Chat turns, compaction, and title calls now stamp session_id on their
cost.UsageEvent, and the done event carries session_cost_usd summed from
the operator ledger (cost.Store.SessionCostUSD). The drawer's last-turn
summary appends '$0.12 session' with a sub-cent floor. The figure is
omitted whenever any of the session's models has unknown pricing, and
free local models price known-at-zero, so no figure is ever partial.
Every registered Pulse tool now carries a canonical invocation
descriptor (internal/agentcapabilities/invocation.go): static or
discriminator-based, classifying each invocation with a workflow kind
plus a mutation target (none / pulse_state / infrastructure). Mixed
descriptors must exactly cover their schema enum and registration
panics otherwise, so an unclassifiable tool cannot exist. Missing,
malformed, unknown, or fabricated discriminator values classify
fail-closed as infrastructure writes.
Provider projection and runtime enforcement consume the same
descriptor under one InvocationPolicy (control level plus the
request-local, non-serializable deny_infrastructure_mutations
restriction, isolated across executor clones): ListTools and
ListToolGovernance remove forbidden enum values, drop empty tools, and
recompute the offered action mode, while ToolRegistry.Execute blocks
forbidden invocations before the handler runs. This closes the mixed
tool control-level bypass, most seriously Docker action:update, which
previously fell through to direct execution at read-only, and fixes
the Kubernetes misclassification: the retired switch read the action
argument while the schema discriminator is type, so type:scale
classified as read.
pulse_file_edit is now write-only (append/write); file inspection
routes through pulse_read action=file, whose exec path keeps its
structural read-only execution-intent enforcement. ClassifyToolCall
consults the descriptor table first and retains only genuinely
non-registry compatibility cases. The deny restriction is deliberately
separate from autonomous mode, which only suppresses interactive
questions and grants no mutation authority.
Proofs: descriptor validation and fail-closed classification unit
tests, plus the invocation-policy regression suite (scale classifies
write and never invokes at read-only or under deny; Docker update
queues nothing at read-only; autonomous plus deny cannot mutate;
fabricated enum values fail at runtime; filtered projection and
runtime enforcement agree; executor clones keep request policies
isolated). Contracts and registry ownership updated for the new
shared invocation descriptor boundary.
Slice 3a of the typed-lifecycle ratchet; the patrol_investigation
execution profile and patrol_propose_action tool build on this
substrate next.
Ollama is the zero-cost AI path but the setup row offered only a Server
URL, and Patrol then failed on models that cannot emit tool_calls
(#1463, #847, #1425, #1152, #880). Bless qwen3:8b, the model family
Ollama's own tool-calling docs are written against, verified locally
against Patrol's real preflight: qwen3:8b emitted the tool call on
every run; qwen3:4b never did (0/4), so no low-RAM tag is suggested.
- Registry: SuggestedModel/Note/Equivalents on AIProviderDefinition,
projected on /api/settings/ai providers; Ollama default model goes
llama3.2 -> qwen3:8b.
- Provider row: copyable 'ollama pull qwen3:8b' block with hardware
note, and a next-step hint when a successful test resolves a model
outside the blessing set.
- Model resolution: exact-ID blessed preference, so pulling qwen3:8b
makes it the auto-resolved Patrol model with no manual selection.
- Readiness copy names the blessed model (its contract pins landed
with 94ccc7a0c's staging; this commit restores green).
- manual_ollama_preflight_test.go is the env-gated re-blessing
harness; contracts updated for ai-runtime, api-contracts,
frontend-primitives, and the agent-lifecycle/storage-recovery
dependent boundaries; subsystem_lookup_test line pins follow the
api-contracts.md insertion.
Planning, approval decisions, and execution for typed resource actions
move out of the HTTP handlers in internal/api/actions.go into a new
internal/actionlifecycle.Service owned by api-contracts. The REST
handlers become thin decode/actor/error-mapping adapters over the one
shared service, and ResourceHandlers.ActionLifecycle() exposes the same
service for in-process consumers, so a future Patrol action broker
inherits identical resource lookup, availability checks, plan hashing,
audit persistence, remediation locks, plan-drift revalidation,
execution, and terminal publication instead of loopback HTTP or a
parallel lifecycle.
Behavior is preserved: same status codes, error codes, and audit/
lifecycle persistence ordering, backed by the existing api contract
tests plus new fail-closed proofs for the service itself (unknown
resource/capability, availability refusal, unapproved execution,
remediation lock, plan drift, missing executor, missing store).
Contract text in api-contracts, agent-lifecycle, and storage-recovery
now names the service alongside actions.go and planner.go; the
subsystem registry owns internal/actionlifecycle/ under api-contracts
with a dedicated path policy; the code-standards and contract source
pins follow the moved invariants; and the subsystem_lookup line-number
pin shifts with the api-contracts canonical-files list insertion.
