Skip to main content
Released August 10, 2026 · Stable · View on GitHub This stable release finalizes 0.6.0-beta; its notes cover the full range since 0.5.0. 0.6.0 stabilizes the two engine rewrites introduced in the beta — the new agent loop and the standalone parsing & extraction services — and layers ~50 additional PRs of hardening on top: a query-service performance overhaul (~1.8× throughput, p50 latency halved), a fix for a Redis Streams producer bug that could poison publishing process-wide, OpenAI Responses API compatibility fixes, DOCX/CSV chat attachments, and an Omnigent integration for the PipesHub MCP server. Roughly 195 merged PRs since 0.5.0. Operators upgrading from 0.5.0 should read the upgrade notes: this release runs a knowledge-base record-group migration, introduces the parsing-service flag, removes GRAPH_DB_TYPE, changes the Helm chart’s default message broker to Redis, and raises the Docker image RAM limit.

​
Highlights

​
New agent loop, now the only mode

The agent runtime was reimplemented with a new loop (#2702 — @abhishekgml1991) and, in this stable release, becomes the sole execution mode (#2879). The Slack bot was moved onto the new loop (#2857 — @kaushal1999), prompts were tuned for it (#2848), and its navigate/lookup tools are now exposed as HTTP endpoints so the MCP server can consume them as MCP tools (#2937 — @uncleSlayer). Reasoning-effort support runs through the stack: model handling (#2858), agent model fixes (#2896 — @vishwjeet-pawar03), friendly provider names with the reasoning flag defaulted on (#2870), a reasoning parameter on indexing LLM calls (#2932 — @tushar1245), and defaultReasoningEffort declared on agent schemas in the OpenAPI spec (#2877). Deep-agent stale tasks were fixed early in the cycle (#2656 — @vishwjeet-pawar03).

​
Query service performance overhaul

A chat turn was redoing work proportional to the whole answer on every streamed token — roughly 700 times per turn, in three independent places — plus a record-cache bug forced repeat fetches to re-download whole documents. All four were fixed (#2872 — @shrikantNemiwal1): ~1.8× throughput (23 → 43 req/min at 4 workers / 16 users), p50 turn latency halved (36 s → 17.8 s), and SSE traffic down 28×, with the answer itself unchanged.

​
Parsing and data extraction as standalone services

Document parsing and data extraction were split out of the indexing path into their own services (#2541 — @abhishekgml1991), gated by a parsing-service flag (#2734). Follow-ups hardened concurrency (#2738), fixed the HTML parser and other parsing paths (#2749 — @jatingaur18, #2770), added health status for both services (#2845 — @rish664) plus build targets (#2822), and dropped base64 encoding when sending PDFs to the Docling service (#2792 — @kaushal1999).

​
Smarter, cheaper PDF and OCR pipeline

Docling is now the default PDF parser (with a BlockParser bug fix) and falls back to OCR when it fails (#2724, #2672 — @kaushal1999). OCR got safer and faster: an individual VLM-OCR instance per parse call (#2739), a cap on OCR-detection pages (#2790), Docling memory and latency optimizations (#2809), and batched LLM calls for table indexing (#2844).

​
OpenSearch joins the supported backends

OpenSearch is now a supported search backend (#2547 — @abhishekgml1991), extending deployment options for organizations standardized on OpenSearch.

​
Redis Streams producer survives disconnects again

disconnect() on the shared Redis Streams producer used ioredis quit(), which is terminal — one request handler stopping the singleton producer poisoned publishing for the whole process until restart. The client is now recreated on reconnect, restoring producer/consumer recovery after any disconnect (#2867 — @anupPradhan0).

​
MCP grows: Omnigent integration and new tools

A ready-to-run Omnigent agent now ships under integrations/omnigent/, exposing the full PipesHub MCP tool set with chat-first routing (pipeshub_chat, pipeshub_search, pipeshub_sources, and more) against the existing /mcp server (#2902 — @shekharkadyan). The MCP server itself was updated to v2.2.0 (#2780 — @uncleSlayer), with a scope fix and a fetch-full-record API (#2726) and a fetch-full-record tool bug fix (#2743).

​
Bulk user invites, with a review step

Admins can upload a CSV or Excel file of email addresses — parsed, validated, normalized, and deduplicated server-side, with invitations processed asynchronously (#2715 — @anupPradhan0). The stable release adds a review screen so imports can be inspected before invites are sent (#2912).

​
Breaking changes & upgrade notes

  • Knowledge-base record groups are migrated to connectors; the migration runs as part of this release (#2650 — @tushar1245).
  • Parsing and extraction now run as separate services controlled by a flag — review your deployment config before enabling (#2541, #2734).
  • The env template was refreshed and the redundant GRAPH_DB_TYPE key removed from Dockerfiles; the Helm chart now defaults the message broker to Redis, deploying Kafka/ZooKeeper pods only conditionally (#2887 — @tushar1245).
  • The Atlassian site URL field was removed from connector configuration (#2693).
  • The PipesHub Docker image RAM limit was increased — check host sizing (#2853); the database sandbox was disabled (#2854).

