BeamWeaver

v0.1.11 Feature

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

Published 17d 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

ai-agents deepagents elixir harness human-in-the-loop langchain

+4 more

langgraph-alternative llm observability distributed-tracing

Summary

AI summary

Added first-class GPT‑5.6 profiles with extended context limits, new cache options, and safety identifiers.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Medium	Adds first-class OpenAI GPT-5.6 Sol, Terra, Luna profiles with gpt-5.6 alias and 1.05M context limits. Adds first-class OpenAI GPT-5.6 Sol, Terra, Luna profiles with gpt-5.6 alias and 1.05M context limits. Source: llm_adapter@2026-07-16 Confidence: high	—
Feature	Medium	Adds GPT-5.6 prompt_cache_options, explicit content‑block cache breakpoints, Responses file detail, and persisted reasoning‑context metadata. Adds GPT-5.6 prompt_cache_options, explicit content‑block cache breakpoints, Responses file detail, and persisted reasoning‑context metadata. Source: llm_adapter@2026-07-16 Confidence: high	—
Feature	Medium	Adds `safety_identifier` as a model‑level option for Responses models. Adds `safety_identifier` as a model‑level option for Responses models. Source: llm_adapter@2026-07-16 Confidence: high	—
Bugfix
Bugfix	Medium	Fixes OpenAI cache‑write usage to populate canonical `cache_creation_tokens`. Fixes OpenAI cache‑write usage to populate canonical `cache_creation_tokens`. Source: llm_adapter@2026-07-16 Confidence: high	—
Bugfix	Medium	Fixes response‑level service tier/region metadata propagation to model traces and WeaveScope event fields. Fixes response‑level service tier/region metadata propagation to model traces and WeaveScope event fields. Source: llm_adapter@2026-07-16 Confidence: high	—
Bugfix	Medium	Changes GPT‑5.6 models to prefer the Responses API; Chat Completions rejects function‑tool requests unless reasoning effort is `none`. Changes GPT‑5.6 models to prefer the Responses API; Chat Completions rejects function‑tool requests unless reasoning effort is `none`. Source: llm_adapter@2026-07-16 Confidence: low	—

Full changelog

0.1.11 - 2026-07-08

Added

Added first-class OpenAI GPT-5.6 Sol, Terra, and Luna profiles plus the
official gpt-5.6 alias, including 1.05M context limits, reasoning modes,
provider capability metadata, and standard/cache/long-context pricing data.
Added GPT-5.6 prompt_cache_options, explicit content-block cache
breakpoints, Responses file detail, cache-write usage normalization, and
persisted reasoning-context metadata for OpenAI requests and responses.
Responses models now also accept safety_identifier as a model-level option.

Changed

GPT-5.6 models now prefer the Responses API, and Chat Completions rejects
function-tool requests before transport unless reasoning effort is none.

Fixed

OpenAI cache-write usage now populates canonical cache_creation_tokens, and
response-level service tier/region metadata now reaches model traces and
WeaveScope event fields instead of remaining only in raw provider metadata.

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 BeamWeaver

Get notified when new releases ship.

About BeamWeaver

All releases →