@anvailabs/agentbrowser-mcp 1.10.0 → 1.11.0

package/README.md

@@ -21,13 +21,15 @@ responses, with a digest over complete descriptions and schemas. The existing re
 artifact check rejects drift. Regenerate after building with
 `node scripts/mcp-catalog-docs.mjs --write`.
 
-Delegated mode replaces create/close/cookies with `browser_session` (current control
-and pages) and `browser_operation` (operation status). `AGENTBROWSER_MODE` fixes one
-profile for the lifetime of the bridge connection. Reconnect to change profiles;
-clients may cache catalogs. Obtain the effective catalog from your own connection
-with `tools/list`; metadata never enlarges a session grant, and the service rejects a
-tool call that the bearer grant's profile does not allow even if a mismatched bridge
-advertises it.
+`browser_session` inspects metadata and pages when given a `sessionId`. On a delegated
+connection the binding supplies that ID and the same response also includes current
+control status. The tool requires both `session.control` and `page.observe`; application
+mode therefore does not expose it. Delegated mode removes create/close/cookies and adds
+`browser_operation` (operation status). `AGENTBROWSER_MODE` fixes one profile for the
+lifetime of the bridge connection. Reconnect to change profiles; clients may cache
+catalogs. Obtain the effective catalog from your own connection with `tools/list`;
+metadata never enlarges a session grant, and the service rejects a tool call that the
+bearer grant's profile does not allow even if a mismatched bridge advertises it.
 
 `qa`, `operations`, `appsec`, `bounty`, and `forms` currently project the complete
 browser catalog. `audit` omits bulk autofill. `application` exposes only delegated
@@ -68,6 +70,34 @@ receipt and preserve uncertain writes. For explicit heterogeneous steps use
 `browser_snapshot` → `browser_plan` — see the
 [main README](../../README.md#the-fast-path-for-forms-snapshot-then-plan).
 
+## Multiple pages and large research results
+
+`browser_create` still returns its initial `pageId`. Use `browser_page_create` with
+that `sessionId` and an optional HTTP(S) `url` to create another page in the same
+cookie context. Use `browser_pages` to discover page IDs, including adopted popups;
+never invent an ID or expect navigation to create a page implicitly. These tools
+delegate to the existing SDK, and the service remains the authorization/policy owner.
+The equivalent shell interfaces remain `agentbrowser page create --help` and
+`agentbrowser page list --help`.
+
+Bound creation requires `operationId` chosen before dispatch. Controlled sessions
+deduplicate that ID, but operation status does not retain the resulting page ID.
+Ordinary sessions made by `browser_create` do not acquire deduplication from an ID
+alone. Do not automatically retry an uncertain create in either case; inventory is
+not proof of which page a concurrent create produced. A general explicit-page quota
+and result correlation remain follow-ups, separate from the existing popup cap.
+
+`browser_extract` preserves complete `data` and evidence within `maxBytes`. Its
+default ceiling is 1 MiB of compact JSON including evidence; the operator can raise
+the ceiling with `AGENTBROWSER_EXTRACT_MAX_BYTES` before starting the service.
+Raw HTML size is not the extracted result size. Over-limit results fail explicitly,
+with no partial JSON. The MCP text envelope is separately serialized and can be
+larger. Any overflow files written by Claude or another harness belong to that
+harness; AgentBrowser does not define their paths.
+
+For the reproducible headed research smoke and its limits, see
+[research qualification](../../docs/spec/evidence/consumer-research-smoke.md).
+
 ## Running it
 
 ### Release consumers: the single binary (recommended)