d054c0b8b1
PRD line 70: "Everything runs locally — no cloud APIs, total data privacy." Yesterday's PR #13 (feb638e) violated this by routing customer-facing inference paths to opencode + ollama_cloud + openrouter. Reverting the hot-path routes only; cloud providers stay configured in providers.toml for explicit dev-tool opt-in. Reverted: - modes.toml staffing_inference: kimi-k2.6 → qwen3.5:latest (local Ollama) - modes.toml doc_drift_check: gemini-3-flash-preview → qwen3.5:latest - execution_loop overseer: opencode/claude-opus-4-7 → ollama/qwen3.5:latest Was a paid Anthropic call on every overseer escalation; now local + free. Gateway compiles + restarts clean. Lance smoke 10/10. Live providers list unchanged (kimi/ollama_cloud/opencode/openrouter all still CONFIGURED; they just aren't ROUTED to from the staffing inference path anymore). This stops the API meter on customer requests. Cloud providers remain opt-in via explicit provider= caller hint, which the scrum tool + auditor pipeline + bot/propose use deliberately. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
90 lines
3.8 KiB
TOML
90 lines
3.8 KiB
TOML
# Mode router config — task_class → mode mapping
|
||
#
|
||
# `preferred_mode` is the first choice for a task class; `fallback_modes`
|
||
# get tried in order if the preferred one isn't available (LLM Team can
|
||
# return Unknown mode for some, OR the matrix has stronger signal for a
|
||
# fallback). `default_model` seeds the mode runner's model field if the
|
||
# caller doesn't override.
|
||
#
|
||
# Modes are dispatched against LLM Team UI (localhost:5000/api/run) for
|
||
# now; future Rust-native runners will short-circuit before the proxy.
|
||
# See crates/gateway/src/v1/mode.rs for the dispatch path.
|
||
|
||
[[task_class]]
|
||
name = "scrum_review"
|
||
# 2026-04-26 pass5 variance test (5 reps × 4 conditions, grok-4.1-fast,
|
||
# pathway_memory.rs): composed corpus LOST 5/5 vs isolation (Δ −1.8
|
||
# grounded findings, p=0.031). See docs/MODE_RUNNER_TUNING_PLAN.md.
|
||
# Default is now isolation — bug fingerprints + adversarial framing +
|
||
# file content carries strong models without matrix noise. The
|
||
# `codereview_lakehouse` matrix path remains available via force_mode
|
||
# (auto-downgrades to isolation on strong models — see the
|
||
# is_strong_model gate in crates/gateway/src/v1/mode.rs).
|
||
preferred_mode = "codereview_isolation"
|
||
fallback_modes = ["codereview_lakehouse", "codereview", "consensus", "ladder"]
|
||
default_model = "qwen3-coder:480b"
|
||
# Corpora kept defined so experimental modes (codereview_matrix_only,
|
||
# pass2/pass5 sweeps) and weak-model rescue rungs can still pull them.
|
||
# scrum_findings_v1 is built but EXCLUDED — bake-off showed 24% OOB
|
||
# line citations from cross-file drift, only safe with same-file gating.
|
||
matrix_corpus = ["lakehouse_arch_v1", "lakehouse_symbols_v1"]
|
||
|
||
[[task_class]]
|
||
name = "contract_analysis"
|
||
preferred_mode = "deep_analysis"
|
||
fallback_modes = ["research", "extract"]
|
||
default_model = "kimi-k2:1t"
|
||
matrix_corpus = "chicago_permits_v1"
|
||
|
||
[[task_class]]
|
||
name = "staffing_inference"
|
||
# Staffing-domain native enrichment runner — Pass 4 (2026-04-26).
|
||
# Same composer architecture as codereview_lakehouse but with staffing
|
||
# framing + workers corpus.
|
||
preferred_mode = "staffing_inference_lakehouse"
|
||
fallback_modes = ["ladder", "consensus", "pipeline"]
|
||
# 2026-05-03: REVERTED to local. PRD line 70 — everything runs locally,
|
||
# no cloud APIs on the customer hot path. Cloud models stay available
|
||
# in providers.toml for explicit dev-tool opt-in (scrum, auditor).
|
||
default_model = "qwen3.5:latest"
|
||
matrix_corpus = "workers_500k_v8"
|
||
|
||
[[task_class]]
|
||
name = "fact_extract"
|
||
preferred_mode = "extract"
|
||
fallback_modes = ["distill"]
|
||
default_model = "qwen2.5"
|
||
matrix_corpus = "kb_team_runs_v1"
|
||
|
||
[[task_class]]
|
||
name = "doc_drift_check"
|
||
preferred_mode = "drift"
|
||
fallback_modes = ["validator"]
|
||
# 2026-05-03: REVERTED to local per PRD line 70.
|
||
default_model = "qwen3.5:latest"
|
||
matrix_corpus = "distilled_factual_v20260423095819"
|
||
|
||
[[task_class]]
|
||
name = "pr_audit"
|
||
# Auditor's claim-vs-diff verification mode (2026-04-26 rebuild).
|
||
# Replaces the auditor's hand-rolled inference check with the mode-runner
|
||
# composer: pathway memory (PR-level patterns) + lakehouse_answers_v1
|
||
# corpus (prior accepted reviews + observer escalations) + adversarial
|
||
# JSON-shaped framing. Default model is paid Ollama Cloud kimi-k2:1t for
|
||
# strong claim-grounding; tie-breaker via auditor-side env override.
|
||
preferred_mode = "pr_audit"
|
||
fallback_modes = ["consensus", "ladder"]
|
||
# kimi-k2:1t broken upstream 2026-04-27 (Ollama Cloud 500 ISE, multi-hour
|
||
# sustained outage verified by repeated probes). deepseek-v3.1:671b is
|
||
# the drop-in substitute — proven working end-to-end through pr_audit
|
||
# during Phase 5 distillation acceptance testing.
|
||
default_model = "deepseek-v3.1:671b"
|
||
matrix_corpus = "lakehouse_answers_v1"
|
||
|
||
# Fallback when task_class isn't in the table — useful for ad-hoc calls
|
||
# during development that don't yet have a mapped mode.
|
||
[default]
|
||
preferred_mode = "pipeline"
|
||
fallback_modes = ["consensus", "ladder"]
|
||
default_model = "qwen3.5:latest"
|