Andy Dixon
9b2521bffd
A statement made to a mind is now three things kept apart: the observation that it arrived, an append-only assertion (attributed actor, stance, certainty, modality, negation, reported or quoted speech, hypothetical status, interpretation confidence and notes), and, only for factual assertions, one piece of evidence for a proposition belief attributed to whoever actually stands behind it. Reported speech is attributed to the person reported and weighed as second-hand; hypotheticals, questions and imperatives create no belief; expressed doubt counts against; a possibly sarcastic remark is recorded with low interpretation confidence rather than guessed at. Interpretation is deterministic code; a model may enrich the claim list but never sets stance or confidence. Association no longer treats conversational turns as world events: hypotheticals, questions, requests and consecutive turns by one speaker cannot seed causal hypotheses. Adds internal/epistemics, migration 0018, the assertions API, assertions on belief pages and in belief detail, a shared end-to-end test harness (tests/harness), end-to-end tests for eight speech patterns, and updates the milestone test to the new provenance.
4.6 KiB
Conversation
Observation, assertion, belief
Three things are kept apart when somebody speaks to a mind:
- Observation. The message arrived. This is certain and is recorded as an
observationevent with the speaker, channel and trust level. - Assertion. The speaker took a stance on a proposition. This is recorded in the append-only
assertionstable with who is attributed (the speaker, or the person they quote or report), the stance (asserts, denies, doubts, questions, supposes, reports), the certainty they expressed (asserted, hedged, uncertain, emphatic), the modality (factual, hypothetical, reported, quoted, imperative, question), negation, and an interpretation confidence with notes that say how sure the reading itself is (possible sarcasm, diffuse attribution, a conditional). Interpretation is deterministic (internal/epistemics.Interpret); a model may enrich the claim list but never sets stance or confidence. - Belief. Only factual assertions, direct or reported, create or feed a proposition belief, as one piece of evidence whose family is the attributed actor and whose weight follows the stance, certainty, second-handness and interpretation confidence. Hypotheticals ("imagine Bob…"), questions and imperatives create no belief. An expressed doubt ("…but I don't believe her") records the reported claim and adds the speaker's doubt as counter-evidence. Reported speech is attributed to the person reported and weighed as second-hand.
So "Andy says Steve steals laptops" yields an assertion by Andy (high interpretation confidence) and a claim belief about Steve at claim confidence, resting on one family (actor:andy). Repeating it does not strengthen it; an independent source would. "Alice thinks the server is compromised" is attributed to Alice, marked reported, and weighs less. "I have high confidence that Andy asserted X" and "I have low confidence that X" are therefore two different rows and two different numbers.
A message to a mind is never forwarded to a model. It goes through the cognitive cycle (spec §38):
message ──▶ observation event (trust: user/operator, channel, actor, reference)
──▶ perceive process: deterministic analysis (intent, entities, claims, urgency),
optionally enriched by the perceive prompt → "perceive" candidate
──▶ attention competition (with recall and association candidates)
──▶ perceive handler: perception event, episodic memory, claims → beliefs,
response intent built from beliefs and memories, reply wording,
response_generated event citing everything used
──▶ message row (role: mind) linked to the event, the intent and the model call
Intents
The deterministic analyser classifies each message as question, statement, request, correction, greeting or introspection. Introspective questions are answered from state, not invented:
| Question | Source of the answer |
|---|---|
| What are you thinking about? | workspace and working memory |
| What do you believe about X? | belief search plus memory retrieval for X |
| Why do you believe that? | the evidence rows of the best-matching belief |
| What are you uncertain about? | beliefs in the 0.3–0.7 band or contested |
| Which beliefs contradict each other? | contested beliefs and their contradiction links |
| What did you learn this week? | memory and belief creation events in the last seven days |
| What have you changed your mind about? | beliefs whose status changed, with the recorded reason |
| predictions / curiosity / surprise / patterns | declined honestly until those subsystems exist |
Statements and corrections become claims: beliefs with the message as evidence (weight by certainty, credibility by trust). Contradictions with existing beliefs are detected and reported in the reply. Requests are declined while the mind has no capabilities, citing the self-model.
Wording
If a model is assigned to the respond role and the per-cycle budget allows, the respond prompt receives the personality brief, the intent, the cited beliefs and memories, the uncertainty note and the self-model limits, with the user message in a data block. Otherwise the reply is a direct, plain rendering of the intent with confidences shown and a note that no model was used. Either way the stored intent lets an operator check that the words match the evidence.
Provenance
The response_generated event cites the observation, the perception, every belief and memory used, the episode written, and the model call. The chat page shows "why this reply" under each answer and links each turn to its event.