Skip to content

docs(memory): close semantic memory docs - #662

Merged
delete-cloud merged 3 commits into
mainfrom
docs/memory-docs-closeout
Jul 2, 2026
Merged

delete-cloud merged 3 commits into
mainfrom
docs/memory-docs-closeout

Conversation

@delete-cloud

@delete-cloud delete-cloud commented Jul 2, 2026 •

Copy link
Copy Markdown
Owner

Summary

  • accept ADR-0072 and ADR-0073 now that semantic memory and SQLite TopicStore work has landed
  • update topic-layer and architecture docs with current semantic memory source-of-truth, Helm/o6n opt-in, supported backends, and KB defer behavior
  • keep scope explicit: no default semantic memory enablement, no o6n rollout, no Chroma/Milvus/pgvector adapter

Verification

  • git diff --check -- docs/adr/0072-tape-memory-semantic-index-and-enable-switch.md docs/adr/0073-sqlite-topic-store-parity.md docs/topic_layer/USAGE.md docs/CODING-AGENT-ARCHITECTURE.md
  • uv run pytest tests/coding_agent/test_topic_store_contract.py tests/coding_agent/test_topic_store.py tests/coding_agent/test_sqlite_topic_store.py tests/coding_agent/test_sqlite_local_durable_fencing.py tests/ui/test_session_manager_runtime.py tests/coding_agent/test_runtime_preparation.py tests/ui/test_http_server.py tests/coding_agent/test_semantic_maintenance.py tests/deploy/test_helm_chart.py tests/coding_agent/test_memory_switch.py tests/coding_agent/test_semantic_recall.py --collect-only -q
  • uv run pytest tests/coding_agent/test_semantic_recall.py -k "current_query or derived_current_query or deterministic_topics_stay_first or semantic_refill" -q
  • uv run pytest tests/deploy/test_helm_chart.py -k "memory_semantic or semantic_memory or defer_when_semantic_memory_hits or local_sqlite_topic_store_path" -q
  • uv run pytest tests/ui/test_session_manager_runtime.py::test_sqlite_durable_semantic_rebuild_recalled_by_later_build_context_without_backend_hit_text -q
  • uv run pytest tests/coding_agent/test_semantic_maintenance.py -k "factory or topic_store_available or rebuild_requires_topic_store" -q

Summary by CodeRabbit

  • Documentation
    • Updated memory and semantic recall docs to reflect the current configuration, including read/write controls and default-disabled semantic memory.
    • Clarified how semantic hits are refreshed from authoritative stores and how semantic recall interacts with KB context.
    • Documented supported semantic backends and deployment settings for enabling the feature.
    • Marked multiple design notes as accepted and aligned the storage guidance for local vs. multi-instance setups.

@coderabbitai

coderabbitai Bot commented Jul 2, 2026 •

Copy link
Copy Markdown
Contributor

Review Change Stack

Warning

Review limit reached

@delete-cloud, you've reached your PR review limit, so we couldn't start this review.

Next review available in: 50 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details
⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro Plus

Run ID: 3ae4f9f9-caf2-4165-bd19-9df5f8026acd

📥 Commits

Reviewing files that changed from the base of the PR and between d32cea4 and 5e0ad5b.

📒 Files selected for processing (2)
  • coding-agent/docs/CODING-AGENT-ARCHITECTURE.md
  • coding-agent/docs/topic_layer/USAGE.md
📝 Walkthrough

Walkthrough

This PR updates documentation only, revising the architecture doc's Memory Grounding section, promoting ADR-0072 and ADR-0073 from Proposed to Accepted with updated decisions and acceptance checklists, and adding a new Semantic Memory section to the topic layer usage guide.

Changes

Memory and semantic memory documentation

Layer / File(s) Summary
Memory grounding architecture doc rewrite
coding-agent/docs/CODING-AGENT-ARCHITECTURE.md
Replaces the old two-mode MemoryPlugin description with a configuration-driven model ([memory].enabled, read_enabled, write_enabled), documents semantic memory plugin registration/behavior and semantic-vs-KB ordering.
ADR-0072 acceptance and decision updates
coding-agent/docs/adr/0072-tape-memory-semantic-index-and-enable-switch.md
Status changed from Proposed to Accepted; refines Decision B wording, generalizes destructive rebuild failure conditions, expands the backend contract test suite requirement, and appends checked acceptance criteria items.
ADR-0073 acceptance and decision updates
coding-agent/docs/adr/0073-sqlite-topic-store-parity.md
Status changed from Proposed to Accepted; rewrites decision on SessionManager.selected_topic_store() selection/fallback rules, updates SQLiteTopicStore parity wording, adds upgrade test and Helm/o6n derivation details, and converts the acceptance checklist to fully checked proofs.
Topic layer usage guide semantic memory section
coding-agent/docs/topic_layer/USAGE.md
Adds a new "Semantic Memory" section covering recall rehydration, supported backends, default-disabled opt-in configuration, and KB deferral ordering.

Estimated code review effort: 2 (Simple) | ~10 minutes

Possibly related PRs

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title clearly matches the main change: updating and closing out semantic memory documentation.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch docs/memory-docs-closeout

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands.

@delete-cloud
delete-cloud marked this pull request as ready for review July 2, 2026 01:42

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@coding-agent/docs/CODING-AGENT-ARCHITECTURE.md`:
- Around line 967-973: Update the SemanticMemoryPlugin registration note to
reflect the real gate in app setup: it is only registered when semantic memory
is enabled and effective memory read is on, not by [memory.semantic].enabled
alone. In the architecture doc section describing SemanticMemoryPlugin and the
backend adapters, clarify that the registration behavior follows the logic in
coding_agent/core/app.py and aligns with the read-disabled expectation so
operators do not treat the semantic toggle as independent from the memory read
switch.
🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

  • Push a commit to this branch (recommended)
  • Create a new PR with the fixes

ℹ️ Review info
⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro Plus

Run ID: fedfda6c-873b-42d5-9612-df084eab7e99

📥 Commits

Reviewing files that changed from the base of the PR and between 5615771 and d32cea4.

📒 Files selected for processing (4)
  • coding-agent/docs/CODING-AGENT-ARCHITECTURE.md
  • coding-agent/docs/adr/0072-tape-memory-semantic-index-and-enable-switch.md
  • coding-agent/docs/adr/0073-sqlite-topic-store-parity.md
  • coding-agent/docs/topic_layer/USAGE.md

@delete-cloud
delete-cloud merged commit 5649d06 into main Jul 2, 2026
2 checks passed
@delete-cloud
delete-cloud deleted the docs/memory-docs-closeout branch July 2, 2026 01:56
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.

1 participant