6d713aeeb9
Some checks failed
PR Checklist / pr-checklist (pull_request) Failing after 1m18s
Golden state: Kimi K2.5 primary → Gemini via OpenRouter → local Ollama. Anthropic is gone from every active config, fallback chain, and loop script. Wizard configs (3): - allegro, bezalel, ezra: removed anthropic from fallback_providers, replaced with gemini + ollama. Removed anthropic provider section. Playbooks (7): - All playbooks now use kimi-k2.5 as preferred, google/gemini-2.5-pro as fallback. No claude model references remain. Fleet scripts (8): - claude-loop.sh: deprecated (exit 0, original preserved as reference) - claudemax-watchdog.sh: deprecated (exit 0) - agent-loop.sh: removed claude dispatch case - start-loops.sh: removed claude-locks, claude-loop from proc list - timmy-orchestrator.sh: removed claude worker monitoring - fleet-status.sh: zeroed claude loop counter - model-health-check.sh: replaced check_anthropic_model with check_kimi_model - ops-gitea.sh, ops-helpers.sh, ops-panel.sh: removed claude from agent lists Infrastructure (5): - wizard_bootstrap.py: removed anthropic pip package and API key checks - WIZARD_ENVIRONMENT_CONTRACT.md: replaced ANTHROPIC keys with KIMI - DEPLOY.md: replaced ANTHROPIC_API_KEY with KIMI_API_KEY - fallback-portfolios.yaml: replaced anthropic provider with kimi-coding - fleet-vocabulary.md: updated Ezra and Claude entries to Kimi K2.5 Docs (2): - sonnet-workforce.md: deprecated with notice - GoldenRockachopa-checkin.md: updated model references Preserved (not touched): - training/ data (changing would corrupt training set) - evaluations/ (historical benchmarks) - RELEASE_*.md (changelogs) - metrics_helpers.py (historical cost calculation) - hermes-sovereign/githooks/pre-commit.py (secret detection - still useful) - security/secret-scan.yml (key detection - still useful) - architecture_linter.py (warns about anthropic usage - desired behavior) - test_sovereignty_enforcement.py (tests anthropic is blocked - correct) - son-of-timmy.md philosophical references (Claude as one of many backends) Refs: Sovereignty directive, zero-cloud vision
285 lines
7.3 KiB
YAML
285 lines
7.3 KiB
YAML
schema_version: 1
|
|
status: proposed
|
|
runtime_wiring: false
|
|
owner: timmy-config
|
|
|
|
ownership:
|
|
owns:
|
|
- routing doctrine for task classes
|
|
- sidecar-readable per-agent fallback portfolios
|
|
- degraded-mode capability floors
|
|
does_not_own:
|
|
- live queue state outside Gitea truth
|
|
- launchd or loop process state
|
|
- ad hoc worktree history
|
|
|
|
policy:
|
|
require_four_slots_for_critical_agents: true
|
|
terminal_fallback_must_be_usable: true
|
|
forbid_synchronized_fleet_degradation: true
|
|
forbid_human_token_fallbacks: true
|
|
anti_correlation_rule: no two critical agents may share the same primary+fallback1 pair
|
|
|
|
sensitive_control_surfaces:
|
|
- SOUL.md
|
|
- config.yaml
|
|
- deploy.sh
|
|
- tasks.py
|
|
- playbooks/
|
|
- cron/
|
|
- memories/
|
|
- skins/
|
|
- training/
|
|
|
|
role_classes:
|
|
judgment:
|
|
current_surfaces:
|
|
