feat(channel): structured tool-call IM display with edit-in-place

Introduce a new `show_tool_calls_in_im` bot setting plus a full overhaul of
how tool calls are surfaced in IM channels:

- Add per-bot setting + migration (0072) and expose through settings API /
  handlers / frontend SDK.
- Introduce a `toolCallDroppingStream` wrapper that filters tool_call_* events
  when the setting is off, keeping the rest of the stream intact.
- Add a shared `ToolCallPresentation` model (Header / Body blocks / Footer)
  with plain and Markdown renderers, and a per-tool formatter registry that
  produces rich output (e.g. `web_search` link lists, `list` directory
  previews, `exec` stdout/stderr tails) instead of raw JSON dumps.
- High-capability adapters (Telegram, Feishu, Matrix, Slack, Discord) now
  flush pre-text and then send ONE tool-call message per call, editing it
  in-place from `running` to `completed` / `failed`; mapping from callID to
  platform message ID is tracked per stream, with a fallback to a new
  message if the edit fails. Low-capability adapters (WeCom, QQ, DingTalk)
  keep posting a single final message, but now benefit from the same rich
  per-tool formatting.
- Suppress the early duplicate `EventToolCallStart` (from
  `sdk.ToolInputStartPart`) so that the SDK's final `StreamToolCallPart`
  remains the single source of truth for tool call start, preventing
  duplicated "running" bubbles in IM.
- Stop auto-populating `InputSummary` / `ResultSummary` after a per-tool
  formatter runs, which previously leaked the raw JSON result as a
  fallback footer underneath the formatted body.

Add regression tests for the formatters, the Markdown renderer, the
edit-in-place flow on Telegram/Matrix, and the JSON-leak guard on `list`.

db/migrations/0001_init.up.sql

@@ -179,6 +179,7 @@ CREATE TABLE IF NOT EXISTS bots (
   transcription_model_id UUID REFERENCES models(id) ON DELETE SET NULL,
   browser_context_id UUID REFERENCES browser_contexts(id) ON DELETE SET NULL,
   persist_full_tool_results BOOLEAN NOT NULL DEFAULT false,
+  show_tool_calls_in_im BOOLEAN NOT NULL DEFAULT false,
   metadata JSONB NOT NULL DEFAULT '{}'::jsonb,
   created_at TIMESTAMPTZ NOT NULL DEFAULT now(),
   updated_at TIMESTAMPTZ NOT NULL DEFAULT now(),

db/migrations/0072_add_show_tool_calls_in_im.down.sql

@@ -0,0 +1,5 @@
+-- 0072_add_show_tool_calls_in_im (down)
+-- NOTE: After rolling back this migration, re-run `sqlc generate` to update the
+-- generated Go code in internal/db/sqlc/.
+
+ALTER TABLE bots DROP COLUMN IF EXISTS show_tool_calls_in_im;

db/migrations/0072_add_show_tool_calls_in_im.up.sql

@@ -0,0 +1,5 @@
+-- 0072_add_show_tool_calls_in_im
+-- Add show_tool_calls_in_im column to bots table to control whether tool call
+-- status messages are surfaced in IM channels.
+
+ALTER TABLE bots ADD COLUMN IF NOT EXISTS show_tool_calls_in_im BOOLEAN NOT NULL DEFAULT false;

db/queries/settings.sql

@@ -21,7 +21,8 @@ SELECT
   tts_models.id AS tts_model_id,
   transcription_models.id AS transcription_model_id,
   browser_contexts.id AS browser_context_id,
-  bots.persist_full_tool_results
+  bots.persist_full_tool_results,
+  bots.show_tool_calls_in_im
 FROM bots
 LEFT JOIN models AS chat_models ON chat_models.id = bots.chat_model_id
 LEFT JOIN models AS heartbeat_models ON heartbeat_models.id = bots.heartbeat_model_id
@@ -59,9 +60,10 @@ WITH updated AS (
       transcription_model_id = COALESCE(sqlc.narg(transcription_model_id)::uuid, bots.transcription_model_id),
       browser_context_id = COALESCE(sqlc.narg(browser_context_id)::uuid, bots.browser_context_id),
       persist_full_tool_results = sqlc.arg(persist_full_tool_results),
+      show_tool_calls_in_im = sqlc.arg(show_tool_calls_in_im),
       updated_at = now()
   WHERE bots.id = sqlc.arg(id)
-  RETURNING bots.id, bots.language, bots.reasoning_enabled, bots.reasoning_effort, bots.heartbeat_enabled, bots.heartbeat_interval, bots.heartbeat_prompt, bots.compaction_enabled, bots.compaction_threshold, bots.compaction_ratio, bots.timezone, bots.chat_model_id, bots.heartbeat_model_id, bots.compaction_model_id, bots.title_model_id, bots.image_model_id, bots.search_provider_id, bots.memory_provider_id, bots.tts_model_id, bots.transcription_model_id, bots.browser_context_id, bots.persist_full_tool_results
+  RETURNING bots.id, bots.language, bots.reasoning_enabled, bots.reasoning_effort, bots.heartbeat_enabled, bots.heartbeat_interval, bots.heartbeat_prompt, bots.compaction_enabled, bots.compaction_threshold, bots.compaction_ratio, bots.timezone, bots.chat_model_id, bots.heartbeat_model_id, bots.compaction_model_id, bots.title_model_id, bots.image_model_id, bots.search_provider_id, bots.memory_provider_id, bots.tts_model_id, bots.transcription_model_id, bots.browser_context_id, bots.persist_full_tool_results, bots.show_tool_calls_in_im
 )
 SELECT
   updated.id AS bot_id,
@@ -85,7 +87,8 @@ SELECT
   tts_models.id AS tts_model_id,
   transcription_models.id AS transcription_model_id,
   browser_contexts.id AS browser_context_id,
-  updated.persist_full_tool_results
+  updated.persist_full_tool_results,
+  updated.show_tool_calls_in_im
 FROM updated
 LEFT JOIN models AS chat_models ON chat_models.id = updated.chat_model_id
 LEFT JOIN models AS heartbeat_models ON heartbeat_models.id = updated.heartbeat_model_id
@@ -120,5 +123,6 @@ SET language = 'auto',
     transcription_model_id = NULL,
     browser_context_id = NULL,
     persist_full_tool_results = false,
+    show_tool_calls_in_im = false,
     updated_at = now()
 WHERE id = $1;