This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+4 more
Affected surfaces
Summary
AI summaryAdded contextlattice agent-fit command with comprehensive steering workflows.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
`contextlattice agent-fit` adds steering publish, replay, acknowledgement, watch, runner selection, model selection, profile resolution, configuration, and explicit context-preparation workflows. `contextlattice agent-fit` adds steering publish, replay, acknowledgement, watch, runner selection, model selection, profile resolution, configuration, and explicit context-preparation workflows. Source: llm_adapter@2026-07-19 Confidence: high |
— |
| Feature | Medium |
Steering supports resumable Server‑Sent Events with event IDs, acknowledgements, bounded replay, backpressure handling, and honest pull fallback. Steering supports resumable Server‑Sent Events with event IDs, acknowledgements, bounded replay, backpressure handling, and honest pull fallback. Source: llm_adapter@2026-07-19 Confidence: high |
— |
| Feature | Medium |
Runner and model selection combines readiness, capabilities, observed quality, context fit, cost, latency, failures, and abstains when evidence is weak. Runner and model selection combines readiness, capabilities, observed quality, context fit, cost, latency, failures, and abstains when evidence is weak. Source: llm_adapter@2026-07-19 Confidence: high |
— |
| Feature | Medium |
Effective profiles resolve deterministically from explicit request, stored agent profile, then generic fallback, applying capability and context‑window constraints. Effective profiles resolve deterministically from explicit request, stored agent profile, then generic fallback, applying capability and context‑window constraints. Source: llm_adapter@2026-07-19 Confidence: high |
— |
| Feature | Medium |
Context preparation is opt‑in, approval‑first, and binds artifacts to task, profile, source generation, authorization state, expiry, and external‑worker consumption. Context preparation is opt‑in, approval‑first, and binds artifacts to task, profile, source generation, authorization state, expiry, and external‑worker consumption. Source: llm_adapter@2026-07-19 Confidence: high |
— |
| Feature | Medium |
Pi and Droid task‑worker adapters consume entitled selection authorization only when it matches the named runner or model. Pi and Droid task‑worker adapters consume entitled selection authorization only when it matches the named runner or model. Source: llm_adapter@2026-07-19 Confidence: high |
— |
| Feature | Low |
Operator and Enterprise add workspace‑isolated governance for steering delivery, revocation, profile rollout, context‑prep budgets, schedules, and owner‑only state with hash‑linked receipts. Operator and Enterprise add workspace‑isolated governance for steering delivery, revocation, profile rollout, context‑prep budgets, schedules, and owner‑only state with hash‑linked receipts. Source: llm_adapter@2026-07-19 Confidence: high |
— |
| Bugfix | Low |
Rollback instructions clarify deactivating or rolling back governance policy by generation and stopping new selection authorizations or context‑prep schedules. Rollback instructions clarify deactivating or rolling back governance policy by generation and stopping new selection authorizations or context‑prep schedules. Source: llm_adapter@2026-07-19 Confidence: high |
— |
Full changelog
ContextLattice v3.23.0
Agent Fit
ContextLattice now adapts the briefing around the agent without absorbing the
agent itself. The CLI remains the primary interface. HTTP remains the
integration fallback.
What changed
contextlattice agent-fitadds steering publish, replay, acknowledgement,
watch, runner selection, model selection, profile resolution, profile
configuration, and explicit context-preparation workflows.- Steering supports resumable Server-Sent Events with event IDs,
acknowledgements, bounded replay, backpressure handling, and an honest pull
fallback when a harness cannot hold a stream. - Runner and model selection combines readiness, capabilities, observed
quality, context fit, cost, latency, and failures, then abstains when the
evidence is weak. Public selection is advisory and performs no execution. - Effective profiles resolve deterministically from explicit request, stored
agent profile, then generic fallback, with capability and context-window
constraints applied before use. - Context preparation is opt-in and approval-first. Artifacts are bound to the
task, profile, source generation, authorization state, expiry, and explicit
external-worker consumption. - Pi and Droid task-worker adapters can consume an entitled selection
authorization only when it matches the runner or model already named by the
task. No hidden auto-routing was added.
Product boundary
The public core includes steering delivery, advisory selection, effective
profiles, context preparation, the primary CLI, bounded telemetry, and every
fail-closed execution boundary.
Operator and Enterprise add workspace-isolated governance for steering
delivery and revocation, outcome-calibrated profile rollout, context-prep
budgets and schedules, and explicit selection authorization. These routes
retain bounded owner-only state and hash-linked receipts. They do not run a
model, spawn a process, inject a prompt, write ordinary memory, merge, or push.
Rollback
Deactivate or roll back the affected governance policy by generation. Stop
issuing new selection authorizations or context-prep schedules. Public Agent
Fit remains advisor-only, and external task workers retain process and mutation
ownership throughout rollback.
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]