PipelineFacts::DeskAnswer gains counts, derived through counted_answer over the
read's Docs::at(image, as_of); the stored outcome name stays the write-time record.
DeskOutcome::Refused carries the retraction target as sent; the record's choice is a
Short kept as sent (a choice_invalid choice is no label), and an illegal retraction
form keeps its choice and note. body_sha256 form unchanged. Schemas regenerated.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Rules 3-8, R1, R2, R4 of the binding spec; counted_answer derives which answer
counts; Door::Desk is the only door that may write a desk_answer, so Admit,
import and derivation refuse it. options_hash sits behind one seam, failing
closed until the bytes are filled; tests use a named fixture hash.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
SourceQuery gains `front` (serde default false, so an old client's request
decodes as before). The one owner of the list is sources::FRONT_PAGE_FILES;
the Qdrant filter matches `path` against it with MatchAny on the existing
keyword index, composed with the `repo` condition. The CLI prints the
citation line range as before.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
A follow-up the receiver wrote natively, closed, and a later batch replays is inert to the
daemon now and refused as an identity collision when the batch arrives.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
inert_in_window covered FollowUp and Idea only, so a receiver's own resolution
of such a record, admitted after the import began, refused the rerun in both
the tool (resume/window_writes) and the daemon (root_holds_native_write).
A Resolution whose subject is a follow-up or idea the plan does not replay
touches nothing planned and now stays beside the replay. One predicate, both
callers; the resolution of a replayed follow-up, or of any other kind, still
refuses.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Soul F1: the window left open by `inert_in_window` let a later imported record
withdraw or cite the receiver's native follow-up. Admission now refuses an
imported document that cites or resolves a native document of its own root
(another root's native documents are cited as ever). Stale docs and the import
help name the amended rule.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Nibu's stopped import of aetheria-release was refused twice over for her own
run's follow-up chat-s4606-4606: by the verb's resume (a record under the root
not imported from the source) and, had that passed, by admission
(ImportOutsideCampaign, a native write under the root). Both now leave a native
FollowUp or Idea alone when it was admitted after the root's first imported
document, share one predicate (`inert_in_window`), and the verb names what it
left in place and leaves it out of the final verification walk. Every other
native kind (a question, a resolution, a ruling, a target) can answer or
resolve a replayed document and still refuses; a collision on a planned key
still refuses. No evict verb: a receipt cannot be unwritten.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
The verb walks the giver (Query only), plans with huginn_mind::plan, walks her own root to
resume by what she holds, admits one batch per source receipt with imported_from, and ends
with a verification walk. Settings::source builds the giver's client from explicit flags.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The giver: (Campaign, Moved) joins the matrix; a Moved to this mind refuses MoveToSelf and a withdrawn Moved MoveIsFinal; any staged document rooted at a moved campaign, derived ones included, refuses CampaignMoved; Docs::closing_resolution reads every other document under the root closed by the Moved, and the image fans status_changed out so an earlier as_of still reads in force. The oracle derives the same fallback independently.
The receiver: PipelineProvenance.imported_from (optional, absent from every other receipt and from the digest) names the source receipt and the externals the batch cites. An import derives nothing, refuses its own instance, a Moved outcome, and an external this mind holds; a listed external stands in for an absent referent. mind-body persona.rs gains one outcome_words arm for the new variant.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
cut huginn-admit-hold r2. admit decodes, then asks near::neighbours (the one
neighbour query, for admit now and recall dispatch next) for the nearest
in-force rulings and questions to each of the batch's first three titled
rulings or questions, minus the batch's own ids, the question a ruling answers
and the subject of a Superseded resolution. A neighbour left holds the batch:
exit 6, the neighbours and a token (16 hex of sha256 over the decoded batch and
the agent) printed, nothing sent. The same command with --seen <token> admits
it; any other token is InvalidInput. A trouble during the check prints a note on
stderr and the admission proceeds.
PipelineDocumentSummary::of is public so the neighbours print as header lines.
sha2 joins eureka-state (already in the lock).
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
persona get prints the stored gamecult.persona_state.v0 document, then its
updatedAt and receipt (absent, exit 1, until the first put). persona put reads
the whole document from a file or stdin and prints Committed <receipt>, or the
refusal (a stale put names the stored updatedAt), exit 1; a document that is
not one JSON object is a usage error and sends nothing. Provenance tool is huginn.
