Who wakes is decided from the room as the round opens, as one heartbeat poll decides from the pending it read, so a line spoken this round counts toward a cap from the next round. A room that woke her but was not read stays unseen and wakes her next round. Tests: a DM and a #minds address answered in rounds 1 and 2; Soul's three rooms answered in three rounds, one turn a round, under ruled and names_with_cap.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
People::person_of is the one key reader for senders, targets, about: tags and bond objects. A value has no mark in the schema; one that carries one is not rendered. Tests: both spellings of a Mind behave alike for target and about:, a bond keyed by full ids is found, a marked value never renders.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- A quotation is standalone when it, marks included, is a run of whole top-level sentences; any other is framed, and a line may not start or end strictly inside it. A line holding a framed quotation whole stays sayable.
- The three-word refusal against private items is deleted: whether a line tells a confidence is meaning, the Interpreter's judgement over the private list it is shown.
- An opening mark left unclosed (the budget cut her prose) is stripped from the sentence it starts, so the sentence is citable and the line carries no stray mark.
- Tests: every F1 probe refused (stray inch mark and scare-quote plan included); Weksa's hedge and a whole scare-quote sentence said; Weksa r6 and r10 said; the Q5d test keeps the prompt list and shows no word match refuses.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
woken() returns one wake per room; every turn of hers in a round reads from where the round found her, so a direct message is never marked seen without a turn. Test: a DM and a #minds address in one round give Libby a turn in each, each reading only its own room's line.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Every cited span starts and ends on a UAX#29 sentence boundary; the spans of one line are consecutive sentences, and the line is that unbroken run of her prose. A quotation's inside is segmented as a text of its own, so quoted speech stays sayable. She cannot say half a sentence.
- The prompt lists what she knows privately and allows plain speech of a private matter only to its person, in a DM with exactly them. Code refuses a line that shares a run of three words with a listed item.
- Tests: Soul's Q1a-Q1d refused, Q3d refused on a beat, Q5d refused in a DM with Libby, R9 said, P3 still refused; Hands' "Fine," + "winter" test rewritten.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- concerns(): private is extensions.privacy, a private tag, or a room:! tag; it is about target/object person, else an about: tag, else the DM's partner, else everyone. private_elsewhere is deleted.
- scope(): plain only in a DM whose members are exactly her and that person (a partner-only item: in its own DM, still two; an everyone item: her own room); left out where the person is in the room, a group DM included; framed elsewhere.
- Applied to memories, shortTerm, incubation, needs, doctrine stances and bonds; history.said in a DM is private about its partner.
- Packet.private carries the framed items' words for the Interpreter; a beat's bodies are the tail lines its stimulus quoted.
- Tests: Soul's Q5a-Q5c, the DM-memory test rewritten for the room-tag rule, the said pool; the golden packet moves because dm-secret is now framed in public.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Self's decision: the blanket framing smothered relationship texture in public rooms. A bond or memory is private only
when marked (`extensions.privacy = "private"`, or a memory's `private` tag); the schema is unchanged. A marked item
renders as written in a direct message with the person it is about, is left out about someone present in any other
room, and is framed "she knows privately" about someone absent. Unmarked items render as written everywhere. The
Interpreter's rule about private knowledge stays. The convention is documented in the Persona State Standard
(gamecult-ops `docs/persona-state-standard.md`, GameCult/gamecult-ops#129).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Soul's hold on #81 and Self's privacy decision.
- F1: a spoken line is exactly the spans of her prose the Interpreter cites, located in order by Ghostlight's
SourceSpan::locate and joined with one space. The model never writes the words; `text` is gone from the contract.
The Persona writes the words she would type, never a description of them. Given up: indirect speech and any
paraphrase by the Interpreter.
- F3: Huginn owns a short chat Interpreter prompt (what, where, to whom; gaps conditional, addressee, elsewhere);
Ghostlight's membrane and the INTERPRETER_GUIDANCE patch are gone. `[interpreter]` keeps only the model.
- F2: an echo is a line of four words or more whose word trigrams are mostly the heard message bodies
(heard_overlap); short answers are never echoes.
- F4: mentions and reply targets only for people this packet showed her.
- F5: a line said once; at most two lines a turn.
- F6: stale docs on the Mind run, the exchange and the policies.
- F7: a human's line ends a Mind's run only in a room the run has lines in.
- Privacy: she speaks only in the turn's room; the Interpreter is told the room, its kind (public, her own, a direct
message) and who is in it, and not to say in a room what she knows privately; the packet frames bond summaries and
memories about a person as known privately everywhere but a direct message with that person.
