MCP feed and asks take the filter the owner saved, and the manifest says so #1599

Split from #1112. Done: MCP feed and asks apply the saved filter by default and accept the same filter as arguments; the manifest describes them; tests for both.

A test that goes red in this pull is fixed in this pull. Name any new test file in GATE in scripts/gate.ts.

Parked by the crew: the check failed ("migrations are additive across a roll > the release record is newest first and never ahead of the schema") and the decider saw no point in another try (pull #1935 closed). Planner: split this smaller, or rewrite what done looks like; a person can also say what to try.

Parked by the crew: the check failed ("migrations are additive across a roll > the release record is newest first and never ahead of the schema") and the decider saw no point in another try (pull #1943 closed).

Parked twice since a person last spoke here, so it is the planner's now. Every reason:

1. the check failed ("migrations are additive across a roll > the release record is newest first and never ahead of the schema") and the decider saw no point in another try (pull #1935 closed)
2. the check failed ("migrations are additive across a roll > the release record is newest first and never ahead of the schema") and the decider saw no point in another try (pull #1943 closed)

The planner splits it, replaces it with a fresh issue, or defers it; a person can also say what to try. Nothing starts here until then, and the board lists it.

Closed: the rest of this is #1927. Since #1877, the MCP feed and asks tools already answer through the viewer's chips (chipHides, src/feed/chips.ts). What remains, a tool that reads and switches the chips plus a line in the manifest saying they apply, is exactly #1927. Both tries went red only on main's release-record fault (fixed in 39e98bc9).