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>
Source refresh now upserts a repo's new chunks first and deletes what is
left in scope under another commit afterwards, so a failed embed never
removes indexed content (embed-outage-empties-repo). The cursor is still
dropped before the first write.
The pool's reserve endpoints use EmbedBounds::RESERVE (30 s a text, 60 s
floor) instead of the GPU default (reserve-bounded-like-a-gpu).
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answered-retire question Withdrawn; the beat runs it before reading briefs.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 CLI binary asks a real in-process daemon over CultNet; the daemon answers
through sources::search against an in-memory source index and a flat embedder.
Pins the citation line, the repo filter and limit, and the refusal naming both
models when the daemon embeds under another digest (Soul test-gaps). common
serve takes any index sink.
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 shared request decoder (envelope.rs) no longer quotes decoder text or
envelope fields: a refusal names the field path and the class. MindStatus.persona
is PersonaStatus {Absent, Stored, Unreadable}, so whoami answers in the persona
door's own terms.
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>
Adds Absent, Symbol, ReadAnchor and read_window_is_bounded, the marker in
value_types!, the workspace fixtures and the reads admission test. The
golden file and the six published schemas are not regenerated yet, so the
golden, schema and wire-schema tests fail at this commit (it builds).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Add the AGPL-3.0 text as LICENSE and set the workspace license to
AGPL-3.0-only (rulings license-split, leaf-relicensed-agpl); the leaf's
provenance (Epiphany ef956865, PolyForm Noncommercial, relicensed by its sole
copyright holder 2026-10-09) is recorded in its Cargo.toml and README.
One [workspace.dependencies] entry per CultLib crate now owns the revision;
the crates inherit it. index.json lists Huginn's two wire schemas too, and the
catalogue test drops its huginn. prefix exclusion: every schema file is listed.
README and AGENTS stop naming Epiphany notes as the owner of the cut.
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>
snapshot_admits_and_reads_back now counts pipeline envelopes apart from the
loop, asserts validate() and pipeline_key == stored key for every one, admits
a resolution for every stuck finding and a withdrawal for every unwithdrawable
resolution, and fails with the id named on any refusal.
The refusal tests assert the exact leaf refusal (field and value from
pipeline_key) at Mind::admit and at the helper, and eureka-state gains a
tool-level test that the typed refusal reaches the result intact.
Tests only; no production code changes.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
eureka-state on Windows could not reach the daemon: the cultnet-rs RUDP
client bound 127.0.0.1, and a loopback-bound socket cannot send to
10.77.0.1 (os error 10051). CultLib 8fc74c7 binds the unspecified address
for a remote endpoint. The daemon and the client move together, because
the ack cuts between the revs changed the RUDP handshake.
epiphany-pipeline moves to Epiphany 73edee5, which pins the same CultLib,
so one cultcache-rs is in the graph and the pipeline's CultCache types
stay Huginn's.
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>
The source runtime id adds its field name when present, so exact sizes are
searched over both paddings. The attribution test admits a campaign, which
needs its repo stewarded first.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Request sizes step by four (the payload rides as base64), so a request of
exactly the limit is not reachable through the request. The client tests use
the largest request that fits and the smallest that does not; the raw-socket
test tops a message up with a source runtime id to reach the limit and one
byte past it, which pins the limit against the transport's own refusal.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
- The client refuses a request whose encoded size exceeds what one RUDP send
carries (65,507 less the 36-byte header and the 6-byte channel id), before
connecting, as ClientError::TooLarge { bytes, limit }. It was reported as
a retryable Unavailable ("Message too long"). The MCP tools surface it as
isError with {"error":"TooLarge","bytes","limit"}.
- Arguments that fail to deserialize are still a tool error, now with the
same typed body as every other one: {"error":"InvalidInput","detail"}.
- A non-UTF-8 EUREKA_INSTANCE or HUGINN_ENDPOINT is reported as not valid
UTF-8 and not as unset.
- Tests: the schema walk asserts no $id or $schema below any tool's root; the
15 s timeout is measured against a silent daemon; the semantic part of a
query is observed on the wire; Internal's and TooLarge's bodies and the
InvalidInput rewrite are pinned; attribution is refused through the MCP
admit; oversize is TooLarge at and one past the limit.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
cargo-mutants on the Cut 13b diff: replacing get_info with Default::default()
survived, and a client that does not see a tools capability does not list tools.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
8041d82 did not build on its own: the moved Inert index names PipelineRef and
the import stayed behind in client.rs.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
The eureka-state binary serves whoami, admit, view and query over stdio (rmcp
2.2.0), each one HuginnClient call. EUREKA_INSTANCE and HUGINN_ENDPOINT are
process configuration: the server fills in the instance and provenance.tool, so
input can name neither. Bad configuration never stops startup; whoami reports
it and every other tool refuses with the typed body. A mind's refusal is a
normal result; Unavailable, Rejected and Misconfigured are results with
isError. The query input schema bundles CultLib's selection schema into $defs
(vendored; a test pins it to the cultnet-rs revision).
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>