feat(phase5): hierarchical abstraction engine (v3.11)#164
Open
salishforge wants to merge 1 commit into
Open
Conversation
Feature 4 of the Phase 5 split (umbrella #129): Sleep Phase 5.11 distills cross-cutting principles from accumulated meta-reflections into a queryable abstractions store. - abstractions table (migration-v3.11.sql + canonical schema): level CHECK (principle|strategy|mental_model), stored md5 content_hash with UNIQUE (agent_id, level, namespace, content_hash) — the umbrella's ON CONFLICT DO NOTHING had no conflict target and would have duplicated every principle every cycle. RLS + grants. - Phase 5.11: gated on LLM presence, token budget, and >= 3 meta-reflections; prompt carries the codebase-standard injection guard, wraps reflection content via wrapUserContent, and states the schema's own limits (max 10, under 2000 chars, empty-array escape) so one overlong item does not sink the batch silently. Re-derivation is corroboration: ON CONFLICT keeps GREATEST confidence and revives a deactivated principle only when the fresh derivation is confident (>= 0.5); the conditional WHERE keeps change counts honest. Age-based deactivation of stale sub-0.2 principles. Not skip-gated (input accumulates independently). Cancellation checkpoint before the LLM call so canceled dream runs stop paying. runPhase now records real per-phase token spend in sleep_phase_analytics; count surfaces as SleepCycleResult.principles_extracted. - getAbstractions()/getPrinciples(), GET /principles + /abstractions routes, memforge_principles + memforge_mental_models MCP tools wired to real client methods (honest description: only 'principle' is auto-extracted today), TS + Python SDKs incl. resilient wrappers, tool-definitions, OpenAPI with shared Abstraction component. - tests/abstractions.test.ts: 39 tests — read paths, extraction incl. dedup/revival/confidence-raise/skip-gate immunity/token attribution/ budget + window gates/malformed + schema-invalid + missing-key LLM output, deactivation age and scope boundaries, ordering tiebreak, HTTP status paths, migration shape + RLS. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011xCqQo49d3CEbn6oEvb3Ru
This was referenced Jul 26, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Feature 4 of the Phase 5 split from umbrella #129. Stacked on #163 (causal graph), which stacks on #160.
abstractionstable with a storedmd5(content)hash andUNIQUE (agent_id, level, namespace, content_hash)— the umbrella'sON CONFLICT DO NOTHINGhad no conflict target, so every cycle would have re-inserted the same principles forever.sleep_phase_analytics(therunPhasewrapper previously hardcoded 0 — fine while all wrapped phases were SQL-only, wrong for the first LLM phase).GET /principles,GET /abstractions,memforge_principles+memforge_mental_modelsMCP tools (real executors; descriptions state honestly that only theprinciplelevel is auto-extracted today), TS + Python SDKs incl. resilient wrappers, OpenAPI with a sharedAbstractioncomponent.Review process
3-stage implementation workflow, then a 20-agent adversarial review: 16 raw findings → 12 confirmed, all fixed. Three verifier agents died on a session limit mid-run; I adjudicated their findings manually — two were real (missing cancellation checkpoint before the new LLM call; frozen-confidence/no-revival upsert semantics) and are fixed, one duplicated an already-confirmed finding.
Test evidence
npm run type-check/npm run linttests/abstractions.test.ts(new)npm run test:causal-graphnpm run test:dream-runsnpm run test:integrationDev-DB migration applied and verified idempotent.
🤖 Generated with Claude Code
https://claude.ai/code/session_011xCqQo49d3CEbn6oEvb3Ru