Huginn/crates/mind-body
Repository files (latest commit first)
Filename Latest commit message Latest commit date
Meta Vens dd039e55b9 Projector after Soul: no Mind recall; messages to her always whole; sampled inclusion; effective tuning hash and validation; schema-derived guard; budget edges; read-only organs; grapheme clips
F1/F2: the Projector shows her persona state and her room; recall.rs and the
recall pool, recall_sorts and its cap are deleted. Reading the Mind is the
Interpreter's (C3b).
F3: messages to her go in whole and first; others fill what is left, with an
exact note; overflow past the cap is reported.
F4: candidates are included with probability 1 - exp(-score / inclusion_score);
caps are maxima. F5: the hash is of the effective tuning. F6: the guard reads
the persona schema and the tuning keys. F7: bounded fixed slots and relatedness
cue; the redundant final clip is gone. F8: tuning values are validated.
F9: project's organs are read-only traits. F10: clips land on graphemes.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-19 23:43:50 +01:00
..
src Projector after Soul: no Mind recall; messages to her always whole; sampled inclusion; effective tuning hash and validation; schema-derived guard; budget edges; read-only organs; grapheme clips 2026-11-19 23:43:50 +01:00
tests mind-body public surface: regenerated after the F3/F4 follow-ups 2026-11-19 22:30:50 +01:00
Cargo.toml Projector after Soul: no Mind recall; messages to her always whole; sampled inclusion; effective tuning hash and validation; schema-derived guard; budget edges; read-only organs; grapheme clips 2026-11-19 23:43:50 +01:00
clippy.toml mind-body: the process environment is unreadable by library code, by lint 2026-10-10 20:15:18 +02:00
README.md Body map after C2: the persona-only body, stale rows marked, READMEs corrected 2026-11-19 22:40:02 +01:00

mind-body

The Mind's body: the control store, the unit launcher, the mind-heartbeat, the inert mind-persona organ and the mind-self-run actuator.

mind-self-run --instance <slug> [--endpoint rudp://<ip>:<port>] runs inside mind-self@<instance>. It finds her one open Self run, starts claude over stream-json with a fixed argument list, asks for the flush once at the context ceiling and stops a child that outlives the flush (SIGINT, then SIGTERM and SIGKILL). It exits 0 when the child exited 0, 1 otherwise, 3 when she has no single open Self run and 2 when the arguments are wrong or the mind cannot be reached.

The heartbeat

mind-heartbeat is the one process that decides who wakes and when. It starts a Persona's unit and writes no Mind: the beat (HEARTBEAT_BEAT_S, default 1800 s) goes to the idle, released Mind that has waited longest, bent by a member addressing her, and the operator or another Mind naming a Persona wakes her at once, once per message. mind-heartbeat timeline prints its latest record.

mind-persona is inert: it reads the brakes and exits dead or no organ. It writes nothing. Nothing launches mind-self-run.

The actuator has its own ignored test, the_real_bin_finds_her_run_... in tests/self_run.rs: the real mind-self-run against the real daemon with a fake claude first on PATH. It needs the daemon built beside the binary and a POSIX shell, not root:

cargo build -p huginn-daemon -p mind-body --all-targets   && cargo test -p mind-body --test self_run -- --include-ignored

Mutation testing of the actuator, with the globs that reach the library and the binary: cargo mutants -p mind-body -f "**/src/self_run.rs" -f "**/src/bin/mind-self-run.rs". The binary's mutants are killed only by the lane above.