feat(read_file): let capable models view images, video and PDFs
Nightly Build / build (push) Successful in 6m38s

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.
This commit is contained in:
2026-07-22 11:01:44 +01:00
parent 624f6b0a95
commit cfaa7bace3
12 changed files with 524 additions and 42 deletions
+27 -10
View File
@@ -18,6 +18,10 @@ pub struct LlmToolCall {
/// size cap (no diff shown then). Only populated by `for_message` (history).
pub preview_old: Option<String>,
pub preview_new: Option<String>,
/// JSON `[{host_path, mime}]` — media files this tool produced (e.g. `read_file`
/// on an image), to be inlined to the model as native input by the message
/// builder. `None` for non-media tools. Only populated by `for_message`/`get`.
pub media: Option<String>,
}
/// Inserts a tool call in `running` state and returns its id.
@@ -81,6 +85,19 @@ pub async fn set_preview(
Ok(())
}
/// Persists the JSON media manifest for a tool that produced viewable media
/// (`ToolResult::Media`). Separate from [`complete`] — like [`set_preview`] — so the
/// out-of-band media write stays independent of the status/result write. Read back
/// by `for_message` so the message builder can inline the files for the model.
pub async fn set_media(pool: &SqlitePool, id: i64, media_json: &str) -> anyhow::Result<()> {
sqlx::query("UPDATE chat_llm_tools SET media = ? WHERE id = ?")
.bind(media_json)
.bind(id)
.execute(pool)
.await?;
Ok(())
}
pub async fn fail(pool: &SqlitePool, id: i64, error: &str) -> anyhow::Result<()> {
sqlx::query(
"UPDATE chat_llm_tools SET result = ?, status = 'failed' WHERE id = ?",
@@ -150,8 +167,8 @@ pub async fn for_message(
pool: &SqlitePool,
message_id: i64,
) -> anyhow::Result<Vec<LlmToolCall>> {
let rows = sqlx::query_as::<_, (i64, i64, String, Option<String>, Option<String>, String, String, Option<String>, Option<String>)>(
"SELECT id, message_id, name, arguments, result, result_type, status, preview_old, preview_new
let rows = sqlx::query_as::<_, (i64, i64, String, Option<String>, Option<String>, String, String, Option<String>, Option<String>, Option<String>)>(
"SELECT id, message_id, name, arguments, result, result_type, status, preview_old, preview_new, media
FROM chat_llm_tools
WHERE message_id = ?
ORDER BY id ASC",
@@ -161,8 +178,8 @@ pub async fn for_message(
.await?;
Ok(rows.into_iter()
.map(|(id, message_id, name, arguments, result, result_type, status, preview_old, preview_new)| {
LlmToolCall { id, message_id, name, arguments, result, result_type, status, preview_old, preview_new }
.map(|(id, message_id, name, arguments, result, result_type, status, preview_old, preview_new, media)| {
LlmToolCall { id, message_id, name, arguments, result, result_type, status, preview_old, preview_new, media }
})
.collect())
}
@@ -170,8 +187,8 @@ pub async fn for_message(
/// A single tool call by id, with its diff-preview columns. Backs the tool-detail
/// page (`GET /api/tools/{id}`). Returns `None` when the id is unknown in this pool.
pub async fn get(pool: &SqlitePool, id: i64) -> anyhow::Result<Option<LlmToolCall>> {
let row = sqlx::query_as::<_, (i64, i64, String, Option<String>, Option<String>, String, String, Option<String>, Option<String>)>(
"SELECT id, message_id, name, arguments, result, result_type, status, preview_old, preview_new
let row = sqlx::query_as::<_, (i64, i64, String, Option<String>, Option<String>, String, String, Option<String>, Option<String>, Option<String>)>(
"SELECT id, message_id, name, arguments, result, result_type, status, preview_old, preview_new, media
FROM chat_llm_tools
WHERE id = ?",
)
@@ -179,8 +196,8 @@ pub async fn get(pool: &SqlitePool, id: i64) -> anyhow::Result<Option<LlmToolCal
.fetch_optional(pool)
.await?;
Ok(row.map(|(id, message_id, name, arguments, result, result_type, status, preview_old, preview_new)| {
LlmToolCall { id, message_id, name, arguments, result, result_type, status, preview_old, preview_new }
Ok(row.map(|(id, message_id, name, arguments, result, result_type, status, preview_old, preview_new, media)| {
LlmToolCall { id, message_id, name, arguments, result, result_type, status, preview_old, preview_new, media }
}))
}
@@ -189,6 +206,6 @@ fn row_to_tool(
i64, i64, String, Option<String>, Option<String>, String, String,
),
) -> LlmToolCall {
// The resume path (`pending_for_stack`) never needs the diff preview.
LlmToolCall { id, message_id, name, arguments, result, result_type, status, preview_old: None, preview_new: None }
// The resume path (`pending_for_stack`) never needs the diff preview or media.
LlmToolCall { id, message_id, name, arguments, result, result_type, status, preview_old: None, preview_new: None, media: None }
}
+3 -1
View File
@@ -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)",