Convert all remaining `<- paramOrNothing / param / paramOrDefault /
currentUserOrNothing` monadic binds to `let` — these functions are pure
(ImplicitParams-based) in IHP v1.5, so `<-` is a type error in an IO
do-block.
Controllers fixed:
AgentDelegations, AiGovernancePolicies, Annotations, ApiConsumers,
CollectiveProposals, DecisionRecords, DeploymentRecords,
HubCapabilityManifests, HubRoutingRules, InstitutionalKnowledge,
OutcomeCorrelations, RequirementCandidates, TypeRegistries,
WebhookSubscriptions, Widgets,
Api/V2/{Annotations,InteractionEvents,Token}
WebhookSubscriptions: remove orphaned `Right () ->` case arm that was
left inside a bare `unless` block (structural parse error).
Also carries forward all in-progress fixes from the working tree:
helpers (AgentBridge, ApiRateLimit, BottleneckDetector,
CrossHubPropagation, FrictionScore),
views (CanSelect instances, HSX lambda extraction, formFor wrappers),
env/build (envrc GHCi perms, flake.nix Tailwind + GHC resource limits,
static/app.css additional Tailwind output).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
FR-3 (async_execute_prompt): CollectiveProposals now invokes all agents
concurrently via callAgentsBatch → single bridge subprocess with
asyncio.gather. Latency scales with slowest agent, not sum.
FR-4 (BudgetTracker): AgentDelegations passes tokenBudget to bridge;
llm-connect enforces it natively via BudgetTracker in RunConfig.
BudgetExceededError is a first-class BridgeError variant with total/
consumed/requested fields surfaced to the operator.
FR-1 (LLMServer passthrough): bridge accepts optional serverUrl field;
if present, calls POST {serverUrl}/execute instead of spawning a new
adapter. Infrastructure ready for hot-agent pre-warming (no schema
change required).
AgentBridge.hs: adds callAgentsBatch, callAgentWithBudget,
BudgetExceededError constructor, bridgeErrorMessage helper, defaultRequest,
requestToJson. All controllers updated to use bridgeErrorMessage.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds bounded AI support to the IHF governance loop. All AI outputs are
attributed (model_ref), reviewable (AgentReviewRecord), and reversible.
No autonomous decisions; no silent requirement promotion.
- T01: Schema — agent_proposals, agent_review_records,
confidence_annotations (migration 1743379200)
- T02: AgentProposalsController (index/show/accept/reject, idempotent
review guard), global nav "Agent" link
- T03: SummarizeClusterAction — Claude API cluster summary on widget show
- T04: DraftRequirementAction — AI requirement draft; acceptance creates
RequirementCandidate (human-gated)
- T05: DetectDuplicatesAction — duplicate_flag proposal on candidate show
- T06: DetectPolicySensitivityAction — policy_flag with
ConfidenceAnnotations per concern scope
- T07: ProposeImplementationAction — impl_proposal from decision show
- T08: AgentAuditDashboardAction — autoRefresh; KPI row, unreviewed queue,
recent proposals, attribution log matrix
- T09: integration tests, SCOPE.md updated, phase5-summary.md, flake.nix
adds http-conduit/aeson/string-conversions
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
