wildlifechorus/condenseit](https:

v2.6.0 Feature

This release adds 1 notable feature for engineering teams evaluating rollout.

Published 10d Productivity & Wikis

✓ No known CVEs patched

✓ No known CVEs patched in this version

Affected surfaces

deps breaking_upgrade

Summary

AI summary

Updates Commits Since 2.5.0, Bug Fixes, and New Features across a mixed release.

Type	Severity	Summary	CVE
Feature	Low	Adds OpenAI-compatible provider for summarization via configurable endpoint Adds OpenAI-compatible provider for summarization via configurable endpoint Source: llm_adapter@2026-05-25 Confidence: high	—
Bugfix
Bugfix	Medium	Raises max_tokens from 900 to 1400, recovers partial fields when LLM responses truncate JSON Raises max_tokens from 900 to 1400, recovers partial fields when LLM responses truncate JSON Source: llm_adapter@2026-05-25 Confidence: high	—
Bugfix	Medium	Displays timestamps in user's local timezone in sidebar and admin UI Displays timestamps in user's local timezone in sidebar and admin UI Source: llm_adapter@2026-05-25 Confidence: high	—
Bugfix	Medium	Prevents sqlite misuse errors and transient key upsert failures under concurrent digest runs Prevents sqlite misuse errors and transient key upsert failures under concurrent digest runs Source: llm_adapter@2026-05-25 Confidence: high	—
Bugfix	Low	Passes think=False to Ollama models so reasoning output becomes visible Passes think=False to Ollama models so reasoning output becomes visible Source: llm_adapter@2026-05-25 Confidence: high	—

Full changelog

OpenAI-compatible provider — CondenseIt can now summarize via any OpenAI-compatible endpoint (Ollama's /v1 compat layer, LM Studio, vLLM, llama.cpp, real OpenAI, Azure OpenAI). Configured via llm.provider: openai, llm.openai_base_url, and optional llm.openai_api_key.

Raw JSON summaries eliminated — LLM responses truncated at the token limit were previously stored as raw ```json blobs visible in the UI. Fixed by raising max_tokens/num_predict from 900 → 1400, adding partial-field recovery from truncated JSON (rescues tldr/key_takeaways even when summary is cut off), and refusing to store unparseable JSON blobs as summary text. A finish_reason=length warning is now logged when truncation is detected.
Ollama think tokens — Pass think=False so Qwen3-class and other reasoning models emit visible output instead of only internal thinking tokens.
Localized timestamps — Sidebar and admin UI timestamps are now shown in the user's local timezone.
SQLite stability — Prevent sqlite misuse errors and transient key upsert failures under concurrent digest runs.

bfacf99 fix(llm): prevent raw JSON summaries from truncated LLM responses
e9c2d0a Merge pull request #3 from wildlifechorus/feature/openai-api-support-2
aac25e7 feat(llm): add openai-compatible summarizer provider
486cebe Merge pull request #1 from melissamcdougall/fix/disable-think-tokens
26cb0c7 fix(ollama): pass think=False so Qwen3-class thinking models produce visible summaries
e41df7c fix(frontend): localize timestamps in sidebar and admin ui
0b31363 fix(pipeline): prevent sqlite misuse and transient key upsert errors

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 wildlifechorus/condenseit](https:

Get notified when new releases ship.

About wildlifechorus/condenseit](https: