Repository navigation
feat(memory): add semantic dogfood ops - #652
Conversation
Add admin dogfood topic seeding, session-scoped memory review listing, and explicit global semantic rebuild confirmation.\n\nVerification:\n- git diff --check\n- uv run ruff format --check src/coding_agent/cli/remote_commands.py src/coding_agent/remote/client.py src/coding_agent/server/http_server.py src/coding_agent/server/schemas.py src/coding_agent/server/session_manager.py src/coding_agent/topics/store.py src/coding_agent/stores/durable_pg.py src/coding_agent/stores/durable_local.py tests/cli/test_remote_client.py tests/ui/test_http_server.py\n- uv run ruff check src/coding_agent/cli/remote_commands.py src/coding_agent/remote/client.py src/coding_agent/server/http_server.py src/coding_agent/server/schemas.py src/coding_agent/server/session_manager.py src/coding_agent/topics/store.py src/coding_agent/stores/durable_pg.py src/coding_agent/stores/durable_local.py tests/cli/test_remote_client.py tests/ui/test_http_server.py\n- uv run pytest -q tests/ui/test_http_server.py::TestSemanticMemoryMaintenance tests/ui/test_http_server.py::TestMemoryReviewTransitions tests/cli/test_remote_client.py\n- uv run pytest -q tests/coding_agent/test_topic_store_contract.py tests/coding_agent/test_sqlite_topic_store.py tests/coding_agent/test_topic_store.py tests/coding_agent/test_topic_lifecycle.py tests/coding_agent/test_semantic_maintenance.py tests/coding_agent/test_semantic_sync.py tests/coding_agent/test_semantic_recall.py tests/coding_agent/test_semantic_tape_index.py tests/coding_agent/test_pg_durable_fencing.py tests/coding_agent/test_sqlite_local_durable_fencing.py
|
Warning Review limit reached
More reviews will be available in 40 minutes and 10 seconds. Learn how PR review limits work. Your organization has used up its prepaid credits, and credit purchases are no longer available. Enable the review add-on in the billing tab to keep reviews running — you're only billed for reviews past your plan's rate limits ($0.25/file). ⌛ How to resolve this issue?After more reviews become available, a review can be triggered using the 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 credits. 🚦 How do rate 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 see our Fair Usage Limits Policy for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (4)
📝 WalkthroughWalkthroughAdds two new REST endpoints ( ChangesSemantic Memory Extensions
Estimated code review effort🎯 4 (Complex) | ⏱️ ~60 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
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. Comment |
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 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/src/coding_agent/remote/client.py`:
- Around line 393-397: The list_remote_memory_reviews flow is still using user
auth only, so requests can fail when only an admin token is configured. Update
the authentication used by the remote memory reviews helper in client.py to
match the adjacent semantic-memory methods by falling back to
admin_auth_headers(endpoint) when user auth is unavailable, and make sure the
request path-building logic in list_remote_memory_reviews() remains unchanged.
In `@coding-agent/src/coding_agent/server/session_manager.py`:
- Around line 1490-1503: `propose_memory_candidate_from_topic(finalized)` is
currently executed outside the warning-handled failure path, so proposal errors
can escape after the topic is already finalized. Move the proposal call into the
same `try` block in `session_manager.py` that already wraps
`review_store.add_candidate`, and handle any exception there by logging a
warning and appending it to `warnings`, just like the existing candidate-write
failure path. Keep the control flow in `session_manager.py` centered around
`memory_write_enabled`, `review_store.candidate_writes_enabled`, and
`add_candidate` so proposal and write failures are both treated as non-fatal
warnings.
In `@coding-agent/tests/ui/test_http_server.py`:
- Around line 323-330: The _runtime_ctx helper is replacing an explicitly
provided empty Tape because it uses a truthiness fallback. Update the tape
selection in _runtime_ctx to preserve any non-None Tape instance passed by the
caller, even when it is empty, and only create a new Tape when tape is None.