This is the first slice of making the typed action lifecycle the only
autonomous execution route for Patrol, Assistant, and MCP.
Reuse shared release-line validation for Docker, floating-tag, and Helm artifact workflows so stable patch tags can publish from the previous stable tag without a fabricated same-version RC.
Capacity forecasts (days-to-full, current usage, trend) were previously
computed deterministically but only fed into LLM prompt text. They never
reached the finding as structured data, so the frontend could not render a
verified urgency signal and the model's speculation was the only thing the
operator saw.
This persists CapacityForecast on Finding (marshal-mirror pair) and stamps
it post-analysis via a service join (StampCapacityForecasts). The forecast
filter now also keeps stable-high (>=80%) pools so the deterministic "no
fill trend" reading wins over model speculation, and fixes isQuiet wrongly
treating stable (-1) trends as filling.
Frontend maps the forecast through the UnifiedFinding view model and renders
a deterministic urgency line (Filling up / Stable / days-to-full · % used)
in the expanded finding detail.
Note: forecasts only populate for resources whose usage is ingested into
metrics history (Proxmox/Ceph storage, nodes, guests). Agent-host storage
(unraid pools) is not yet ingested as a time-series and remains a follow-up
to activate the feature for those pools.
Refs lane: protection-posture-attention-queue
Agentless availability checks (ICMP/TCP/HTTP) were always minting
standalone network-endpoint resources, leaving them disconnected from
the known Proxmox/Docker guest they actually monitor. This made
availability evidence invisible on the platform resource row where the
user expects it, per the performance-and-scalability bounded-row
contract.
Backend (unified-resources ingest):
- Add LinkedResourceID field to AvailabilityData and AvailabilityTarget
- resolveAvailabilityLink: explicit link first, then exact-IP unambiguous
correlation; skip hostname-only (lossy); guard against overwriting a
different target's facet
- Unlinked/unmatched probes still mint network-endpoint (fallback)
Frontend:
- Relax getAvailabilityProbePresentation for any resource with availability
- Add compact protocol badge to UnifiedResourceHostTableCard name cell
- Add optional 'Link to resource' field to availability target form
- Add linkedResourceId to frontend types
Contracts: api-contracts, unified-resources, monitoring,
performance-and-scalability, storage-recovery.
Governance: coverage_gap + candidate_lane in status.json.
The alert AI button now offers a manual targeted Patrol check alongside the
existing context-only Pulse Assistant handoff, so the take-the-lead intent routes
to Patrol (the investigator) instead of overloading Assistant (the explainer).
POST /api/ai/patrol/run (HandleForcePatrol) accepts an optional scope body and
routes through the same TriggerScopedPatrol engine and scoped run record as
automatic alert-triggered work, not a new trigger route; empty body keeps the
legacy fleet-wide run. Scoped runs honour Patrol readiness but bypass the
full-run cadence gate, consistent with the existing scoped-cadence rule, and
carry resource identity only (no command or remediation payload).
Frontend: triggerPatrolRun(scope?) and a split AI button (patrolOption) on the
alert overview card whose menu runs the scoped check; icon/history rows stay
single-purpose. Contract updates land in the touched/dependent subsystem docs
(ai-runtime, api-contracts, agent-lifecycle, storage-recovery, frontend-primitives,
security-privacy, patrol-intelligence, alerts); subsystem_lookup_test line
expectation refreshed for the api-contracts shift.
The free Patrol working surface stays clean of ambient paid surfacing, but a
plan-locked operator who expands an active critical or warning finding now gets
one honest, non-salesy capability line in the empty primary-action slot: "Pulse
Pro can investigate and fix issues like this." A "Learn about Pulse Pro" action
appears there only when the upgrade-prompt policy allows it.
This is the single allowed contextual at-need prompt — gated to plan-locked
installs, active critical/warning findings, and the upgrade-prompt policy — so
discovery happens at the moment of genuine need without re-tainting the daily-use
surface. Adds getPatrolProInvestigationHandoff in patrolControlPresentation,
threads the handoff through PatrolIntelligenceWorkspace into FindingsPanel,
codifies the carve-out across the owner and dependent contracts, and registers
the patrolControlPresentation test as patrol-page-and-state proof.
Add a registry-backed provider model for runtime metadata and chat-compatible transports.
Support Z.ai, Groq, Mistral, Cerebras, Together, and Fireworks through the shared chat-compatible client path while keeping native providers on their existing adapters. Expose provider metadata through settings and render the expanded provider set in the frontend.
Manifest-backed MCP tools, prompts, and resources with surface affordance contracts; agent capability manifest and governance projection; API contract tests and capability route projection; operations-loop and intelligence-funnel telemetry; release-control subsystem documentation, registry, and tooling; licensing and configuration.
rcourtman