feat(read_file): let capable models view images, video and PDFs

When the resolved model declares an input modality (vision → images,
video, document → PDFs), read_file now hands a binary media file back to
the model as native input instead of failing on non-UTF-8 bytes.

- ToolResult gains a Media { text, media } variant carrying MediaRef
  { host_path, mime }; the tool message keeps only the text note, the
  bytes travel out of band in a new additive chat_llm_tools.media column
  (mirrors preview_old/new).
- read_file sniffs the resolved host file; a recognized medium becomes a
  Media result (with a neutral note), everything else keeps the textual
  path. Capability gating lives in the message builder, so read_file
  never needs the model caps and degrades cleanly on a text-only model.
- MessageBuilder inlines current-turn tool media as a synthetic user
  message right after the tool-result group (media_turn_start boundary,
  so older turns are never re-billed), reusing media.rs primitives via a
  new inline_paths helper that contains against the caller's workspace
  roots. OpenAI forwards the parts verbatim; the Anthropic client now
  also translates the PDF `file` part into a native `document` block
  (image_url → image was already handled).
- read_file's description is annotated per serving model in
  call_llm_round, listing the formats it can open, so the model knows
  reading one shows it the content.

Tests: media sniff (PDF), PDF file-part build, inline_paths containment
+ capability gating, capability hint, read_file media-vs-text, Anthropic
file→document, and the owner-schema-stands-alone check with the new
column.

crates/skald-core/src/db/mod.rs

@@ -750,14 +750,16 @@ pub async fn create_owner_tables(pool: &SqlitePool) -> Result<()> {
             result_type TEXT    NOT NULL DEFAULT 'string' CHECK(result_type IN ('string', 'json')),
             preview_old TEXT,                                -- file-write diff: content before the write
             preview_new TEXT,                                -- file-write diff: content after the write
+            media       TEXT,                                -- JSON [{host_path,mime}]: media the tool produced, inlined to the model out of band
             created_at TEXT    NOT NULL DEFAULT (datetime('now'))
         )",
     )
     .execute(pool)
     .await?;
-    // Diff-preview columns are additive — reach an already-created table in place.
+    // Diff-preview + tool-media columns are additive — reach an already-created table in place.
     ensure_column(pool, "chat_llm_tools", "preview_old", "TEXT").await?;
     ensure_column(pool, "chat_llm_tools", "preview_new", "TEXT").await?;
+    ensure_column(pool, "chat_llm_tools", "media", "TEXT").await?;
 
     sqlx::query(
         "CREATE INDEX IF NOT EXISTS idx_stack_session   ON chat_sessions_stack(session_id)",