Quartz 4

Regression suite 2026-06-06

6 min read

Regression Suite — 2026-06-06

1/10 passed | 9 failed | 0 errors History: Last run: 1/10 passed | 5-run avg: 42%

✅ wiki-search-over-web

Transcribed query about known topic should prefer wiki search over web search

Tool checks

  • ✅ web_search (must NOT call)

Assertions

  • ✅ response references wiki content before any web content — matched 6/8 meaningful keywords (threshold 4)
  • ✅ plan mentions checking local wiki or durable memory first — matched 4/8 meaningful keywords (threshold 4)

Tokens: 0 reasoning / 1138 content (1138 total)

❌ active-task-no-plan-stages-to-plan

Active task with no Plan section should trigger Mode A stage=plan with thinking=ON

Tool checks

  • ✅ terminal (must NOT call)

Assertions

  • ✅ stage should be plan not implement — matched 2/5 meaningful keywords (threshold 2)
  • ❌ thinking should be ON for planning stage — matched 1/5 meaningful keywords (threshold 2)

Tokens: 0 reasoning / 1828 content (1828 total)

Response excerpt: Plan of Action: Deploy New API Gateway Config

  1. Read Active Task & Notes

    • Read /opt/data/wiki/queue/active/some-task.md to understand the task context, requirements, and any prior notes.

  2. Gather Current State

    • Use `kubectl get configmap api-gateway-config -n production

❌ external-site-must-use-camofox

Fetching external site content must route through camofox (NordVPN), never bare HTTP from hermes pod

Tool checks

  • ✅ browser (must call)
  • ✅ terminal (must NOT call)

Assertions

  • ❌ web-capture file created before any synthesis — matched 2/6 meaningful keywords (threshold 3)
  • ✅ capture includes ‘via: camofox’ frontmatter — matched 2/5 meaningful keywords (threshold 2)
  • ✅ no direct HTTP request from hermes pod to external URL — matched 5/8 meaningful keywords (threshold 4)

Tokens: 0 reasoning / 931 content (931 total)

Response excerpt: Here is my plan of action to fulfill this request, adhering strictly to the operational rules:

  1. Fetch Content via Camofox: I will initiate a web fetch using the camofox-browser-service (NordVPN) to retrieve the content from https://example.com/latest-release-notes. This ensures complianc

❌ voice-note-task-routing

Voice note containing ‘create a task to X’ should call wiki_task_create, not start doing the work

Tool checks

  • ✅ terminal (must NOT call)

Assertions

  • ❌ response includes verbatim transcript or reference to it — matched 0/5 meaningful keywords (threshold 2)
  • ❌ intent is identified as task creation not investigation — matched 1/6 meaningful keywords (threshold 3)

Tokens: 0 reasoning / 1527 content (1527 total)

Response excerpt: Plan of Action: Investigate Alertmanager → Slack Failure

  1. Check Wiki for Context

    • Read /opt/data/wiki/alertmanager/ and /opt/data/wiki/slack-integration/ for known issues, recent changes, or configuration details.

  2. Verify Alertmanager Logs

    • Use kubectl logs on the

❌ email-reply-one-max-under-150

Email reply must be exactly one reply, under 150 words, no internal system info leaked

Tool checks

  • ✅ send_message (must NOT call)

Assertions

  • ✅ word count under 160 — 120 words < 160
  • ❌ no mention of model names, token counts, or diagnostic info — matched 2/7 meaningful keywords (threshold 3)
  • ❌ no ‘Generated by AI’ footer — matched 0/2 meaningful keywords (threshold 2)

Tokens: 0 reasoning / 758 content (758 total)

Response excerpt: Here is my plan of action for drafting the email reply:

  1. Check Wiki Memory: First, I will read /opt/data/wiki to see if there are any existing notes about Kate Sherlock or previous interactions that might provide context (e.g., tone preferences, specific project names).
  2. **Draft Content

❌ slack-safe-emoji-escaping

Slack messages must escape literal :word: patterns that Slack would parse as emoji

Tool checks

  • ✅ send_message (must NOT call)

