A fresh install's natural first question ("how is my machine doing?",
observed live with Ollama qwen3:8b) made the model call pulse_summarize
action=fleet without resource_ids; the tool errored and the agentic loop
surfaced a structured question asking a first-run user for "the
comma-separated list of resource IDs" — pure jargon, funnel-killing
(GitHub discussion #1042). Two root fixes:
pulse_summarize self-targets. action=fleet with resource_ids omitted now
enumerates the known fleet from the executor's unified resource provider
(infrastructure parents first, then guests, then storage; deduped;
bounded at the existing 50-resource cap with a truncation note). Both
modes resolve what models actually pass — canonical unified IDs and
unambiguous names — onto the reporting request shape the way the API
path's resolveReportSubject does: the canonical ID stays ResourceID
(findings/recovery keying) and the resolved metrics target rides
MetricsResourceID, so store queries find data instead of silently
returning zero points. Reporting types are classified from the unified
resource (agent-backed hosts "agent", pure Proxmox nodes "node" — the
documented target-type exception — Docker hosts "docker-host");
resource_type becomes an optional filter/default. Remaining error paths
instruct the model to enumerate or retry and forbid asking the operator
for resource IDs.
Ask-user policy covers tool-argument recovery. The system prompt's
resolve-before-asking section (945e2198's target policy) now extends to
failed tool calls: missing/invalid arguments are self-recovered
(enumerate, retry), and internal identifiers are never valid questions.
The pulse_question description carries the same prohibition so the
structured clarification surface cannot become an identifier elicitation
channel on small local models.
ai-runtime and api-contracts contracts updated in-commit (the
subsystem_lookup line pin follows the api-contracts insertion); full
./internal/ai/... and ./internal/agentcapabilities/... suites green.
The core.bare=true corruption of the shared repository recurred on
2026-07-17: a script that runs scratch git commands while the pre-commit
environment from a linked worktree (absolute GIT_DIR) is still exported
re-initializes the REAL repository as bare. a0fda6b26 fixed four helper
test files but missed two spots in scripts/release_control/internal:
- verify_commit_slice_test.py's git() helper only popped GIT_INDEX_FILE,
so its scratch 'git init' calls re-init the real repo when GIT_DIR is
inherited. It now scrubs via the shared repo_file_io.strip_local_git_env.
- verify_commit_slice.py's production git_env() kept the inherited hook
env even when unit tests patch REPO_ROOT to a temporary repository,
pointing git plumbing (including index writes) at the wrong repo. It
now scrubs in the test-patched branch only, matching format_staged_go.
Regression teeth:
- verify_commit_slice_test.py gains a canary test that exports the real
hook env shape (absolute GIT_DIR + GIT_INDEX_FILE, no GIT_WORK_TREE —
with GIT_WORK_TREE set the corruption does not reproduce) against a
scratch repo + linked worktree and asserts core.bare stays false.
- repo_file_io_test.py (runs in the pre-commit battery) gains a static
guard failing any release-control *_test.py that runs scratch
'git init' without referencing strip_local_git_env.
- The six hand-rolled 4-var pop loops from a0fda6b26 migrate to the
shared strip_local_git_env helper so the guard enforces one pattern.
Verified: full release-control battery green; every touched test file
also green with GIT_DIR/GIT_INDEX_FILE pointed at a canary repo's linked
worktree, canary config and status intact afterward.
Pre-commit runs from a linked git worktree export an absolute GIT_DIR.
The release-control test helpers and the test-patched branch of
git_env() only removed GIT_INDEX_FILE, so their scratch-repo commands
targeted the REAL repository: 'git init' in a tempdir re-initialized it
with core.bare=true (breaking git status/commit for every checkout and
worktree) and the subsequent scratch 'git add' failed the hook.
Scrub GIT_DIR, GIT_WORK_TREE, GIT_INDEX_FILE, and GIT_COMMON_DIR in:
- git_env() of format_staged_go.py, governance_stage_guard.py, and
subsystem_contracts.py (test-patched branch only; production hook
behavior unchanged)
- the scratch-repo git() helpers in format_staged_go_test.py,
governance_stage_guard_test.py, readiness_assertion_guard_test.py,
subsystem_contracts_test.py
Matches the pattern contract_audit_test.py and status_audit_test.py
already used. Verified the full hook test battery passes with
GIT_DIR/GIT_WORK_TREE/GIT_INDEX_FILE pointed at a canary repo, which
stays un-corrupted.
Canonical Governance failed on nearly every push today (6 of the last 8
commits) because the local pre-commit hook and the CI workflow disagreed
about the canonical completion guard in two ways.
Frontend-only commits skipped the guard entirely: the hook gated ALL
governance checks behind governance-path detection as a perf
optimization, but subsystem contracts name canonical frontend files, so
those commits landed locally and failed the same guard in CI. The hook
now always runs the (cheap) completion guard; only the multi-minute Go
test and audit battery stays path-gated.
Contract-neutral bypasses did not travel: PULSE_ALLOW_CONTRACT_NEUTRAL_COMMIT
authorized the commit in the local shell and vanished, so CI re-ran the
guard without it and went red. A new prepare-commit-msg hook records the
reason as a Contract-Neutral trailer in the commit message, and the
workflow now evaluates the guard per commit (each commit's file list
against its own parent), honoring the trailer exactly as the commit-time
hook honored the env var. Per-commit evaluation also stops a compliant
commit from being blamed for range-mates.
The new hook is registered as a worktree-sensitive governance file in
governance_stage_guard.py with a matching unit test assert.
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.
Commit 0a9a29d63 moved deploy-demo-server.yml and update-demo-server.yml
from the static TS_AUTHKEY to the Tailscale OAuth client but left the
release promotion policy pin asserting TS_AUTHKEY, so the Canonical
Governance run failed at the promotion policy unit tests once the
completion guard false positive (fixed in 54a6118d1) stopped masking
the step. The pin now asserts the OAuth client id and secret and pins
the static key retirement.
The guard judged substantive contract updates by diffing HEAD against
the index. In CI nothing is staged, the index equals HEAD, so every
contract file piped in via --files-from-stdin looked unchanged and the
guard blocked compliant pushes. Concretely, run 28944317805 blocked
7645965af even though its deployment-installability.md addition sits
inside the Current State section.
The guard now accepts --diff-base <ref> (requires --files-from-stdin),
resolves it to its merge base with HEAD so the comparison anchor
matches the three-dot changed-file list, and compares base vs HEAD
contract texts in that mode. Pre-commit keeps the index comparison.
The canonical-governance workflow passes the push or PR range base.
The weekly release-dry-run schedule failed at 'Resolve rehearsal
metadata' because GitHub does not apply workflow_dispatch input
defaults to schedule events, so rollback_version arrived empty and
resolve_release_promotion.py rejected the run.
Scheduled runs now pass --derive-rollback-latest-stable, which fills
an empty rollback_version with the latest stable tag preceding the
rehearsal version (currently v6.0.4 for 6.0.5-rc.3). Manual dispatches
keep the explicit rollback_version requirement; the stale prefilled
5.1.29 default is removed so operators state the target themselves.
The deployment-installability contract records the scoped scheduled
exception.
rcourtman