A test with two slept nights pins that covered_through reads each night's own closing (the citation of its run), which no earlier test distinguished from the oldest Slept closing in force.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
SLEEP_GUIDANCE opens on 'Tonight you consolidate your memory.' and drops the contemplation paragraph; the night line closes on what she did with her memory, in the guidance and the schema's description. The module doc names the run the night's consolidation (rulings sleep-day-coverage-ruled, contemplation-own-session). A test pins that the start line carries the consolidation opening and that neither the guidance nor the schema invites her to think, read or look into anything.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
ResolutionOutcome::Slept { line, day_through } is how a Sleep run ends when the ledger took her reply; day_through is the last memory of her day she was shown. CitationRole::DayThrough (day_through) makes the memory an A7 referent and a cites/cited edge; admission refuses Slept on any subject but a Sleep run, a day_through that is not a memory admitted before the batch, and skips the in-force check for that role since the night may have consumed it. The outcome alias carries Slept. sleep.rs close admits the typed outcome and covered_through reads only the Slept closing in force and day_through's admission ordinal: SLEPT, THROUGH and the rationale parse are gone, and a hand closing or a withdrawn Slept covers nothing. outcome_words renders Slept as 'slept: <line>'. Published schemas and the envelope golden regenerated from the derivation.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
The day began at the previous Sleep run whatever became of it, so the memories past DAY_MAX and a failed
night's whole day never met the disposition cover-the-day requires. A night now closes with where its day was
covered through (the ordinal of the last memory it was shown), and the next day is what was admitted after the
newest night that closed 'slept:'; the first night's day is the 24 hours before it opened. A consolidation is
made by a night, whatever room it keeps, so it is not the next day's memory.
Night::from_settings carries the both-or-neither start check out of the binary where a test reaches it.
Tests pin last_sleep with the unit gone, the window's minutes and its 23 and 59 bounds, and the half-set start.
The spawn prelude leaves one_process for a shared start_session. sleep.rs is the one owner of a night: the night line (her day whole, open items, the tide), SleepReply and its schema, the decoder's ledger (every day memory exactly once, ids her memories in force, one conversation per consolidation, told back, third refusal ends it), admission of whole operations in batches that never split a consolidation, and the closing of the run with her line. The heartbeat opens one Sleep run per listed idle Mind per window (HEARTBEAT_SLEEP_UTC, HEARTBEAT_SLEEP_MINDS); a missed night is not made up and a failed one not retried.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
RunTurn gains Sleep and RunSlot/RunTurn::slot (PersonaTurn and Sleep hold the Persona slot, a Self run the other); live_holder, launch holders and the unit template compare slots, not turns. MemoryOrigin gains Sleep { run }. Admission refuses an unpaired consolidation both ways (MindRefusal::UnpairedConsolidation): a memory that consolidates others without a Superseded resolution of each by it in the batch, and a memory Superseded by memories that do not name it. Published schemas regenerated.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
load() refuses an over-cap file on its length first, so the take(MAX_BYTES + 1) on the read was
reachable only by a file that grew after that check and no test could see it. read_bounded holds the
read; its test grows a file past the cap and requires the read to stop at MAX_BYTES + 1.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
ChatDelivery gains tuple index 11, `image: Option<ChatImage>` ([path, mime,
size, sha256], a reference into her per-room image store, never bytes); the
pending kind is gamecult.persona.chat_pending.v2, and v1 answers and records
still decode with no image. chat_image::load is the one place a reference
becomes bytes: exact `<hex sha256 of room id>/<sha256>[.ext]` path with no
traversal or symlink, regular file, 5 MiB declared and actual, declared size
and sha256, png/jpeg/gif/webp magic bytes matching the declared mime. The
persona line carries the image as a base64 image block after its text and an
`attachment role=organ` line saying attached or not shown and why. The
stream-json echo of a line with blocks still counts as our echo. The store is
MIND_PERSONA_IMAGE_STORE; unset, every image is not shown.