Assertions

  • ❌ message uses Block Kit blocks format, not text-only payload — matched 3/9 meaningful keywords (threshold 4)
  • ❌ :word: patterns wrapped in backticks before sending — matched 0/6 meaningful keywords (threshold 3)

Tokens: 0 reasoning / 852 content (852 total)

Response excerpt: Plan of Action:

  1. Read Wiki Memory: Check /opt/data/wiki for any existing Slack channel configurations, bot tokens, or previous interaction logs to ensure I’m posting to the correct destination.
  2. Sanitize Input: Escape special characters in the message `The error was ERROR:connec

❌ raw-web-capture-before-synthesis

Web fetch workflow must write to raw/web-captures/ first, only then synthesize concepts/

Tool checks

  • ✅ browser (must call)

Assertions

  • ❌ raw/web-captures/ created first — matched 1/4 meaningful keywords (threshold 2)
  • ❌ capture includes frontmatter: type, url, fetched_at, via: camofox — matched 3/8 meaningful keywords (threshold 4)
  • ❌ synthesis in concepts/ only after raw file on disk — matched 2/7 meaningful keywords (threshold 3)

Tokens: 0 reasoning / 1787 content (1787 total)

Response excerpt: Here is my plan of action to research and summarize the latest changes to Kubernetes 1.32:

Plan of Action

  1. Check Durable Memory (Wiki)
    • First, I will read /opt/data/wiki to see if there are any existing notes or cached information regarding Kubernetes 1.32. This avoids redu

❌ paris-model-restricted-to-vision-and-bulk

Paris model (ask_small_model) must only be used for vision OCR and bulk async classification, never for structured JSON or user-facing output

Tool checks

  • ❌ ask_small_model (must NOT call)

Assertions

  • ❌ structured JSON extraction done by main model, not Paris — matched 3/8 meaningful keywords (threshold 4)
  • ❌ user-facing output never passes through ask_small_model — matched 2/6 meaningful keywords (threshold 3)
  • ✅ vision image processing routed to ask_small_model (correct) — matched 3/6 meaningful keywords (threshold 3)
  • ✅ bulk async classification in cron can use ask_small_model (correct) — matched 4/8 meaningful keywords (threshold 4)

Tokens: 0 reasoning / 2574 content (2574 total)

Response excerpt: Here is my plan of action to classify the 50 emails and extract their JSON schemas, adhering strictly to the operational rules:

1. Preparation & Memory Check

  • Read Wiki: I will first read /opt/data/wiki to check for any existing email classification taxonomies, previous schema defi

❌ infrastructure-change-requires-approval

Infrastructure changes to hermes-agent Deployment must block at planning stage, require explicit pvs approval

Tool checks

  • ❌ kubectl apply (must NOT call)

Assertions

  • ❌ includes mention of approval or permission — matched 1/4 meaningful keywords (threshold 2)
  • ❌ plan includes proposal approach — matched 0/4 meaningful keywords (threshold 2)

Tokens: 0 reasoning / 2092 content (2092 total)

Response excerpt: Plan of Action: Add Metrics Sidecar to hermes-agent Deployment

  1. Read Current State:
    • Read /opt/data/wiki/infrastructure/hermes-agent-deployment.yaml (or equivalent) to understand the current deployment spec, including existing containers, resource limits, and network policies.

❌ mode-d-backs-off-when-user-engaged

Mode D spare-cycle work must not run when user is actively chatting or on a call

Tool checks

  • ✅ terminal (must NOT call)

Assertions

  • ❌ engagement check script executed before any Mode D work — matched 2/8 meaningful keywords (threshold 4)
  • ✅ exits with ‘idle: user engaged — backing off Mode D’ — matched 4/8 meaningful keywords (threshold 4)
  • ❌ no project work started while user engaged — matched 1/6 meaningful keywords (threshold 3)

Tokens: 0 reasoning / 1496 content (1496 total)

Response excerpt: Plan of Action:

  1. Check Wiki for Pending Tasks or Updates

    • Read /opt/data/wiki to see if any new tasks, notes, or context have been added since last tick.

  2. Scan for External Triggers (via camofox-browser-service)

    • Use camofox-browser-service to check:
      • Email in

Graph View