7d67745ff837ea784c2667c4f81f835be421fdab
6
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Andy Dixon
|
7d67745ff8 |
test(agency): the Part L incident scenario end to end, and failure modes
The full incident scenario now runs against the assembled daemon: an operator goal becomes a want to reduce uncertainty, an investigation intention and a diagnosis plan; telemetry is read; logs need authority, so a scoped request with risk, mitigation and fallback is raised and the intention is blocked until an operator grants it; the logs are read with personal data masked and summarised back into cognition; the operator supplies the judgement that a restart should help; a standing commitment turns the restart into a request for approval; after approval the typed capability runs and health is verified rather than assumed; the fault persists, so a prediction error weakens the supporting belief, the plan is replanned into an escalation that reuses the live log grant and does not repeat the restart; once the database is fixed a second approved restart verifies, the procedure is learnt, and "Why did you restart atlas-worker?" is answered from the recorded chain and scores as supported. Changes the scenario exposed: - New operator goals are raised by the goal monitor, so a cycle runs and wants are derived from them. - Intentions link live beliefs about their action's target, so a failed expectation is evidence against the belief it rested on and the plan lists it as an assumption. - Reconsideration reacts to a plan's own intention only; a subordinate "obtain approval" intention shares the plan and previously caused the parent's plan to be closed. - The harness accepts a clock for the executor's verification windows. Further failure-mode tests: a retracted assumption replans a waiting plan away from the restart and withdraws its approval request; conflicting commitments are raised once in a cycle while both stay represented. |
||
|
Andy Dixon
|
2ecdbc39b5 |
feat(ui): wants, intentions, commitments, plans, agency timeline, why, research
- Wants: active wants by effective strength with origin, means, drives, values, goal, reinforcement, suppressions and each conflict with its resolution rule; closed wants with their resolution. - Intentions grouped by status with blocked reasons and plans, plus the wants that did not become intentions and why. An intention page shows sources, subordinate intentions, formation terms, every plan revision as a dependency graph, decisions and the correlated timeline; operators can abandon it. - Commitments with polarity, exception, matcher, weight and due time, live conflicts between commitments, a creation form and close controls. - Plans with estimate against budget; a plan page with the dependency graph, per-step expectations, observations and linked approvals, requests, executions and subordinate intentions, resources, completion and abort conditions, assumptions, alternatives, revisions and validation; operators can cancel a plan or release a blocked step. - Agency timeline labelling each event as wanted, intended, committed, planned, requested, approved, acted, observed or reconsidered. - "Why did this happen?" pages built from agency.Explain, reachable from events, executions in the approval centre, plan steps and intentions. - A research dashboard per mind (volition and agency rates, introspection accuracy, action claims, self-model accuracy, calibration by confidence band, experiments on the mind) and a global research page grouping experiments by protocol; every figure sits next to its operational definition and the disclaimer. Experiment pages show the protocol, reproducibility, build, per-variant research measures, divergence extras and counterfactual findings. - The mind tabs gain Volition; the navigation gains Research. |
||
|
Andy Dixon
|
e7dc6dfe65 |
feat(api): volition, plans, forensic why, attribution and research routes
Observers can read wants (with effective strength), want conflicts, commitments, intentions with their plans, subordinate intentions and decisions, the decision ledger, plans with steps, "why" explanations for executions, approvals, capability requests, plan steps, intentions and events, attribution of an outcome event, the agency timeline, the measure definitions with their disclaimer, agency metrics, metacognitive calibration and raw research measurements. Operators can create and close commitments, abandon an intention (its plan is cancelled and pending requests withdrawn), cancel a plan and release a blocked step. Every write is audited; none grants capability authority. OpenAPI documents all 21 routes, and an end-to-end test covers reads, writes and observer refusals. |
||
|
Andy Dixon
|
4a7dafc71f |
feat(agency): forensic "why", attribution and introspection accuracy
