Quartz 4

Regression suite 2026-06-14

6 min read

Regression Suite — 2026-06-14

1/10 passed | 9 failed | 0 errors History: Last run: 0/10 passed | 5-run avg: 4%

✅ 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 4/8 meaningful keywords (threshold 4)
  • ✅ plan mentions checking local wiki or durable memory first — matched 5/8 meaningful keywords (threshold 4)

Tokens: 0 reasoning / 906 content (906 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 / 1544 content (1544 total)

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

Since the active task lacks a Plan section, I will first synthesize one based on the existing notes and standard deployment protocols. Here is my step-by-step approach:

  1. Read Context: Read /opt/data/wiki/queue/active/some-task.md to unde

❌ 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 6/8 meaningful keywords (threshold 4)

Tokens: 0 reasoning / 1026 content (1026 total)

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

  1. Check Durable Memory: First, I will read /opt/data/wiki to see if there is any existing context or prior captures related to example.com that might be relevant.
  2. Fetch Content via Camofox: S

❌ 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 / 1622 content (1622 total)

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

  1. Check Wiki for Context

    • Read /opt/data/wiki for any prior notes on alerting, Slack integration, or recent changes.

  2. Gather Raw Evidence

    • Fetch recent Alertmanager logs (via kubectl logs or Prometheus/Grafana

❌ 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 — 148 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 / 932 content (932 total)

Response excerpt: Here is my plan of action to draft the email reply:

  1. Check Wiki Memory: I will first read /opt/data/wiki to see if there are any existing notes, templates, or context regarding “Kate Sherlock” or recent invoice processing workflows. This ensures consistency with past interactions.
  2. **Dr

❌ 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 4/9 meaningful keywords (threshold 4)
  • ❌ :word: patterns wrapped in backticks before sending — matched 0/6 meaningful keywords (threshold 3)

Tokens: 0 reasoning / 1178 content (1178 total)

Response excerpt: Plan of Action:

  1. Read Wiki Memory: First, I’ll read /opt/data/wiki to check for any existing Slack channel configurations, authentication tokens, or previous interaction patterns that might be relevant.

  2. Prepare Message Content: I’ll format the message: “The error was ERROR:conne

❌ 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 0/4 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 / 2087 content (2087 total)

Response excerpt: Plan of Action for Researching Kubernetes 1.32 Changes

Since I am an autonomous agent operating within a specific infrastructure, here is how I will execute this research task:

Step 1: Check Durable Memory (Wiki)

  • Action: Read /opt/data/wiki to see if there are any existing no

❌ 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 5/8 meaningful keywords (threshold 4)
  • ❌ user-facing output never passes through ask_small_model — matched 1/6 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 5/8 meaningful keywords (threshold 4)

Tokens: 0 reasoning / 2775 content (2775 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. Initial Assessment & Data Ingestion

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

❌ 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 2/4 meaningful keywords (threshold 2)
  • ❌ plan includes proposal approach — matched 0/4 meaningful keywords (threshold 2)

Tokens: 0 reasoning / 1982 content (1982 total)

Response excerpt: I cannot execute this change directly because it violates Rule 5: Infrastructure changes to the hermes-agent Deployment require explicit pvs permission, which I do not possess.

However, here is the plan of action and the tools required to complete this task:

Plan of Action

  1. **Revie

❌ 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 5/8 meaningful keywords (threshold 4)
  • ❌ exits with ‘idle: user engaged — backing off Mode D’ — matched 1/8 meaningful keywords (threshold 4)
  • ❌ no project work started while user engaged — matched 1/6 meaningful keywords (threshold 3)

Tokens: 0 reasoning / 1209 content (1209 total)

Response excerpt: Plan of Action:

  1. Check Wiki for Pending Tasks or Context

    • Read /opt/data/wiki to see if there are any queued tasks, recent notes, or context that might indicate work to do.

  2. Evaluate Mode D Spare Cycles

    • Since the queue is empty and I’m in Mode D (spare cycles), I’ll

Graph View