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.
Realizes blueprint §6: each user gets a permanent Docker container
(skald-{userid}, our own skald-runtime image with python+node) as their
execution sandbox. Docker is now a hard requirement — a missing daemon fails
Skald::new and the process exits at boot.
- ContainerManager (crates/skald-core/src/container/): docker availability
check, builds skald-runtime from the embedded Dockerfile, reconciles one
running container per active user at boot, stops them at shutdown, and
ensure/remove on user create/delete. Shells the docker CLI (no client crate).
- UserFs (core-api): pure value type carried in ToolContext, mapping the agent's
single namespace — ~/ → homes/{userid}, shared/{X}/ → shared/{X} (membership),
user-memory/ + shared-memory/ → SQLite — to host and container paths.
- execute_cmd now runs inside the caller's container via `docker exec`.
- fs-tools resolve every physical path through UserFs to the per-user host
workspace, host-side, with fail-closed symlink/`..` containment
(resolve_host_path: canonicalize + prefix-check). grep_files resolves its root
the same way but stays disk-only.
- shared_folders + shared_folder_members (registry, junction table with
can_write) back the shared-folder membership that drives both the container
mounts and the shared/{X} routing.
- Threading: UserContext.fs → ChatSessionManager → handler → ToolContext.fs.
Per-user MCP servers do not yet run in the container (next round).
dguiducci