mirror of
https://github.com/rcourtman/Pulse.git
synced 2026-10-21 05:30:35 +00:00
a3f8b18bfb
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.
|
||
|---|---|---|
| .. | ||
| dev | ||
| eval | ||
| installtests | ||
| intelligence_lab | ||
| lib | ||
| lint-fixer | ||
| release_control | ||
| systemd | ||
| tests | ||
| .go-version | ||
| audit-private-boundary.sh | ||
| backfill-release-assets.sh | ||
| build-release.sh | ||
| bundle.manifest | ||
| bundle.sh | ||
| check-bench-regression.sh | ||
| check-workflow-dispatch-inputs.py | ||
| clean-mock-alerts.sh | ||
| cleanup.sh | ||
| cloud-backup.sh | ||
| com.pulse.hot-dev.plist.template | ||
| conformance-smoke.sh | ||
| demo_public_browser_smoke.cjs | ||
| dev-check.sh | ||
| dev-deploy-agent.sh | ||
| dev-launchd-setup.sh | ||
| dev-launchd-wrapper.sh | ||
| docker-build.sh | ||
| ensure_test_assets.sh | ||
| exclusive-lock.mjs | ||
| generate-pulse-intelligence-docs.go | ||
| generate-release-notes.sh | ||
| generate-self-hosted-feature-catalog.go | ||
| generate-types.go | ||
| hot-dev-bg.sh | ||
| hot-dev.sh | ||
| install-container-agent.sh | ||
| install-docker.sh | ||
| install-go-toolchain.sh | ||
| install-mcp.ps1 | ||
| install-mcp.sh | ||
| install.ps1 | ||
| install.sh | ||
| package-helm-chart.sh | ||
| patrol_e2e_matrix.sh | ||
| pulse-auto-update.sh | ||
| release_asset_common.sh | ||
| release_candidate_manifest.py | ||
| release_ldflags.sh | ||
| release_update_key.go | ||
| remerge-parallel.sh | ||
| render_installers.go | ||
| repo-boundary-paid-surface.allowlist | ||
| run_cloud_public_signup_smoke.sh | ||
| run_demo_public_browser_smoke.sh | ||
| run_hosted_staging_smoke.sh | ||
| session-handoff.sh | ||
| standalone.manifest | ||
| sync-production-config.sh | ||
| sync_chart_release_metadata.py | ||
| telemetry_adoption_report.py | ||
| test-vm-disk.sh | ||
| toggle-mock.sh | ||
| trigger-release-dry-run.sh | ||
| trigger-release.sh | ||
| trigger-stable-patch.sh | ||
| uninstall-sensor-proxy.sh | ||
| validate-published-release.sh | ||
| validate-release.sh | ||