​
Connectors

  • Slack — personal (user-scoped) connector added (#2801 — @jatingaur18).
  • Box — shared files sync (#2719 — @R0gue-one).
  • Google Drive — shared-drive filter (#2620) and folder filter (#2811), plus a NoneType guard before logging (#2691).
  • Gmail — indexing fix (#2748).
  • Outlook — removed external-user sync (#2742) and fixed idle-closed transport on long-lived connectors (#2772 — @shrikantNemiwal1).
  • Jira Data Center — handle users/permission-schema endpoints that differ across DC versions (#2704 — @darshangodase).
  • GitLab — connector fixes (#2920 — @darshangodase).
  • Web — crawl4ai support for higher-fidelity crawling (#2641 — @R0gue-one) with follow-up bug fixes (#2750).
  • RSS — indexing fix (#2729).

​
Agents & AI

  • Jira Data Center and Confluence Data Center toolsets so agents can act against self-hosted Atlassian (#2661, #2667 — @darshangodase), plus Confluence tool fixes (#2812).
  • OpenAI Responses API compatibility: an initial fix (#2876 — @abhishekgml1991) plus correct token-limit truncation detection and normalization of structured responses to plain text for image descriptions, streaming, and reflection history (#2917 — @kaushal1999).
  • Chat attachments: markdown and txt (#2657), DOCX and CSV (#2894 — @abhishekgml1991); images capped at 25 per message (#2655).
  • Retrieved records are enriched with related records from graph edges (parent, child, attachment), carrying parent ticket/project metadata into LLM context (#2596 — @darshangodase), with a follow-up fix for to_llm_context and graph enrichment (#2840).
  • Blocks now carry author and mentioned-user IDs for people-aware retrieval (#2827 — @jatingaur18) and a head tag (#2936).
  • Handled the deprecated temperature field for Claude models (#2723).
  • Fixed the user-ask tool schema (#2873 — @vishwjeet-pawar03), sandbox code execution (#2892), artifact creation (#2916), and the completion-gate artifact trigger (#2888).

​
Fixes

  • Indexing: failures propagate to queued MD5 duplicates (#2694 — @shekharkadyan), YAML support with JSON/YAML/YML handling fixes (#2731, #2752), Unicode preserved in indexing prompts (#2686 — @TatshSiow), semantic metadata added to blob storage in the legacy parsing flow (#2768), default indexing status and reindex pagination (#2735), placeholder-record handling (#2767), reindex API for non-creators (#2733), and a fix for issue #2883 (#2890 — @kaushal1999).
  • File preview: reliable PPT/PPTX-to-PDF conversion with LibreOffice and CJK fonts installed in Docker (#2711, #2713 — @TatshSiow, #2732 — @hamza426-ahm).
  • Chat & UI: answer-response rendering (#2868), markdown rendering with $ signs (#2922 — @tushar1245), citation markdown (#2678), citation popover no longer closes on preview (#2923 — @Pranjal-wq), Gemini PDF upload crash when the LLM returns content as a list (#2635 — @shekharkadyan), user-query UI (#2834), chat window alignment (#2862, #2875), removed the graph/plot force-download hook (#2866), external-link icons open the source web URL (#2925), folder-upload hierarchy shown with a compact add button (#2928), embedding-model download progress in the UI (#2681), fail reason no longer shown on completed records (#2671), empty manual-indexing tooltip (#2687), connector label typo (#2700).
  • Knowledge hub: app-scoped search and folder filter (#2709), shared-with-me record groups (#2688), collection record stats (#2777), agent builder shows all configured collections (#2673).
  • Graph queries: replaced invalid coalesce with not_null in AQL (#2914 — @tushar1245).
  • Desktop: the Electron app can now switch servers (#2865 — @abhishekgml1991).
  • Cleanup: removed admin/everyone broadcast notifications (#2728), stale x-oauth-header (#2664), unused redirect-uri field (#2782), user event (#2828); invite-mail error logging fixed (#2658).

​
Performance & reliability

  • Stabilized MongoDB failures in deployment (#2677 — @shekharkadyan).
  • Message-broker retry and configuration support (#2626 — @shrikantNemiwal1).
  • Increased file-descriptor limits to prevent EMFILE errors under load (#2843 — @anupPradhan0).

​
Security & authentication

  • New token scopes and JWT generators for email verification and OTP (#2784 — @rish664, #2781 — @vanshg685).
  • Authentication is skipped for expired refresh tokens instead of failing noisily (#2736).
  • SMTP values are masked, with related refactoring (#2793).
  • GitHub Actions hardened per GitHub’s new security guidance (#2747).

​
Developer experience & infrastructure

​
New contributors

  • @shekharkadyan made their first contribution in #2677
  • @hamza426-ahm made their first contribution in #2732
  • @Pranjal-wq made their first contribution in #2923
Full commit-level detail: GitHub release · Compare view