The eureka-state MCP's last unique capability is now in the CLI.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
PipelineThought epiphany.pipeline.thought.v2, instance-rooted, validated as
its chosen candidate; ForeignInstance refusal, Answered-by-FollowUp or Recorded
resolutions, facts, a reads citation role, text index. Schemas, golden sample,
huginn schema list regenerated.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Documents decode one by one through serde_path_to_error, so the refusal says
documents[i].path and what is wrong, in the schema's words: a field name, the
allowed variants, the expected type. Serde's own text quotes the input, so it
is not passed through.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The strict decode that refuses unknown keys by path moves from the huginn
binary to eureka_state::door; the CLI re-exports it and the MCP admit takes
documents as a Value (schema still Vec<PipelineDocument>) and decodes through
it, answering InvalidInput before any call. A research note with extra keys is
refused by path and nothing is stored.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
epiphany.pipeline.research.v2 (one claim, typed sources, no status) and
epiphany.pipeline.idea.v2 (what could be, rests_on / toward), campaign-rooted
as <campaign>:research|idea:<pass>.<label>. Resolutions are the matrix alone;
lineage is Global; roles serves, sources, rests_on, toward; alias pass; index
text without a version bump. No faculty is told to use them yet.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
s5 findings of cut-self-session-live:
- blocked-recipe-misses-run-held-spec: eureka_state::hold is the one decider
(a question holds the item it is raised in, or every claim of the run it is
raised in; an answer of retire keeps holding the claims still in force).
queue::on_hold and `huginn blocked` both read it.
- hold-read-not-one-snapshot: on_hold returns a Held snapshot that the request
carries; claimable, queue and the gate read it, none reads it again.
- dead-self-holder-stalls-successor: launch::slot is the one reader of whether
a holder lives; claimable asks it, a dead holder is closed by the launch and
the beat's trace says so.
- retire-answer-reopens: launch::retire_answered resolves the claims of an
answered-retire question Withdrawn; the beat runs it before reading briefs.
- held-note-threshold-unpinned: a test pins the note for exactly one held brief.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
epiphany.pipeline.memory.v2, instance-rooted `<instance>:memory:<label>`:
PipelineMemory with seven sorts (Asked, Decided, Committed, Learned, Did,
Idea, Rapport), her own text, who it is about, where it was learned, whether
directly, what it rests on, a salience that only ranks, and the memories a
consolidating one replaces.
Admission refuses a foreign instance and resolves a memory only Deferred to a
follow-up (an ask taken on), Recorded, Withdrawn or Superseded by a memory.
Memories have their own lineage so supersession stays within one mind. The
read side selects by sort, about (multi-valued) and direct; the index carries
the text; `consolidates` is a citation role.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
The mind decides membership (Mind::members) before the index is asked; the
index scores exactly the members (Qdrant has_id + exact) and the page carries
one cosine score per row. Deletes OVERSAMPLE_MAX, the x4 oversample, the
unfiltered VectorIndex::search contract and check_semantic.
Not yet compiled when committed: the first Yggdrasil run follows.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
The repo stores LF; a scripted edit on Windows wrote CRLF. No content change:
git diff -w d5fddc3 shows only the three commits' real edits.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
One bounded line: absent, stored updatedAt=<stamp>, or unreadable; no value
of the document. Test over canned Whoami answers.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Resolves the eureka-state Cargo.toml comment block to main's, regenerates
Cargo.lock from main's with cargo update -w, adds the Persona and PersonaPut
arms to the CLI's unexpected-answer match and the persona field to the CLI
test MindStatus literals.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The strict decode stopped at the first document with a lost key and let
serde read a struct from a JSON array. It now names every lost path in the
batch and refuses a non-object document or selection.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A new bin of eureka-state, crates/eureka-state/src/bin/huginn/: the agents'
shell door to the mind. Text out, typed exit codes, strict decode of
agent-written JSON (unknown key paths refused, never values), the named
campaign-state recipes, and a read-back after every committed admission.
lib.rs, main.rs and tests/mcp.rs are untouched.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The jsonschema error kind lives in jsonschema::error; the eureka-state tool
closures own their input; huginn.mind_request/response.v1 carry the persona
operations (derived by the existing published_wire_schemas test).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
put_persona replaces the mind's gamecult.persona_state.v0 whole through the
commit primitive: schema-valid against the published file, personaId is the
instance, canonical provenance, CAS on updatedAt, monotone updatedAt. The
document is an opaque seventeenth stored type, one per mind. Wire operations
persona_get and persona_put, MindStatus.persona, HuginnClient methods and the
eureka-state persona tools. Published wire schemas follow in the next commit.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Package and lib become eureka-pipeline / eureka_pipeline; the crate joins the
workspace; huginn-mind's git dependency on GameCult/Epiphany is replaced by
the path, and Cargo.lock is regenerated (the Epiphany source entry is gone).
Every epiphany_pipeline mention in huginn-mind, huginn-daemon and eureka-state
is renamed. The schema-publication test reads ../../schemas/cultnet. The
leaf's license-file key (../LICENSE, which Huginn has no file for) is dropped.
Type ids, the epoch and every schema_id string are untouched. Schemas README
and the pipeline section of schemas/cultnet/README.md are rewritten for the
new home; README and AGENTS no longer say the leaf is pinned by git. New test:
the catalogue lists exactly the schema files beside it.
Not yet built or tested; verification follows on Yggdrasil.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A request that fails to encode is a defect in this client, not a transport
failure, so it is ClientError::Unencodable, typed Unencodable at the tool,
instead of the retryable Unavailable. A test reports a non-UTF-8
HUGINN_ENDPOINT as such.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>