Skip to content

sheawinkler/ContextLattice

v3.11.0 Feature

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

✓ 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

Updates What changed, Safety boundaries, and MRR across a mixed release.

Changes in this release

Feature Low

Adds deterministic `synthesis_pack.v1` responses via new endpoints.

Adds deterministic `synthesis_pack.v1` responses via new endpoints.

Source: llm_adapter@2026-07-15

Confidence: high

Feature Low

Adds bounded async inbox with deduplication and acknowledgement state.

Adds bounded async inbox with deduplication and acknowledgement state.

Source: llm_adapter@2026-07-15

Confidence: high

Feature Low

Adds idempotent context‑pack outcome capture from task‑worker completion paths.

Adds idempotent context‑pack outcome capture from task‑worker completion paths.

Source: llm_adapter@2026-07-15

Confidence: high

Feature Low

Separates observed outcomes from calibration‑eligible outcomes for clearer monitoring.

Separates observed outcomes from calibration‑eligible outcomes for clearer monitoring.

Source: llm_adapter@2026-07-15

Confidence: high

Feature Low

Adds public‑core capability manifest covering 14 contracts and surfaces.

Adds public‑core capability manifest covering 14 contracts and surfaces.

Source: llm_adapter@2026-07-15

Confidence: high

Feature Low

Adds saved graph/recall evaluation artifacts with baseline, intervention, holdout metrics.

Adds saved graph/recall evaluation artifacts with baseline, intervention, holdout metrics.

Source: llm_adapter@2026-07-15

Confidence: high

Feature Low

Preserves ranked evidence, prompt sections, and compiler metadata when context collapses to sparse boundary.

Preserves ranked evidence, prompt sections, and compiler metadata when context collapses to sparse boundary.

Source: granite4.1:30b@2026-07-15-audit

Confidence: low

Dependency Low

Upgrades `golang.org/x/crypto` to v0.52.0 with compatible `x/sync` and `x/text` upgrades.

Upgrades `golang.org/x/crypto` to v0.52.0 with compatible `x/sync` and `x/text` upgrades.

Source: llm_adapter@2026-07-15

Confidence: high

Full changelog

ContextLattice v3.11.0 - Cognition Core

v3.11 turns memory from stored material into a bounded decision surface. Agents can ask for a Synthesis Pack, receive the evidence that matters most, keep slow retrieval warming in the background, and close the loop with observed outcomes instead of guesses.

What changed

  • Added deterministic synthesis_pack.v1 responses through contextlattice_synthesis_pack, POST /memory/synthesis-pack, and POST /tools/synthesis_pack.
  • Preserved ranked evidence, prompt sections, and compiler metadata even when context must collapse to the sparse boundary.
  • Added a bounded async inbox with dedupe and acknowledgement state. Pending or running continuations are warming; only terminal failures are degraded.
  • Added idempotent context-pack outcome capture from task-worker completion paths.
  • Separated all observed outcomes from calibration-eligible outcomes so infrastructure blocks remain visible without poisoning retrieval-quality rates.
  • Added a public-core capability manifest covering 14 contracts and surfaces shared by every ContextLattice distribution.
  • Added saved graph/recall eval artifacts with explicit baseline, intervention, holdout, latency, cost, failures, and reproduction commands.
  • Patched golang.org/x/crypto to v0.52.0, with compatible x/sync and x/text upgrades.
  • Brought Pi, Droid, OMP, and Mercury integration to profile parity across public, paid, and private distributions.

Measured memory activation

The release ledger records the first bounded project graph activation:

  • Graph edges: 0 -> 3 (2 explicit, 1 inferred).
  • Connected documents: 0 -> 4 of 5.
  • Graph quality score: 20 -> 74.
  • Saved recall holdout: 5/5 cases passed on two runs.
  • Recall@5: 1.0.
  • MRR: 0.9.
  • Numeric exactness: 1.0.
  • Citation coverage: 1.0.
  • Graph lift: 0.0 because direct retrieval already found every expected file.

That last number matters. Graph expansion stays disabled until a holdout proves nonzero lift. ContextLattice records the truth, not the marketing fantasy.

Safety boundaries

  • The CLI remains the primary operator and agent interface.
  • ContextLattice does not auto-install Pi, Droid, OMP, Mercury, or any other third-party harness.
  • Runner quality remains advisory; it does not auto-dispatch work.
  • Pi and Droid process execution remains in repo-local adapters, never in gateway-go or Docker Compose.
  • No Python service is part of the active public application runtime. Compact hook glue and optional development scripts remain separate from the Go/Rust hot path.
  • Release artifacts are sanitized for secrets, local absolute paths, and user memory.

Reproduce

contextlattice_synthesis_pack "what matters before the next decision?" --project contextlattice --pretty
contextlattice_async_inbox_drain --session-id <session-id>
contextlattice_runner_quality --pretty
scripts/agent/audit-capability-parity --pretty
scripts/agent/recall-quality-eval --include-debug --tuning --pretty

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

Track sheawinkler/ContextLattice

Get notified when new releases ship.

Sign up free

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.

All releases →

Related context

Earlier breaking changes

  • v3.17.3 Agent guidance now mandates the `/agents/tasks` route family.
  • v3.17.3 Task worker now checks approval before any execution steps.

Beta — feedback welcome: [email protected]