- The simulation's turn is in the room of the line that woke her.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Speech (Soul F1): `projection::interpret` is the Interpreter's speech step, one tool-less structured call through the
connector under Ghostlight's Interpreter membrane, over her prose, her lived stream, the stimulus, the rooms she may
speak in and the people she may address by Matrix id. It proposes lines, each with a room, structured mentions and a
reply target, and the verbatim span of her prose it rests on. Code keeps a line only when the span locates in her prose
(Ghostlight's SourceSpan::locate, map 4.3), the room is hers this turn, and its words are not what she heard; it drops
mentions or a reply target naming anyone not shown, and records every refusal and drop. An answer that is not the
contract is a failure, never a silence. `--through interpreter`; the batch and the simulation run through it, and in
the simulation the only explicit addressees are its structured fields. `would_say`, `inner` and the quote parsing are
gone; the Persona stage writes her thought with no speech convention. Tuning gains `[interpreter]`.
- F2: she is in a room's exchange when she spoke there within `exchange_minutes` (default 30).
- F3: the Projector guidance names no duty, not even to deny one; "X is waiting on her" only when true.
- F4: the narration metric is a lexical overlap, labeled so.
- F5: a scripted direct message in one of the plan's rooms is refused.
- F6: the Mind-run cap counts one run per Mind across her rooms; LineFacts::default() is at the cap (fail-safe).
- F7: an unbonded sender is labeled by display name and full id, or the id: never a bare handle.
- F8: a room is named by the key the tail carries (alias, or a direct message's id); a public room's id is reported,
not mapped, since no table in her body maps it.
- F9: group-state parts are sentences, the person waiting on her first.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Projector (the operator: "Sounds like a Projector issue"):
- The group state is the conversation as it stands, in one room: who is talking with whom, a human's question to the
room that others answered as covered (one nobody answered goes unmentioned), when a human last spoke, Mind lines in a
row, and a human waiting on her by name. Never what she owes. Every count covers the window the line describes (S4);
never several rooms folded together, never a direct message into a public room (S3). Default group_lines 12.
- Absent state is left out: no "mood: none recorded"; a bond, need, memory, stance, wondering or value without content
is not rendered, and a bond without trust or tension says neither.
- Guidance: never retell what she heard (it reaches her verbatim), render what it stirs; never a debt; no options; leave
out what the context does not carry; use pronouns as given. Metrics, not filters: heard_overlap (word trigrams shared
with the heard lines) and offers_options (a narrow lexical flag), per render and per run.
- Pronouns: `[pronouns]` in the tuning by Matrix id, the swarm's people as the default, they/them for anyone else; the
persona schema has no pronoun field for another person. A pronoun line names everyone the packet shows from the room.
The packet speaks of her in her own pronouns throughout ("Said to him:") (S5).
- Bond lines put the kind after a dash and lists use semicolons: a label may hold a comma ("Meta, the operator").
Persona stage: continues her inner stream in the first person; speech only where her thought moves her to it, in double
quotes; others' words she recalls in single quotes; @handle tags someone. The report shows her inner prose apart from
what she would say.
humans_pace (ruling persona-only-humans-pace; the operator's words that Minds' explicit mentions wake too):
`HumansPace(cap)`: a human's line wakes her in her own room or a direct message always, and in a public room when it
addresses her or continues an exchange she is in (an exchange ends at a gap over exchange_gap_minutes, default 20); a
Mind's line wakes her only by a Matrix mention or a reply, in any room, while fewer than `cap` Mind lines in a row came
before it. Own rooms come from the plan: neither the heartbeat's table nor persona.env records ownership. Live is
unchanged. In the simulation a said line's @handle of a cast member stands in for a Matrix mention.
Soul's hold:
- S1: Config::new refuses an operator id that is also a persona's.
- S2: the simulator's beat asks heartbeat::addressed_by_member over the deliveries the mouth would give her.
- S3: --in given as a room id is read by its alias.
- S6: a scripted direct message names its recipient (`to`), is seen by sender and recipient alone, and wakes only her.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- F1: `heartbeat::wakes(policy, addressee, delivery, speaker, mind_run)` is the one wake rule. The poll asks it with
`WakePolicy::Live` (behaviour unchanged until `po-mind-wakes-mind` is answered); the simulator asks it with the plan's
policy: `ruled`, `humans_pace`, `names_with_cap = N`, `all_messages`. The simulator reads each persona's addressee from
the heartbeat's addressing table (stewarded project names included) when the plan names `heartbeat.cc`.
- F2: the beat falls on `beat_s` of simulated time and wakes one Persona, the winner of `tempo::pick`.
- F5: Mind-addressed evidence is counted per wake (its strongest evidence), not per line.
- F6: reply chains are per room and count Mind lines spoken in turns another Mind's line woke.
- F7: a failed call is a failure, apart from silence; silence rate is per woken turn that did not fail.
- F8: a test that another seed changes the order.
- F9: `--state` docs say P4 and P5 are not checked.
