fix(desktop): give tool rows the names, arguments and results the UI renders

[agentforce314]

Follow-up to #820. Tool rows still looked nothing like the TUI's: plain untitled entries, no icons, no diffs, and — for anything that returned text — no output at all.

Why

The desktop renderer keys every per-tool formatter off its own tool vocabulary (read_file, terminal, edit_file, …) and reads a tool's output from named result fields. The agent speaks Claude Code's vocabulary (Read, Bash, Edit) and returns plain text. Nothing matched:

• no name in TOOL_META → the unlabelled generic path: no title, no icon, no tone
• firstStringField(args, ['path','file','filepath']) never sees file_path
• a plain-string result is discarded by the renderer's parseMaybeJsonObject, so finished tools rendered empty

What changed

All three are adapted in the gateway, mirroring the TUI's own summarization (ui-tui/src/gatewayClient.ts toolContext / formatToolResult) so both surfaces describe a run the same way.

	before	after
Read	Read · (empty)	Read file seed.py · file contents · "Read 2 lines"
Bash	Bash · (empty)	Ran command · $ ls src/ transcript · ANSI output
Edit	Edit · (empty)	Edited file a.py · rendered diff, "Added 1 line, removed 1 line"
Glob	Glob · (empty)	Listed files · the matches · 3 files chip
WebSearch	WebSearch · (empty)	Searched web · 3 results · 2.4s
failure	Bash · (empty)	error row · cleaned reason, no diff

Unknown tools (Task, MCP tools) pass through unchanged and keep the generic treatment, which is the right fallback.

Details worth calling out:

• The single argument worth showing rides along as context in the TUI's priority order, so a Grep row shows its pattern rather than its search path. path is aliased in alongside file_path because that is the spelling the file formatters look for.
• An edit's inline_diff is rebuilt from the structuredPatch display envelope, so it renders as a real diff with add/remove counts — the TUI treats the diff AS the result, and now so does the desktop.
• Failure text has its model-facing markup (<tool_use_error>, <sandbox_violations>) stripped before display.

Testing

The wire payloads are frozen into gateway-tool-events.fixture.json, generated by the Python translator and rendered through the real renderer by the new ui-desktop/src/lib/gateway-tool-contract.test.ts, which asserts what a user actually sees.

That pairing is the point. This class of bug is invisible to either language alone — each side happily tests a field the other never reads, which is precisely how the blank rows shipped. Writing the test immediately caught two more live mismatches that the Python tests were happy with: the argument context outranking a Glob's matches on the renderer's generic path, and a diff that never reached the view.

• Full Python suite: 9902 passed, 15 skipped
• tsc --noEmit: clean
• New contract test: 10 passed

🤖 Generated with Claude Code