Write new journal entries under logs/core and merge read-only legacy
history without moving SQLite/WAL files. Atomically spool failed batches,
retaining unspoolable entries for event-driven retries. Journal full trap
diagnostics before UTF-8-safe status display. Port session overflow archives
and followable line/byte excerpts to the still-shipped embedded agent.
Document retention/recovery and cover the contracts with regressions.
Include one rustfmt-only normalization in the existing SDK WASI test.
Card: SAU-143
Make legacy core.exit share core.restart's supervisor gate and pending
request. Seed the stable agent prompt and boot comments with the approval
and shutdown contract, and check real init output under a deadline.
Cover both aliases' gate, response grace, coalescing and exit status.
Card: SAU-135
Return success before scheduling the existing shutdown path, coalesce pending
requests, and mark #loop invocations with SAUSAGE_LOOP=1. Keep core.exit
compatibility and document explicit per-call approval for all agents.
Card: SAU-134
- thinking (off, low, medium, high, xhigh, max) is an enum: serde rejects
unknown levels in the config, and the schema of agent.chat lists them.
reasoning_effort, a second name for the same setting, is gone.
- agent.chat takes an optional thinking level for one turn.
- off really switches thinking off: OpenAI gets the effort none, and
Anthropic gets disabled thinking (newer Claude models think by
default). A model that cannot switch thinking off gets low.
- Unset means the model's default. Anthropic thinking blocks now return
unless thinking is off, because newer models think by default.
- The template sets thinking: medium and shows it in each example, with
current model names.
- Checked against the proxy with gpt-6-luna, glm-5.3-flash, and
claude-haiku-5-5.
- /config/agent.yaml and /config/boot.yaml replace the JSON files, read
with serde_yaml_ng (also in the agent, inside WASM).
- sausage init asks nothing and reads no SAUSAGE_* variables. It writes
commented templates with an example for each API, and prints the path
to edit. Until the agent is configured, agent.chat names the missing
field. allow_no_token: true permits a local model without a key.
- The agent speaks openai-chat-completions, the format of OpenRouter,
Ollama, and most providers. base_url follows each SDK: with /v1 for
the OpenAI shapes, without it for Anthropic.
- Checked against the proxy with glm-5.3-flash: the agent wrote, built,
and activated a counter plugin in 55 s.
The console reads a line, runs it to the end, and prints the result,
with and without a terminal. Notifications print while a command runs.
Ctrl-C during a command stops only the wait. 314 lines (was 480).
All host integration tests are modules of cli/tests/host/, so they run
in one parallel pool, and the probes build once. Warm, the 184 host
tests take 24 s (was about 45 s as seven binaries in sequence), and
cargo test --workspace takes 45 s.
- The cargo target folder is <cache>/cargo-target, next to Wasmtime's
cache, which moves to <cache>/wasmtime: Wasmtime's cleanup worker
deletes unknown entries in its folder, also Cargo's artifacts.
- Builds use the SDK at <cache>/sdk/<content hash>/, so cargo reuses
the compiled SDK in every world. /plugins/cargo/sdk/ stays for agents.
- Tests run in the release profile and share compiled crates with the
release build.
- The cargo and cli tests use a persistent cache in CARGO_TARGET_TMPDIR:
warm, the cargo suite takes 11 s (was 235 s) and the cli suite 6 s
(was 149 s).
- nix flake check runs ignored stress tests. AGENTS.md: rules for fast
tests.
cargo.build and the runner (review T22R): builds use the network again;
core.unlock and core.notify in order under the runner; quiet test
output; manifest preparation keeps [workspace], target tables, renamed
and optional entries; cargo.rpc.discover; -32004 with data.output;
retention of 10 builds; light, empty test worlds with an in-memory
journal; only CARGO_/RUST_/SAUSAGE_ variables; stdin is null; the runner
through --config. A compile cache that cannot be created is not fatal.
Activation replaces plugin.wasm without a gap.
Console and main: init ships the workspace Cargo.lock and creates the
world atomically; each console command runs in its own task, so ps,
stop, and kill work during a slow call; SAUSAGE_HEADLESS; the terminal
mode is restored; signals during boot; chat text is not taken as a
command.
Tests: 20 more tests for PROTOCOL.md sections 2 to 10; the cargo tests
choose the libtest binary from cargo's JSON output and time out.
Activation path (review T6R): a broken plugin or a stray file in
/plugins blocks no activation; candidates replace their own entries;
discovery has a 10 s deadline and its process is stopped after the
answer; an unchanged hash keeps plugin.prev.wasm; activations run in
their own task; the watcher is not recursive; no duplicate services;
rpc.retired waits for live processes of its version; reads and hashes
on blocking threads.
Guest I/O and per-call paths: a stdin write error is EOF, stdout and
stderr are drained before the status; stderr is lossy UTF-8 and goes
to the journal from its own reader; compiled components are freed;
shutdown starts no new processes; lock queues drop stopping processes;
compile before the admission gate; CommandPre per component;
core.unlock in order; null errors are successes; the journal thread
survives SQLite errors.
sausage init builds the agent with cargo.build; sausage without a
command creates ./world. The console reads plain lines without a
terminal. PROTOCOL.md and DECISIONS.md describe the decided rules. The
flake tests the whole workspace and checks the packaged cargo.build.