- Group state (`select.group_state`, default on): one packet line over the room's last `group_lines` lines: who spoke
to whom, when a human last spoke, how many Mind lines in a row, lines to her, an open question to everyone. Inside the
context budget, narrated by the Projector like every other line; golden fixtures for the four scenario rooms.
- Reports: wakes by cause and by round, per-room chains, failures, 18 representative lines, the explicit-addressee gap.
- Tuning: `persona.words` and `persona.guidance` get the upper bounds the Projector's knobs have.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The harness judges candidate persona states before any Mind holds them, through the
same `project` the live turn will use: every case is one `project` call.
- `--room <fixture.toml>`: a mocked room in place of the mouth and the room tail:
her id, rooms, messages (sender, display name, room, ago, body; new, tag,
mentions, dm, follow_up, reply_to), a mocked now and a "last heard from" table.
The fixture is a MouthReader, so addressing is still `address::is_for`. The live
room filter that `--room` used to name is now `--in`.
- `--state` is checked as a put checks content: huginn-mind's P1 to P3 now live in
one owner, `persona::validate_document`, which the put calls.
- `--through persona`: the Persona stage (C3b's first piece). One tool-less
connector call under Ghostlight's persona membrane over identity, narration and
the heard lines; prose capped at 180 words; would-say lines are the double-quoted
spans; usage per call. Tuning gains `[persona]` (model, guidance, words).
- `--batch <plan> --out <md>`: states x scenarios x samples, one Markdown report
with packets, narration, prose, would-say lines, word counts, distinct-2 and
cross-state word similarity, and a total-usage footer.
- `--simulate <plan> --out <md>`: up to eight personas taking turns in one room.
Wake is is_for plus the ruled set (addressed, any human in her rooms, the beat);
`wake = "all_messages"` is the old loop as a control. Woken personas run in a
seeded order; quoted lines join the room as from her id. State does not evolve
(`state_after_turn` is the seam for C3b/C3c). Metrics: messages, silence,
who addresses whom, Mind-to-Mind chains, lexical convergence, a work-talk
heuristic, usage.
- With a state file and a fixture no daemon and no mouth is needed (bin test).
- Request ids take the wall clock, so a fixture's fixed now cannot replay.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
T1: address.rs names_whole_word: a name is glued only by a letter or digit, or
a single hyphen with one beyond it; every other character is a boundary, so
_Eureka_, Eureka/Libby, ok...Eureka? and Huginn.toml name her again and
mind-eureka does not. Soul's 72 forms pinned.
T2: said_to_her decides once; stimulus and heard both carry the count.
T4: Model::ask fails with Failed { reason, usage }; a failed render or judge
call is recorded with its usage and the report goes on.
T5: the sentence cut keeps at least 60% of the budget; 。!? end sentences;
CJK characters are words. T6/T7: spoken is a JSON string; a display name is
quoted, capped at 80 bytes and followed by its Matrix id. T8: the addressing
report gives the table's age and why it was not used. T9: own beat lines
excluded (tested); words, stimulus, item and the other parts bounded.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
S1: to_her is address::is_for over the heartbeat's addressing row (own names
when there is none); a name inside a path or identifier no longer addresses
her, in address.rs itself. S2: room talk is headed Also in the room. S3:
addressed_bytes (8 KiB) bounds the messages to her, newest first; one larger
message is clipped between graphemes with its remainder counted. S4: one
escape (spoken) renders every body. S5: only short-term items decay; memories,
values and stances come forward by lexical relevance to what the room said;
the lens is drawn from included items. Lows: people keyed by full id except
the operator and the Minds; unbonded speakers shown with their id; tuning
refuses an empty model, a temperature outside 0.01..10, all-zero caps and an
overflowing identity; the guard folds kebab and run-together forms; a beat
respects small caps; project refuses without MIND_PERSONA_SELF_SENDER.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
Recall now reads only memories of the cued sorts: follow-ups, rulings and the
open-item filter leave it, with the tests that pinned them.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The upgrade gate opened instance eureka only, and Mind::open refuses a store
whose instance document names another Mind, so no other Mind's store could be
gated. gamecult-ops now gates every store before a release moves any daemon.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Removed: launch's run opener and its types, queue's queue and breaker,
heartbeat's Night; changed: heartbeat Config and HeartbeatState.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
F4: the night wake started a plain mind-persona@ unit and traced it as
Sleep and "asleep". Deleted the night branch, Night, Config.night, the
HEARTBEAT_SLEEP_UTC and HEARTBEAT_SLEEP_MINDS settings and
HeartbeatState.last_night_at (added by this PR, never deployed, so nothing
must decode it). A wake's trace entry is her slug. Reflection and
consolidation return in C4.
F6: deleted a_flag_overrides_the_environment (asserted exit 0 with the
config discarded) and the heartbeat test that compared two identical rigs.
F7: Cargo.toml no longer says the Persona drains her chat or that launch
opens runs; heartbeat.rs no longer says Persona units read its addressing.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>