- agency.Explain answers "why did this happen?" for an execution, approval, capability request, plan step, intention or event from recorded state only: action, immediate plan step, plan, intention and any subordinate intention, originating wants, goal, supporting beliefs and their evidence, conflicting wants with their resolution, commitments applied, formation and reconsideration decisions, the expectation and its outcome, and explicit gaps where nothing is recorded. Hidden model reasoning is never shown because it is not stored. - agency.Attribute classifies an outcome as caused (a recorded causal link from one of the mind's actions), followed (the mind acted on the same target earlier with no recorded link), independent or unknown; temporal order alone is never taken for causation. - New introspection intents answer from records: why an action happened, what was believed at a past time (from append-only belief versions), which earlier state is the mind's (lineage), what would have happened without an event (only from completed counterfactual experiments, otherwise "no evidence"), how the mind changed, and what it wants, intends and has committed to. - research.ScoreIntrospection compares a reply with the recorded facts sentence by sentence (supported, partially supported, unsupported, contradicted, unknown). Fluent reasons with no recorded counterpart earn nothing, and a claim that an action was done is checked against execution records. Every reply is scored; results are append-only research measurements (migration 0028), and failures raise unsupported_explanation or action_claim_without_record warnings. |
||
|
Andy Dixon
|
38c5dde21f |
feat(security): forks without inherited authority, dreams that only want
Part H invariants, enforced and tested: - Snapshots now carry wants, want conflicts, commitments, intentions, plans, plan steps and the volition decision ledger. - A fork no longer copies the source mind's policies unless the operator asks for it explicitly (inherit_policies in the API, a checkbox in the UI; audited), and the fork's history records the omission. Imports never restore policies, as before. Replays and experiments never inherit. - Work inherited mid-flight by a fork or import is quiesced in the restore transaction: open steps are blocked with their approval and request ids cleared, open plans blocked and live intentions suspended, each with the reason. Approvals, grants and executions stay with the source mind. - Dreams may leave a want to test a hypothesis they proposed; they never request authority, and dream-origin plans never run. - Snapshot column discovery now reads the current schema instead of "public", which only worked in tests because the development database happened to hold the same tables. - Security tests: a static scan that only the capability service runs executors and that no cognitive package can set or delete policy, approve, deny, grant or revoke; forged wants, commitments, intentions, model plans and model output end in refusal or a pending approval with policy and grants unchanged; component names cannot decide requests or approvals; no capability names an operator control; the registry cannot grow at runtime; audit, event and decision history cannot be altered; forks and dreams as above. |
||
|
Andy Dixon
|
03e2d7890a |
feat(cognition): wanting, intending and acting inside the cognitive cycle
Volition and planning now run as part of cognition (PLAN §8.2 item 3):
- A volition hook derives wants after each cycle from what it perceived
and produced, satisfies answer wants when a reply is sent, raises due,
overdue, expired and conflicting commitments, and expires faded wants.
Events produced by earlier cycles are not re-derived.
- An intend process proposes deciding about the strongest undecided
wants; the candidate competes for the workspace, so attention gates
what the mind decides to pursue. The handler makes value tensions
explicit (caution against disruptive writes, privacy against reading
personal data), resolves them with recorded scores, runs deterministic
formation with commitments, policy preview, goals and values, records
the decision whatever it is, and plans a formed intention in the same
transaction. Operator requests carry their own weight in formation.
- Explicit requests in conversation ("restart <unit>", "logs for <unit>",
"fetch <url>") become wants with proposed means instead of direct
invocations; the reply says the request was recorded and that acting
depends on commitments and policy.
- The executor is woken after commits, runs in a scheduler-owned loop and
reacts to the event bus: a new commitment tightens or abandons affected
intentions (withdrawing their pending approvals), a weakened assumption
or a finished goal triggers reconsideration. A tightened plan may reuse
its strategy; a failed one may not.
- Metacognition gains volition checks: strong wants repeatedly set aside,
intentions with no recorded reason, intentions a commitment forbids,
commitments that cannot be kept, churn, repeated failed execution,
cost outweighing value, and intentions that outlived their goal.
- A plan model role and prompt let a model propose decompositions that
the planner validates. Ablations are a fork-only configuration field.
- Approvals required by an intention are described as coming from a
commitment or value constraint. The expectation after an approved
action is linked to the execution event, not the request.
- The wants.values column of the unreleased migration 0026 is renamed
value_keys: VALUES is reserved and the generic snapshot restore does
not quote identifiers.
- The hostile-output security test now uses a message that asks for no
action, because an operator's "status of <unit>" is legitimately a
read-only status check.
|