- cargo.build (native): one source copy, tests under WASI, release
build to /state/cargo/builds/<n>/, process groups killed on cancel.
The host writes the SDK copy to /plugins/cargo/sdk/ at start.
- sausage test-runner: one instance per test, in parallel, with its own
mount table (empty world, package folder at its path); answers
core.lock, core.unlock, core.notify, core.log.
- The console: rustyline, notifications while typing, ls/cat through the
process view, methods, ps, log, activate, revert, stop, kill.
- core.notify on stdout is handled in order, before the response.
- /proc is a core layer: core/ (PROTOCOL.md, graph.json, graph.dot,
locks.json, plugins/<name>/discover.json and client.rs) and one folder
per process (info.json, log, and its /self files).
- Locks are released only after the task ended, the store dropped, and
in-flight file operations returned.
- core.activate and core.revert with copies, discovery, compatibility
checks of imports and consumers, groups, force. An admission gate
makes the snapshot of old processes complete.
- Graph of discover documents by hash, refreshed by a file watcher.
- Upgrades: grace periods (x-sausage-grace), stop, service restarts,
rpc.retired.
- SDK plugins in the real core (cli/tests/sdk.rs).
The Nix package, the dev shell, and the test check set CC_wasm32_wasip2
and AR_wasm32_wasip2 to the clang of pkgsCross.wasi32 (wasi-libc), so
build scripts with the cc crate work, for example rusqlite with bundled
SQLite. The runtime-toolchain check links C into a probe with the
packaged host and an empty PATH.
A stopped actor gets the new version installed, keeps its mailbox and does
not run main until the next start. Running actors still restart on the new
version. The upgraded and rolled_back answers say whether the actor runs.
The host watches the whole world folder recursively with the notify crate
(any writer counts, .sausage-tmp-* skipped, ~100 ms coalescing per path).
A new or changed actor/<id>/actor.wasm (or new folder actor/<id>) is
booted as at start once quiet: new = spawn (tested first), changed =
upgrade. The broker `scan` request is gone; the boot pass stays, plus a
full pass when the OS watcher overflows.
New broker requests watch/unwatch {path} (saved in actor.json `watches`)
deliver fs_changed {path, op: write|create|remove|rename, to?} from `fs`,
not routed, dropped when the mailbox is full; overflow sends every watcher
one fs_changed {path:"/actor", op:"rescan"}.
Card #91 (multi-host step 1).
- cli: the subcommand is optional; without one, sausage runs ./world and
runs init first when ./world is not a world yet (test: cli/tests/cli.rs).
So `nix run git+https://gitea.surma.technology/surma/sausage` works.
- flake: .#loop without a folder runs bare sausage.
- README: mention the bare command and the bare loop.
{"type":"remove","actor"} shuts the actor down normally, drops its
mailbox, supervisor and actor.json entry (so also its subscriptions and
tap), and deletes /actor/<id>/. Native actors cannot be removed.
Re-applied from card-1-broker-remove (3c91747) onto card-2-broker-tap.
Tapped copies {type:tapped, message:{id,from,to,reply_to,body}, ts} are
delivered directly (never tapped themselves), dropped when the tapper's
mailbox is full, and the tap is saved in actor.json like subscriptions.
File operations under /actor/<id>/fs/ become messages from `fs` to <id>
(fs_read, fs_write, fs_mkdir, fs_remove, fs_rename) with a 10 s timeout.
vfs.rs wraps the wasi:filesystem implementation of wasmtime-wasi.
- broker: `{"type":"exit"}` answers `exiting`; `sausage run` then stops all
actors and exits with code 75.
- flake: apps `loop` / `loop-internal` run `nix run --refresh git+ssh://.../surma/sausage -- run <world>`
in a loop; exit code 0 (/quit) ends the loop, anything else restarts.
- PROTOCOL.md, README.md, test in cli/tests/host.rs.
Not compiled: written by the Sausage agent, which cannot build the native host.
Staging every write until close broke tempfile, git, and SQLite, which
expect normal files. Actors that need an atomic publish write a temporary
file and rename it; the SDK has write_atomic for that.
Host:
- test first: a new version is tested where it lies; only an installed
version goes to versions/, and instances run from there
- data/ and public/ are shared by all versions; no snapshots; rollback
restores code only
- no re-delivery, status.json, list, remove/archive, smoke test, data/
hiding, or stdin timeout; rollback needs a version
- supervisor.rs split out; one place for installing a version
- init only writes the agent folder; run installs it like any actor
- console: @actor, text to the agent, /help, /quit
Agent:
- every text goes out as a broadcast; 5-line prompt; 5 tools that describe
themselves; turn.json only marks an active turn
Docs: PROTOCOL.md, README.md, DECISIONS.md, AGENTS.md rewritten.
Examples: only notes and notes-v2.
Sausage
surma