge driver heartbeat stale; pipeline halted. Closed automatically on next clean tick.
 auto/invariant-violation
Detected master commit violating the strict merge invariant. Tracked as an issue (not a PR label); kept here for label completeness.
 auto/last-attempt-tier-0
In-cycle escalation: most recent attempt ran at the Tier 0 slot (`tier-0`). Slot's model defined in .opencode/models/tiers.yaml.
 auto/last-attempt-tier-1
In-cycle escalation: most recent attempt ran at the Tier 1 slot (`tier-1`). Slot's model defined in .opencode/models/tiers.yaml.
 auto/last-attempt-tier-2
In-cycle escalation: most recent attempt ran at the Tier 2 slot (`tier-2`). Slot's model defined in .opencode/models/tiers.yaml. Gated behind IMPLEMENTER_ESCALATION_TIER2_ENABLED.
 auto/last-attempt-tier-min
In-cycle escalation: most recent attempt ran at the Tier -1 slot (`tier-min`). Slot's model defined in .opencode/models/tiers.yaml. Suffix is ``-min`` (not ``--1``) so the Forgejo UI reads naturally.
 Automation Tracking
Tracking issues used by the AI Automation system for agents to communicate and report.
 auto/needs-conflict-resolution
Rebase conflict needs LLM conflict-resolver.
 auto/needs-implementer
Failing CI needs implementer attention.
 auto/postmortem
Documenting a driver incident or rollback.
 auto/ready-to-merge
Reviewer has APPROVED this PR and no later REQUEST_CHANGES is outstanding. The merge driver requires this label to even consider a PR for merging. Set by the reviewer worker on APPROVE; cleared on REQUEST_CHANGES.
 auto/restart-throttled
Train repeatedly lost master-tempo races. Driver excludes via merge_cycle until cooldown elapses; label persists as visible history.
 auto/revert
Revert PR backing out an invariant violation. Fast-tracked through the merge driver.
 auto/sentinel
Sentinel PR duplicated from upstream into a personal fork by tools/duplicate_prs_to_fork.py for pipeline testing. Lives only in the fork; the canonical pipeline never sees it.
 auto/stale-inactivity
No implementer activity for N days. Flagged for human review. Auto-cleared on next push to head branch.
 auto/unstable
Repeatedly fails on current master (>= 3 ci-fail-on-rebased-sha releases in 12 h). Excluded from driver until human triage.
 Blocked
A ticket in a blocked state and unable to complete until some other task is completed first.
Bounty
$100
A bounty of $100 for any open-source contributor who provides a MR that solves this issue
Bounty
$1000
A bounty of $1000 for any open-source contributor who provides a MR that solves this issue
Bounty
$10000
A bounty of $10000 for any open-source contributor who provides a MR that solves this issue
Bounty
$20
A bounty of $20 for any open-source contributor who provides a MR that solves this issue
Bounty
$2000
A bounty of $2000 for any open-source contributor who provides a MR that solves this issue
Bounty
$250
A bounty of $250 for any open-source contributor who provides a MR that solves this issue
Bounty
$50
A bounty of $50 for any open-source contributor who provides a MR that solves this issue
Bounty
$500
A bounty of $500 for any open-source contributor who provides a MR that solves this issue
Bounty
$5000
A bounty of $5000 for any open-source contributor who provides a MR that solves this issue
Bounty
$750
A bounty of $750 for any open-source contributor who provides a MR that solves this issue
MoSCoW
Could have
Could have feature in order to satisfy the epic/legendary.
MoSCoW
Must have
Must have feature in order to satisfy the epic/legendary.
MoSCoW
Should have
Should have feature in order to satisfy the epic/legendary.
Needs Feedback
There are questions in the ticket that can not be completed until the project owner provides clarity.
Points
1
1 man-hours worth of work for an expert with no learning curve.
Points
13
13 man-hours worth of work for an expert with no learning curve.
Points
2
2 man-hours worth of work for an expert with no learning curve.
Points
21
21 man-hours worth of work for an expert with no learning curve.
Points
3
3 man-hours worth of work for an expert with no learning curve.
Points
34
34 man-hours worth of work for an expert with no learning curve.
Points
5
5 man-hours worth of work for an expert with no learning curve.
Points
55
55 man-hours worth of work for an expert with no learning curve.
Points
8
8 man-hours worth of work for an expert with no learning curve.
Points
88
88 man-hours worth of work for an expert with no learning curve.
Priority
Backlog
This ticket has backlogged priority and is not to be worked on yet
Priority
CI Blocker
Critical priority issue that blocks CI/CD pipeline and prevents PR merges
Priority
Critical
The priority is critical
Priority
High
The priority is high
Priority
Low
The priority is low
Priority
Medium
The priority is medium
Signed-off: Owner
When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.
 Signed-off: Scrum Master
When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.
 Signed-off: Tech Lead
When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.
 Spike
A ticket for learning a tool or technology that is needed to be able to do future planning and design.
State
Completed
The ticket has been fully implemented, completed, and merged with the source code. This label should only be applied once a ticket is closed.
State
Duplicate
A ticket that represents the same content as an existing ticket.
State
In Progress
A ticket that is actively being developed.
State
In Review
A ticket that has had some code completed to implement but is waiting to pass peer review and is not yet merged in.
State
Paused
This ticket's work started but wasn't finished. It's on hold (likely in a feature branch) and will be resumed later, either due to a blocker or a delay.
State
Unverified
All new tickets start in this state. A developer may set it to show the ticket is unverified. This means we haven't agreed to work on it. It will either move to a verified state or be closed as wontdo.
State
Verified
The issue has been verified by a developer as legitimate. It will be worked on and verified tickets are now considered part of the backlog.
State
Wont Do
This ticket has been decided it wont be done. This may mean the bug has been determined to not be real (cant verify) or the feature is one we have decided we dont want to adopt.
Type
Automation
Any edits or discussion about the AI automated coding system.
Type
Bug
Something that doesnt work as intended.
Type
Discussion
Anytime a ticket represents a discussion about a subject and doesnt fall into one of the other categories.
Type
Documentation
An error or improvement needed in the documentation.
Type
Epic
Any first tier epic. That is, an epic which contains only issues as children and will not have sub-epics.
Type
Feature
Some new functionality not present.
Type
Legendary
A type of Epic which will contain other Epics.
Type
Refactor
A code change that restructures existing code without changing its external behavior.
Type
Support
Someone needs help using the project.
Type
Task
A generic task that doesnt fit into the other type categories.
Type
Testing
Work exclusively focusing on fixing or expanding testing.
No Label
Type
Feature
Milestone
No items
No Milestone v3.6.0
Projects
Clear projects
No project
Assignees
Clear assignees
aditya (Aditya Chhabra) aleenaumair (Aleena Umair) brent.edwards (Brent Edwards) CoreRasurae (Luis Mendes) drew (Drew Morris) eugen.thaci (Eugen Thaci) freemo (Jeffrey Phillips Freeman) HAL9000 (HAL 9000) HAL9001 (HAL9001) hamza.khyari (Hamza Khyari) hurui200320 (Rui Hu) justin.morris khird (Kyle Hird) org.cleveragents
No Assignees
2 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: cleveragents/cleveragents-core#1165
Delete Branch "feature/m6-faiss-acms-backend"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?