You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
- Memory-first: `memory_search(query)` before live fetch
108
+
- Performance inspection: check `_tool_metrics.total_duration_ms`; for `web_fetch`/`visual_scout`, inspect `metrics.phases` to see where time was spent.
Copy file name to clipboardExpand all lines: CHANGELOG.md
+14Lines changed: 14 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,6 +4,20 @@ Policy:
4
4
- Keep changes under **Unreleased** during normal development.
5
5
-`bash scripts/release.sh` automatically promotes `## Unreleased` → `## vX.Y.Z (YYYY-MM-DD)` and commits the changelog before tagging.
6
6
7
+
## Unreleased
8
+
9
+
### Changed
10
+
- Updated MCP tool descriptions and agent guidance to clarify that proxy use is optional by default, balanced fetches stay on the non-proxy/native path unless blocking signals appear, and all tool responses now expose timing information.
11
+
-`web_fetch` balanced-mode strategy now prefers the fast native HTTP path on normal server-rendered pages such as GitHub, only escalating into CDP earlier for proxy mode, high/aggressive mode, or known JS-heavy/problematic hosts.
12
+
13
+
### Added
14
+
- Added `_tool_metrics` total-duration reporting to all Cortex Scout MCP tool responses through the shared HTTP/stdio dispatch layer.
15
+
- Added structured phase timing metrics to `web_fetch`/scrape responses and `visual_scout` responses so slow steps can be identified without external profiling.
16
+
17
+
### Verified
18
+
- Re-tested the live MCP runtime after rebuild/reload and confirmed timing metrics now appear in `visual_scout`, `extract_fields`, and `proxy_control` responses.
19
+
- Re-tested the GitHub discussion fetch path through MCP and confirmed the same content path now completes in about 1.7 seconds instead of hanging for tens of seconds on the prior CDP-first behavior.
0 commit comments