Keep the change localized to the SimpleNamespace construction so the injection
hook continues to work for blank tapes.
🪄 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: 0dbc3fa9-f5d2-4bd4-8215-12da58acedac
📒 Files selected for processing (11)
coding-agent/docs/adr/0072-tape-memory-semantic-index-and-enable-switch.mdcoding-agent/src/coding_agent/cli/remote_commands.pycoding-agent/src/coding_agent/remote/client.pycoding-agent/src/coding_agent/server/http_server.pycoding-agent/src/coding_agent/server/schemas.pycoding-agent/src/coding_agent/server/session_manager.pycoding-agent/src/coding_agent/stores/durable_local.pycoding-agent/src/coding_agent/stores/durable_pg.pycoding-agent/src/coding_agent/topics/store.pycoding-agent/tests/cli/test_remote_client.pycoding-agent/tests/ui/test_http_server.py
Handle memory-review auth fallback, candidate proposal failures, and empty-tape test injection.\n\nVerification:\n- git diff --check\n- uv run ruff format --check src/coding_agent/remote/client.py src/coding_agent/server/session_manager.py tests/cli/test_remote_client.py tests/ui/test_http_server.py\n- uv run ruff check src/coding_agent/remote/client.py src/coding_agent/server/session_manager.py tests/cli/test_remote_client.py tests/ui/test_http_server.py\n- uv run pytest -q tests/ui/test_http_server.py::TestSemanticMemoryMaintenance tests/ui/test_http_server.py::TestMemoryReviewTransitions tests/cli/test_remote_client.py\n- uv run pytest -q tests/coding_agent/test_semantic_maintenance.py tests/coding_agent/test_semantic_sync.py tests/coding_agent/test_semantic_recall.py tests/coding_agent/test_semantic_tape_index.py tests/coding_agent/test_topic_store_contract.py tests/coding_agent/test_sqlite_topic_store.py tests/coding_agent/test_topic_store.py tests/coding_agent/test_topic_lifecycle.py tests/coding_agent/test_pg_durable_fencing.py tests/coding_agent/test_sqlite_local_durable_fencing.py
Summary
confirm_globalfor semantic rebuild because rebuild clears the global semantic backend.delete_topiccleanup support for PG/SQLite topic stores and fenced durable stores so failed dogfood core writes can compensate safely.Review Gate
Verification
git diff --checkuv run ruff format --check src/coding_agent/cli/remote_commands.py src/coding_agent/remote/client.py src/coding_agent/server/http_server.py src/coding_agent/server/schemas.py src/coding_agent/server/session_manager.py src/coding_agent/topics/store.py src/coding_agent/stores/durable_pg.py src/coding_agent/stores/durable_local.py tests/cli/test_remote_client.py tests/ui/test_http_server.pyuv run ruff check src/coding_agent/cli/remote_commands.py src/coding_agent/remote/client.py src/coding_agent/server/http_server.py src/coding_agent/server/schemas.py src/coding_agent/server/session_manager.py src/coding_agent/topics/store.py src/coding_agent/stores/durable_pg.py src/coding_agent/stores/durable_local.py tests/cli/test_remote_client.py tests/ui/test_http_server.pyuv run pytest -q tests/ui/test_http_server.py::TestSemanticMemoryMaintenance tests/ui/test_http_server.py::TestMemoryReviewTransitions tests/cli/test_remote_client.pyuv run pytest -q tests/coding_agent/test_topic_store_contract.py tests/coding_agent/test_sqlite_topic_store.py tests/coding_agent/test_topic_store.py tests/coding_agent/test_topic_lifecycle.py tests/coding_agent/test_semantic_maintenance.py tests/coding_agent/test_semantic_sync.py tests/coding_agent/test_semantic_recall.py tests/coding_agent/test_semantic_tape_index.py tests/coding_agent/test_pg_durable_fencing.py tests/coding_agent/test_sqlite_local_durable_fencing.pySummary by CodeRabbit
New Features
Bug Fixes