- playbooks/issue-triager.yaml
|
|
- playbooks/pr-reviewer.yaml
|
|
- playbooks/verified-logic.yaml
|
|
task_classes:
|
|
- issue-triage
|
|
- queue-routing
|
|
- pr-review
|
|
- proof-check
|
|
- governance-review
|
|
degraded_mode:
|
|
fallback2:
|
|
allowed:
|
|
- classify backlog
|
|
- summarize risk
|
|
- produce draft routing plans
|
|
- leave bounded labels or comments with evidence
|
|
denied:
|
|
- merge pull requests
|
|
- close or rewrite governing issues or PRs
|
|
- mutate sensitive control surfaces
|
|
- bulk-reassign the fleet
|
|
- silently change routing policy
|
|
terminal:
|
|
lane: report-and-route
|
|
allowed:
|
|
- classify backlog
|
|
- summarize risk
|
|
- produce draft routing artifacts
|
|
denied:
|
|
- merge pull requests
|
|
- bulk-reassign the fleet
|
|
- mutate sensitive control surfaces
|
|
|
|
builder:
|
|
current_surfaces:
|
|
- playbooks/bug-fixer.yaml
|
|
- playbooks/test-writer.yaml
|
|
- playbooks/refactor-specialist.yaml
|
|
task_classes:
|
|
- bug-fix
|
|
- test-writing
|
|
- refactor
|
|
- bounded-docs-change
|
|
degraded_mode:
|
|
fallback2:
|
|
allowed:
|
|
- reversible single-issue changes
|
|
- narrow docs fixes
|
|
- test scaffolds and reproducers
|
|
denied:
|
|
- cross-repo changes
|
|
- sensitive control-surface edits
|
|
- merge or release actions
|
|
terminal:
|
|
lane: narrow-patch
|
|
allowed:
|
|
- single-issue small patch
|
|
- reproducer test
|
|
- docs-only repair
|
|
denied:
|
|
- sensitive control-surface edits
|
|
- multi-file architecture work
|
|
- irreversible actions
|
|
|
|
wolf_bulk:
|
|
current_surfaces:
|
|
- docs/automation-inventory.md
|
|
- FALSEWORK.md
|
|
task_classes:
|
|
- docs-inventory
|
|
- log-summarization
|
|
- queue-hygiene
|
|
- repetitive-small-diff
|
|
- research-sweep
|
|
degraded_mode:
|
|
fallback2:
|
|
allowed:
|
|
- gather evidence
|
|
- refresh inventories
|
|
- summarize logs
|
|
- propose labels or routes
|
|
denied:
|
|
- multi-repo branch fanout
|
|
- mass agent assignment
|
|
- sensitive control-surface edits
|
|
- irreversible queue mutation
|
|
terminal:
|
|
lane: gather-and-summarize
|
|
allowed:
|
|
- inventory refresh
|
|
- evidence bundles
|
|
- summaries
|
|
denied:
|
|
- multi-repo branch fanout
|
|
- mass agent assignment
|
|
- sensitive control-surface edits
|
|
|
|
routing:
|
|
issue-triage: judgment
|
|
queue-routing: judgment
|
|
pr-review: judgment
|
|
proof-check: judgment
|
|
governance-review: judgment
|
|
bug-fix: builder
|
|
test-writing: builder
|
|
refactor: builder
|
|
bounded-docs-change: builder
|
|
docs-inventory: wolf_bulk
|
|
log-summarization: wolf_bulk
|
|
queue-hygiene: wolf_bulk
|
|
repetitive-small-diff: wolf_bulk
|
|
research-sweep: wolf_bulk
|
|
|
|
promotion_rules:
|
|
- If a wolf/bulk task touches a sensitive control surface, promote it to judgment.
|
|
- If a builder task expands beyond 5 files, architecture review, or multi-repo coordination, promote it to judgment.
|
|
- If a terminal lane cannot produce a usable artifact, the portfolio is invalid and must be redesigned before wiring.
