sheawinkler/ContextLattice

v3.12.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 15d AI Agents & Assistants

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-framework agent-orchestration ai-infra ai-interface context-engineering context-management

+4 more

go long-horizon-agents long-horizon-intelligence rust

Summary

AI summary

Added a persisted Temporal Claim Graph, deterministic retrieval planning advice, and Proof-Carrying Synthesis v2 with full provenance.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Medium	Adds bounded persisted Temporal Claim Graph with validity intervals and provenance. Adds bounded persisted Temporal Claim Graph with validity intervals and provenance. Source: llm_adapter@2026-07-15 Confidence: high	—
Feature	Medium	Adds deterministic retrieval_plan.v1 advice with evidence obligations and token allocation. Adds deterministic retrieval_plan.v1 advice with evidence obligations and token allocation. Source: llm_adapter@2026-07-15 Confidence: high	—
Feature	Medium	Adds Proof-Carrying Synthesis v2, requiring evidence identity for findings. Adds Proof-Carrying Synthesis v2, requiring evidence identity for findings. Source: llm_adapter@2026-07-15 Confidence: low	—
Feature	Low	Adds CLI commands: contextlattice_claim_write, contextlattice_claim_query, contextlattice_retrieval_plan, contextlattice_synthesis_pack_v2. Adds CLI commands: contextlattice_claim_write, contextlattice_claim_query, contextlattice_retrieval_plan, contextlattice_synthesis_pack_v2. Source: llm_adapter@2026-07-15 Confidence: high	—
Feature	Low	Adds nine Go‑native HTTP/tool/telemetry routes and four bounded contracts. Adds nine Go‑native HTTP/tool/telemetry routes and four bounded contracts. Source: llm_adapter@2026-07-15 Confidence: high	—
Feature	Low	Expands strict native‑ownership, capability, installer, discovery, audit, and public‑core parity surfaces. Expands strict native‑ownership, capability, installer, discovery, audit, and public‑core parity surfaces. Source: llm_adapter@2026-07-15 Confidence: high	—
Feature	Low	Preserves all v1 routes and contracts for gradual adoption. Preserves all v1 routes and contracts for gradual adoption. Source: llm_adapter@2026-07-15 Confidence: high	—
Feature	Low	Adds Proof-Carrying Synthesis v2; findings must carry support, opposition, temporal state, causal context, missing proof, and decomposed confidence; unverified findings are excluded. Adds Proof-Carrying Synthesis v2; findings must carry support, opposition, temporal state, causal context, missing proof, and decomposed confidence; unverified findings are excluded. Source: granite4.1:30b@2026-07-15-audit Confidence: low	—
Feature	Low	Proof‑carrying synthesis of thirty‑two proof claims has median latency 88 211 ns/op. Proof‑carrying synthesis of thirty‑two proof claims has median latency 88 211 ns/op. Source: granite4.1:30b@2026-07-15-audit Confidence: low	—
Performance
Performance	Low	Bounded 1,000‑claim query median latency is 931 454 ns/op. Bounded 1,000‑claim query median latency is 931 454 ns/op. Source: granite4.1:30b@2026-07-15-audit Confidence: low	—
Performance	Low	1,000‑claim allocation pressure reduced from 2 297 993 B/op to 33 432 B/op. 1,000‑claim allocation pressure reduced from 2 297 993 B/op to 33 432 B/op. Source: granite4.1:30b@2026-07-15-audit Confidence: low	—
Performance	Low	1,000‑claim allocations reduced from 6 933 to 7 allocs/op. 1,000‑claim allocations reduced from 6 933 to 7 allocs/op. Source: granite4.1:30b@2026-07-15-audit Confidence: low	—
Performance	Low	Retrieval planner median latency is 10 719 ns/op. Retrieval planner median latency is 10 719 ns/op. Source: granite4.1:30b@2026-07-15-audit Confidence: low	—

Full changelog

ContextLattice v3.12.0 - Proof, Not Vibes

v3.12 gives memory a sense of time and synthesis a burden of proof. An agent can
now ask what is true, what used to be true, what replaced it, what contests it,
and exactly which evidence allows the claim to exist.

What changed

Added a bounded, persisted Temporal Claim Graph with validity intervals,
provenance, verification, contradiction, supersession, causality, branch,
commit, agent, and session identity.
Added deterministic retrieval_plan.v1 advice with task-phase evidence
obligations, source/query plans, token allocation, graph expansion advice,
observed reliability and p95 latency, and marginal-value stop conditions.
Added Proof-Carrying Synthesis v2. Every emitted finding carries support,
opposition, temporal state, causal context, missing proof, and decomposed
confidence. Findings without an evidence identity are excluded and counted.
Added primary CLI commands:
contextlattice_claim_write, contextlattice_claim_query,
contextlattice_retrieval_plan, and contextlattice_synthesis_pack_v2.
Added nine Go-native HTTP/tool/telemetry routes and four bounded contracts.
Expanded strict native-ownership, context-boundary, capability, installer,
discovery, audit, and public-core parity surfaces for the cognition core.
Preserved every v1 route and contract for gradual adoption.

Measured behavior

The public eval ledger records deterministic, model-free holdouts and benchmarks:

Temporal claim persistence/supersession: passed across process-style reload.
Claim, planner, and synthesis contract holdouts: passed on three repeated runs.
Model calls: 0.
External API/network calls: 0.
1,000-claim bounded query median: 931454 ns/op.
1,000-claim allocation pressure: 2297993 -> 33432 B/op.
1,000-claim allocations: 6933 -> 7 allocs/op.
Planner median: 10719 ns/op.
Thirty-two proof claims median: 88211 ns/op.

These are component benchmarks on the release development host, not universal
latency promises. Reproduce them with the commands in
docs/evals/v3.12-cognition-proof-core.json.

Safety boundaries

Retrieval planning is advisor / shadow_only. It cannot silently mutate the
live source policy.
Synthesis is deterministic and reports llm_used=false.
Lexical claim linking does not pretend to be semantic equivalence.
Unverified claims cannot silently raise confidence.
Contradictions remain visible and unresolved; the public core does not invent
a winner.
The active application path remains Go/Rust. No Python service or gateway-owned
subprocess was added.
The claim ledger is bounded and uses the configured ContextLattice data volume.

Try it

contextlattice_retrieval_plan "prove release readiness" --project contextlattice --pretty
contextlattice_claim_query "current release" --project contextlattice --include-superseded --pretty
contextlattice_synthesis_pack_v2 "prove release readiness" --project contextlattice --pretty
contextlattice_context_boundary --pretty
contextlattice_strict_runtime_native_ownership --pretty

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track sheawinkler/ContextLattice

Get notified when new releases ship.

About sheawinkler/ContextLattice

Private-by-default memory and context layer for agents with Go/Rust runtime, staged retrieval across fused data backends, and long-horizon context continuity.