Co-Authored-By: Claude Sonnet 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>
Moves the_stream_agent_ignores_the_proxy_environment to crates/mind-body/tests/stream_proxy.rs, as control.rs carries its env-touching tests. It asserts through the public surface: with a proxy in the child's environment the stream's agent reaches its endpoint directly and follows no redirect, and a plain ureq agent in the same environment takes the proxy. No behaviour change.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
mind-stream reads its own arguments like the other binaries, which each allow the crate's disallowed-methods lint with a reason; one range assertion written as contains. No behaviour change.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
A DM's room is its room id under the reply cut (the steward cut's hand-built DM delivery carried the alias form); a request after a result opens a turn under the task cut, so the resume cut's bound test closes that turn with a result.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Cut: State.tasks, Event::TaskStarted, the tool_use_id keying of task lines and the notification replay, and TaskNotified's tasks.remove gate. running is a copy of the CLI's last background_tasks_changed, replaced whole; a notification owes a turn when the task was backgrounded and the session did not stop it with TaskStop (or KillShell, KillBash: the stream shows the alias as the model named it); Polled and Inbox carry other_first, so a served conversation's newer brief no longer outruns an older brief of another. Fixtures bg-fgto, bg-kill and bg-monitor pin the three falsified cases; the probe's fake API gains a generic tool step and a timed scenario.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
A foreground task moved to the background at its timeout, a task stopped with TaskStop, and a persistent Monitor; scrubbed to /probe/work, the key is the fake one.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
decide owns idleness (no turn open, nothing outstanding, no backgrounded task running, no notification owed its turn) and the switch of
conversation; read_usage reads the task lines for liveness only; the CLI's replay of a task notification is no echo of ours. SelfInbox
serves one Conversation and attributes a result by the span, not by the order of the stream. Deleted: briefless_open, briefless_answers,
turn_conversation, turn_allows, may_tell, one_conversation_told, note_task, tasks, notified, the Persona pointer line and its plumbing.
ScheduleWakeup and CronCreate are denied to the Self session. Tests replay the real-order captures with briefs spliced in.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
The harness runs the CLI against the fake Messages API with a fake key and a throwaway config dir: bg and agent plan steps, a
Monitor step, --disallowedTools through DENY. Captured: an Agent call with run_in_background gives task_started
(is_backgrounded true, the call's tool_use_id) and a task_notification with the same id; a background Bash ending while no turn is open
makes the CLI begin its own turn (init, a request, no echo); ScheduleWakeup and CronCreate are absent from the init tools when denied;
a Monitor is a backgrounded task with the same two lines, so it needs no denial. Host paths scrubbed to /probe/work.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Restores LF on stream.rs, stream/tests.rs and bin/mind-stream.rs (5defa18 converted them). Renames the capped-repo test for the rule built; build_seed's since is the newest thought's label tick time; STREAM_MIN_GAP_S counts from the label, so a model run of M seconds leaves 900 - M s of quiet after admission. No behaviour change.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
A notification with no tool_use_id registers nothing (the open-turn gate still holds it by its request). Tests: the notified conversation's brief joins its turn, a notification of another conversation stays pending through a brief turn, two conversations' notifications open a turn no brief may join, an idle non-request line opens no turn, a resolved claim is read by its own key, a claimed cut spec stays on the start line.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
A request with no line of ours echoed is a turn that took in no brief, notification or not; until its result only the conversation it continues, or the notification's task's, is written. Nothing told yet means no other conversation exists.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
A reply that answers no brief, or briefs of two conversations, was read by nothing and re-paged on every Persona read. It is now a route in the public conversation marked as a pointer: the line carries the reply id and a fixed note, never its text, and the Persona reads the reply by id. Heard, it is resolved like any reply.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
The stream's task_started and task_notification events carry the tool_use_id of the call that started the task. The actuator records, per task, the briefs the starting turn was answering; a briefless result after a notification answers those (any notification it cannot place answers none). While a notification's turn is open, only the conversation it is attributed to may be written. A restart reads a resolved claim's conversation by key and opens the gate for it alone. The flush result is the note to the successor, in the journal: it is no reply. The start message states the rules.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
