This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+4 more
Summary
AI summaryUpdates What changed, Safety boundaries, and MRR across a mixed release.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| 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.v1responses throughcontextlattice_synthesis_pack,POST /memory/synthesis-pack, andPOST /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/cryptotov0.52.0, with compatiblex/syncandx/textupgrades. - 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(2explicit,1inferred). - Connected documents:
0 -> 4of5. - Graph quality score:
20 -> 74. - Saved recall holdout:
5/5cases passed on two runs. - Recall@5:
1.0. - MRR:
0.9. - Numeric exactness:
1.0. - Citation coverage:
1.0. - Graph lift:
0.0because 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-goor 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
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.
Related context
Related tools
Beta — feedback welcome: [email protected]