diff options
| author | Aman Kumar <145339995+amankumarsingh77@users.noreply.github.com> | 2026-06-29 00:02:54 +0530 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2026-06-29 00:02:54 +0530 |
| commit | 0b32e88f84f36a759d7191e8bdfd09a44789fa95 (patch) | |
| tree | 832fb2e1d636e2c979384fd78e2910e02a74db2e /package.json | |
| parent | 9f428cceb9c070e01df43dd55633c22678b8c406 (diff) | |
feat: address elements by stable refs across re-renders (#8)
Interaction tools could only target elements by raw viewport coordinates
(browser_click) or model-guessed CSS selectors (browser_fill/focus/
select_option/upload). Neither survives a re-render: on React/SPA forms,
every save or edit reflows the page, so captured @(x,y) coordinates go
stale and guessed selectors miss — leaving the agent to fall back to
hand-rolled execute_js DOM walks and unnoticed failed saves.
Add a stable ref system, mirroring Playwright MCP / browser-use:
- snapshot assigns each interactive element a ref (e1, e2, …), shown as
[eN] in the outline, and publishes a per-tab ref → backendNodeId map
- interaction tools accept an optional `ref` that re-resolves the element
at call time (via DOM.resolveNode / getBoxModel), so it stays valid
across re-renders; coordinates/selectors remain as fallbacks
- mutating tools append a compact diff of changed / newly-appeared (*) /
removed interactive elements, so silent failed saves surface immediately
- stale refs return an actionable "re-snapshot" error instead of a miss
Ref map is replaced per snapshot (bounded memory); fill keeps the native
_valueTracker write path so React controlled inputs still update.
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Diffstat (limited to 'package.json')
| -rw-r--r-- | package.json | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/package.json b/package.json index e7768b5..9219afe 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "pi-browser-harness", - "version": "0.6.0", + "version": "0.7.0", "description": "Browser control extension for pi — navigate, click, type, screenshot, and extract data from real Chrome via CDP", "keywords": [ "pi-package", |