|
|
|
|
agents:
|
|
triage-coordinator:
|
|
role_class: judgment
|
|
critical: true
|
|
current_playbooks:
|
|
- playbooks/issue-triager.yaml
|
|
portfolio:
|
|
primary:
|
|
provider: kimi-coding
|
|
model: kimi-k2.5
|
|
lane: full-judgment
|
|
fallback1:
|
|
provider: openai-codex
|
|
model: codex
|
|
lane: high-judgment
|
|
fallback2:
|
|
provider: gemini
|
|
model: gemini-2.5-pro
|
|
lane: bounded-judgment
|
|
terminal:
|
|
provider: ollama
|
|
model: hermes3:latest
|
|
lane: report-and-route
|
|
local_capable: true
|
|
usable_output:
|
|
- backlog classification
|
|
- routing draft
|
|
- risk summary
|
|
|
|
pr-reviewer:
|
|
role_class: judgment
|
|
critical: true
|
|
current_playbooks:
|
|
- playbooks/pr-reviewer.yaml
|
|
portfolio:
|
|
primary:
|
|
provider: kimi-coding
|
|
model: kimi-k2.5
|
|
lane: full-review
|
|
fallback1:
|
|
provider: gemini
|
|
model: gemini-2.5-pro
|
|
lane: high-review
|
|
fallback2:
|
|
provider: grok
|
|
model: grok-3-mini-fast
|
|
lane: comment-only-review
|
|
terminal:
|
|
provider: openrouter
|
|
model: openai/gpt-4.1-mini
|
|
lane: low-stakes-diff-summary
|
|
local_capable: false
|
|
usable_output:
|
|
- diff risk summary
|
|
- explicit uncertainty notes
|
|
- merge-block recommendation
|
|
|
|
builder-main:
|
|
role_class: builder
|
|
critical: true
|
|
current_playbooks:
|
|
- playbooks/bug-fixer.yaml
|
|
- playbooks/test-writer.yaml
|
|
- playbooks/refactor-specialist.yaml
|
|
portfolio:
|
|
primary:
|
|
provider: openai-codex
|
|
model: codex
|
|
lane: full-builder
|
|
fallback1:
|
|
provider: kimi-coding
|
|
model: kimi-k2.5
|
|
lane: bounded-builder
|
|
fallback2:
|
|
provider: groq
|
|
model: llama-3.3-70b-versatile
|
|
lane: small-patch-builder
|
|
terminal:
|
|
provider: custom_provider
|
|
provider_name: Local llama.cpp
|
|
model: hermes4:14b
|
|
lane: narrow-patch
|
|
local_capable: true
|
|
usable_output:
|
|
- small patch
|
|
- reproducer test
|
|
- docs repair
|
|
|
|
wolf-sweeper:
|
|
role_class: wolf_bulk
|
|
critical: true
|
|
current_world_state:
|
|
- docs/automation-inventory.md
|
|
portfolio:
|
|
primary:
|
|
provider: gemini
|
|
model: gemini-2.5-flash
|
|
lane: fast-bulk
|
|
fallback1:
|
|
provider: groq
|
|
model: llama-3.3-70b-versatile
|
|
lane: fast-bulk-backup
|
|
fallback2:
|
|
provider: openrouter
|
|
model: openai/gpt-4.1-mini
|
|
lane: bounded-bulk-summary
|
|
terminal:
|
|
provider: ollama
|
|
model: hermes3:latest
|
|
lane: gather-and-summarize
|
|
local_capable: true
|
|
usable_output:
|
|
- inventory refresh
|
|
- evidence bundle
|
|
- summary comment
|
|
|
|
cross_checks:
|
|
unique_primary_fallback1_pairs:
|
|
triage-coordinator:
|
|
- kimi-coding/kimi-k2.5
|
|
- openai-codex/codex
|
|
pr-reviewer:
|
|
- kimi-coding/kimi-k2.5
|
|
- gemini/gemini-2.5-pro
|
|
builder-main:
|
|
- openai-codex/codex
|
|
- kimi-coding/kimi-k2.5
|
|
wolf-sweeper:
|
|
- gemini/gemini-2.5-flash
|
|
- groq/llama-3.3-70b-versatile
|