ac01fffd9a
Architectural snapshot of the lakehouse codebase at the point where the
full matrix-driven agent loop with Mem0 versioning + deletion was
validated end-to-end.
WHAT THIS REPO IS
A clean single-commit snapshot of the lakehouse code. Heavy test data
(.parquet datasets, vector indexes) excluded — see REPLICATION.md for
regen path. Full lakehouse history at git.agentview.dev/profit/lakehouse.
WHAT WAS PROVEN
- Vector retrieval across multi-corpora matrix (chicago_permits + entity
briefs + sec_tickers + distilled procedural + llm_team runs)
- Observer hand-review (cloud + heuristic fallback) gating each candidate
- Local-model agent loop (qwen3.5:latest) with tool use + scratchpad
- Playbook seal on success → next-iter retrieval surfaces it as preamble
- Mem0 versioning + deletion in pathway_memory:
* UPSERT: ADD on new workflow, UPDATE bumps replay_count on identical
* REVISE: chains versions, parent.superseded_at + superseded_by stamped
* RETIRE: marks specific trace retired with reason, excluded from retrieval
* HISTORY: walks chain root→tip, cycle-safe
KEY DIRECTORIES
- crates/vectord/src/pathway_memory.rs — Mem0 ops live here
- crates/vectord/src/playbook_memory.rs — original Mem0 reference
- tests/agent_test/ — local-model agent harness + PRD + session archives
- scripts/dump_raw_corpus.sh — MinIO bucket dump (raw test corpus)
- scripts/vectorize_raw_corpus.ts — corpus → vector indexes
- scripts/analyze_chicago_contracts.ts — real inference pipeline
- scripts/seal_agent_playbook.ts — Mem0 upsert from agent traces
Replication: see REPLICATION.md for Debian 13 clean install + cloud-only
adaptation (no local Ollama).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
63 lines
2.5 KiB
TypeScript
63 lines
2.5 KiB
TypeScript
// ═══════════════════════════════════════════════════════════════════
|
|
// YOU WRITE THIS FILE. Policy decides what blocks vs what's a comment.
|
|
// Defaults are opinionated on the "stop clicking past placeholder"
|
|
// side — easier to loosen than to tighten when you're watching the
|
|
// auditor behave in live PRs.
|
|
// ═══════════════════════════════════════════════════════════════════
|
|
|
|
import type { Finding, Verdict } from "./types.ts";
|
|
|
|
/// Translate the four-check output into a single verdict. This is the
|
|
/// single pane of glass the auditor operates on — tune thresholds here.
|
|
export function assembleVerdict(
|
|
findings: Finding[],
|
|
metrics: Record<string, number>,
|
|
pr_number: number,
|
|
head_sha: string,
|
|
): Verdict {
|
|
const blocking = findings.filter(f => f.severity === "block");
|
|
const warning = findings.filter(f => f.severity === "warn");
|
|
|
|
let overall: Verdict["overall"];
|
|
let one_liner: string;
|
|
|
|
if (blocking.length > 0) {
|
|
overall = "block";
|
|
one_liner = `${blocking.length} blocking issue${blocking.length > 1 ? "s" : ""}: ${blocking[0].summary}`;
|
|
} else if (warning.length >= 3) {
|
|
// Three or more warnings is a block — death by a thousand cuts.
|
|
overall = "request_changes";
|
|
one_liner = `${warning.length} warnings — see review`;
|
|
} else if (warning.length > 0) {
|
|
overall = "request_changes";
|
|
one_liner = warning[0].summary;
|
|
} else {
|
|
overall = "approve";
|
|
one_liner = `all checks passed (${findings.length} findings, all info)`;
|
|
}
|
|
|
|
return {
|
|
pr_number,
|
|
head_sha,
|
|
audited_at: new Date().toISOString(),
|
|
overall,
|
|
findings,
|
|
metrics,
|
|
one_liner,
|
|
};
|
|
}
|
|
|
|
/// Which strength-of-claim warrants which severity when evidence is
|
|
/// weak? A "Phase X shipped" claim with zero integration tests is a
|
|
/// blocker. A "should work" claim with no test is a warn.
|
|
export function severityFromClaimEvidence(
|
|
claim_strength: "weak" | "moderate" | "strong",
|
|
evidence_grade: "none" | "partial" | "full",
|
|
): "info" | "warn" | "block" {
|
|
if (evidence_grade === "full") return "info";
|
|
if (claim_strength === "strong" && evidence_grade === "none") return "block";
|
|
if (claim_strength === "strong" && evidence_grade === "partial") return "warn";
|
|
if (claim_strength === "moderate" && evidence_grade === "none") return "warn";
|
|
return "info";
|
|
}
|