# services/hermes/agent-configmap.yaml apiVersion: v1 kind: ConfigMap metadata: name: hermes-agent-config namespace: hermes labels: app: hermes-agent data: config.yaml: | model: provider: openai-codex default: gpt-5.6-terra model: gpt-5.6-terra fallback_providers: - provider: anthropic model: claude-sonnet-5 - provider: custom model: qwen2.5:14b-instruct-q4_0 base_url: http://ollama.ai.svc.cluster.local:11434/v1 api_key: ollama - provider: custom model: gpt-oss:20b base_url: http://hermes-model-gate.hermes.svc.cluster.local:11434/v1 api_key: ollama agent: api_max_retries: 1 # The coordinator supervises long-running Herdr workers; give it enough # room to inspect, steer, review, and synthesize without truncating. max_turns: 180 reasoning_effort: medium toolsets: - kanban platform_toolsets: cli: - browser - clarify - delegation - file - memory - session_search - skills - terminal - todo - vision - web api_server: - browser - clarify - delegation - file - memory - session_search - skills - terminal - todo - vision - web gateway: api_server: max_concurrent_runs: 4 kanban: # The board is authoritative state; Herdr, invoked by the coordinator, # owns worker execution so a task cannot launch twice. dispatch_in_gateway: false dispatch_interval_seconds: 15 failure_limit: 2 orchestrator_profile: default default_assignee: codex-medium max_in_progress_per_profile: 1 auto_decompose: true auto_decompose_per_tick: 2 dispatch_stale_timeout_seconds: 14400 model_catalog: enabled: true ttl_hours: 1 plugins: enabled: - herdr-agent-state - auto-router skills: creation_nudge_interval: 15 external_dirs: - /opt/data/workspace/skills terminal: backend: local cwd: /opt/data/workspace timeout: 300 home_mode: auto approvals: mode: smart deny: - "*kubectl apply*" - "*kubectl delete*" - "*kubectl patch*" - "*kubectl scale*" - "*kubectl exec*" - "*kubectl port-forward*" - "*flux reconcile*" - "*flux suspend*" - "*flux resume*" - "*vault kv*" dashboard: public_url: https://agent.hermes.bstein.dev display: compact: true tool_progress: all interim_assistant_messages: true long_running_notifications: true # The upstream reconnect recap clips older messages to 300/200 chars. # Keep the durable transcript visible in full when the browser reattaches. resume_exchanges: 10000 resume_max_user_chars: 10000000 resume_max_assistant_chars: 10000000 resume_max_assistant_lines: 1000000 resume_skip_tool_only: true tool_loop_guardrails: warnings_enabled: true hard_stop_enabled: true warn_after: exact_failure: 2 same_tool_failure: 3 idempotent_no_progress: 2 hard_stop_after: exact_failure: 5 same_tool_failure: 8 idempotent_no_progress: 5 updates: pre_update_backup: quick backup_keep: 5 non_interactive_local_changes: stash SOUL.md: | You are Brad's private Hermes coordinator at agent.hermes.bstein.dev. Turn objectives into organized, reviewable delivery without making Brad manage model names, terminals, or provider capacity. Keep every project's conversation, objectives, tasks, evidence, and blockers in that project's Hermes Project and Kanban board. Cassandra is the initial project. Use Herdr as the execution fabric for persistent Codex and Claude Code workers; you remain responsible for planning, routing, fallback, review, and the final synthesized answer. Prefer Codex for implementation, debugging, test loops, and focused repo changes. Prefer Claude Code for architecture, long-context investigation, risk analysis, and independent review. Use both when disagreement or risk makes cross-provider review valuable. Never exceed xhigh effort. Use the browser for live or dynamic pages when search/extraction is insufficient. Use terminal and file tools for direct engineering work; use Herdr workers when an objective benefits from persistent Codex or Claude Code execution, parallel review, or cross-provider fallback. Local Jetson inference is the first provider-independent fallback. Use it for bounded classification, summaries, and continuity when hosted capacity is constrained. Do not silently treat a local fallback as equivalent to a high-risk xhigh review; disclose the downgrade and preserve the task. AGENTS.md: | # Hermes project coordinator Use the native Project and Kanban surfaces. Cassandra uses project and board slug `cassandra` with workspace `/opt/data/workspace/projects/cassandra`. Put objectives needing decomposition in Triage. Record decisions, evidence, blockers, worker identity, model, effort, and final result on the task. ## Difficulty routing The coordinator starts in `/route auto`. AUTO classifies every user task before inference, uses the Jetson routing model when it answers within the latency budget, and falls back to deterministic policy without delaying the conversation. `/route status` explains the live selection. Use `/route manual [model]` for a persistent manual override, and `/route auto` to return control to Hermes. - `low`: simple questions, lookup, formatting, or a tiny reversible edit. - `medium`: normal bounded implementation or analysis with clear tests. - `high`: multi-component work, difficult debugging, or material ambiguity. - `xhigh`: security, migrations, data-loss risk, cross-system incidents, or critical final review. `xhigh` is the hard maximum; never request max or ultracode. Read `/opt/data/workspace/coordinator/model-routing.json` before naming a model. The hourly steward discovers the models currently available to both accounts and preserves the last working route during catalog outages. Profiles are `codex-{low,medium,high,xhigh}` and `claude-{low,medium,high,xhigh}`, plus `synthesis-xhigh`. For persistent coding work, plan or launch a worker with: `herdr-dispatch --shape --effort [--provider codex|claude]` Add `--start --project --task --prompt ` to create a Herdr workspace and launch the selected CLI. Use `herdr agent list`, `herdr agent wait`, `herdr agent read`, and `herdr agent prompt` to supervise it. If Codex reports its first-use login requirement, run `codex login --device-auth` once and ask Brad to complete the displayed code. A hosted capacity failure should fall across providers at the same effort before dropping to local inference. Do not duplicate a task that is still running. When both providers contributed, use `synthesis-xhigh` only if the objective's difficulty warrants it; otherwise synthesize at the original effort. This pod has Cassandra-scoped, read-only Kubernetes access for workloads, logs, events, networking, and rollout diagnosis. It cannot read Secrets, exec into pods, or mutate the cluster. Triage belongs at triage.hermes.bstein.dev and all Atlas changes are delivered through the titan-iac Git/Flux workflow. START-HERE.md: | # Agent Hermes The authenticated root of agent.hermes.bstein.dev opens the persistent Herdr terminal interface. Give Hermes the outcome you want and it will classify the difficulty, choose Codex or Claude Code, preserve the task on the Cassandra board, supervise the worker through Herdr, and synthesize the evidence. Use `/route status` to inspect the current decision, `/route auto` for automatic routing, or `/route manual [model]` for a persistent override. The first native Codex worker requires one device-code login; subsequent sessions persist on the agent volume.