Skip to content

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

Rust

docs: clarify file-index section references

AkitaOnRailseb74e0990518
diff --git a/docs/design-file-path-index.md b/docs/design-file-path-index.md
index edf39b64..a122828f 100644
--- a/docs/design-file-path-index.md
+++ b/docs/design-file-path-index.md
@@ -59,8 +59,9 @@ CREATE INDEX idx_observations_file_path
```
The column follows the V10 precedent. A row has at most one path in this
-version (3.2), so a side table would only add a join. Because the path lives on
-the observation row, every lifecycle operation in 3.5 applies to it with no new
+version (section 3.2), so a side table would only add a join. Because the path
+lives on the observation row, every lifecycle operation in section 3.5 applies
+to it with no new
code.
### 3.2 Where the path comes from
@@ -320,7 +321,7 @@ section 10, question 7.
- **A side table:** fits several paths per call (a multi-file `apply_patch`), at
the cost of a join and its own lifecycle. Deferred until multi-file calls are
in scope.
-- **The path inside `_ai_memory_capture`:** breaks older servers (3.2).
+- **The path inside `_ai_memory_capture`:** breaks older servers (section 3.2).
- **A protocol version bump:** same effect on older servers.
- **A hash instead of the path:** a repository path has little entropy, so the
hash hides little, and it makes the index unreadable for diagnosis.