86f63a083d
Some checks failed
lakehouse/auditor 1 blocking issue: todo!() macro call in tests/real-world/scrum_master_pipeline.ts
J's framing (2026-04-26): "Modes are how you ask ONCE and get BETTER
information — they mold the data, hyperfocus the prompt on this
codebase's needs, so the model gets it right the first time without
the cascading retry ladder."
Built the first concrete native enrichment runner (codereview_lakehouse)
that composes every context primitive the gateway exposes:
1. Focus file content (read from disk OR caller-supplied)
2. Pathway memory bug_fingerprints for this file area (ADR-021
preamble — "📚 BUGS PREVIOUSLY FOUND IN THIS FILE AREA")
3. Matrix corpus search via the task_class's matrix_corpus
4. Relevance filter (observer /relevance) drops adjacency pollution
5. Assembles ONE precise prompt with system framing
6. Single call to /v1/chat with the recommended model
POST /v1/mode/execute dispatches. Native mode → runs the composer.
Non-native mode → 501 NOT_IMPLEMENTED with hint (proxy to LLM Team
/api/run is queued).
Provider hint logic auto-routes by model name shape:
- vendor/model[:tag] → openrouter
- kimi-*/qwen3-coder*/deepseek-v*/mistral-large* → ollama_cloud
- everything else → local ollama
Live test against crates/queryd/src/delta.rs (10593 bytes, 10
historical bug fingerprints, 2 matrix chunks dropped by relevance):
- enriched_chars: 12876
- response_chars: 16346 (14 findings with confidence percentages)
- Model literally cited the pathway memory preamble in finding #7
- One call to free-tier gpt-oss:120b produced what previously
required the 9-rung escalation ladder
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
59 lines
2.0 KiB
TOML
59 lines
2.0 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"
|
|
# `codereview_lakehouse` is the codebase-specific enrichment runner —
|
|
# bundles defined/imported symbols, pathway-memory bug fingerprints,
|
|
# and relevance-filtered matrix chunks into ONE precise prompt so the
|
|
# model gets it right the first call. The generic `codereview` mode
|
|
# from LLM Team is still the network fallback if execute fails.
|
|
preferred_mode = "codereview_lakehouse"
|
|
fallback_modes = ["codereview", "consensus", "ladder"]
|
|
default_model = "qwen3-coder:480b"
|
|
matrix_corpus = "distilled_procedural_v20260423102847"
|
|
|
|
[[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"
|
|
preferred_mode = "ladder"
|
|
fallback_modes = ["consensus", "pipeline"]
|
|
default_model = "gpt-oss:120b"
|
|
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"]
|
|
default_model = "gpt-oss:120b"
|
|
matrix_corpus = "distilled_factual_v20260423095819"
|
|
|
|
# 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"
|