docs/en/about/02-changelog.md
All notable changes to OpenViking will be documented in this file. This changelog is automatically generated from GitHub Releases.
ov CLI refresh: ov config is now the interactive configuration manager for adding, editing, deleting, and switching saved configs, while ov config show, ov config validate, and ov config switch remain explicit subcommands. New ov language / ov lang selects the display language, ov status [--verbose] provides aggregated diagnostics, and ov health plus runtime errors render with clearer guidance.bot.ov_server.recall_exp_first_round_only, exp_recall_limit, and exp_recall_max_chars inject agent experience only on the first turn, and both local and remote modes isolate experience namespaces by incoming agent_id.add_resource no longer requires an explicit to when watch_interval > 0; when the import returns a stable root_uri, the watch task binds to it automatically, with CLI, MCP, and docs examples updated to match.ov config setup-cli has been removed; use bare ov config for setup. On first use the new CLI prompts for a display language in interactive shells, so non-interactive automation should run ov language en or ov language zh-CN first.ov status now defaults to a curated diagnostic view; use ov status --verbose or -o json for raw component data.ovcli.conf defaults to http://127.0.0.1:1933, and config serialization now omits default and empty fields.vlm.max_concurrent default is corrected to 64. Local directory uploads now skip symlinks to avoid recursive, duplicate, or out-of-scope ingestion.version field now rejects v1 payloads.ap-southeast-1 region host mappings were added for VikingDB.ov CLI reports a missing CLI config before issuing server requests, server-mode terminology was clarified from dev-implicit to dev, and embedding input truncation was unified.version, and v1 payloads are now rejected.dev-implicit to dev; update scripts or dashboards that match on the previous term.retrieval_anchor and an embedding_template, so vector indexing uses trajectory_name + retrieval_anchor instead of the full operation contract. Experiences and trajectories are connected with system-managed derived_from StoredLink records (forward links + reverse backlinks), replacing fragile source_trajectories metadata.POST /api/v1/sessions/{session_id}/messages/batch and ov session add-messages to add multiple messages in one call (useful for history import and memory extraction); ov add-memory now uses the same stricter JSON message parser.ov_search: The OpenViking OpenClaw plugin no longer registers memory_search, avoiding collisions with OpenClaw built-ins. Use ov_search or /ov-search after importing resources or skills.GET when HEAD is unreliable. Local Word/PowerPoint/Excel/EPUB/legacy-doc conversions now run in worker threads so they no longer block the event loop.setup/build now builds and bundles the Web Studio static assets, so /studio works from pip/pipx installs without Docker.nvidia_nim or nemotron now route through the NVIDIA NIM LiteLLM prefix and NVIDIA_NIM_API_KEY.benchmark/tau2/vikingbot for cold start, train trajectory commits, repeated test averaging, and cross-epoch self-improvement; the previous tau2 LLM harness moved to benchmark/tau2/llm./memory-search and memory_search calls to /ov-search and ov_search.OV_SKIP_STUDIO_BUILD=1 to skip the Studio build during local development.content.read adds a raw=true parameter; default reads still hide memory internals for compatibility.server.profile_enabled; requests with profile=1 then run cProfile for only that HTTP request and append profile lines to JSON responses. The ov CLI can enable and display this with --profile.POST /api/v1/sessions/{session_id}/messages/batch plus Python HTTP client and Session wrapper support via batch_add_messages (up to 100 messages per request), reducing HTTP round trips for LangChain/LangGraph-style integrations.embedding_template, replacing field-level searchable flags. The built-in entities, events, and preferences templates include key fields plus final content in embedding input.embedding.max_input_tokens, and oversized-input errors are classified as input_too_large to avoid repeated retries for unrecoverable payloads.searchable: true, migrate it to top-level embedding_template; field-level searchable no longer contributes to embedding text generation.memory.enable_role_id_memory_isolate to memory.role_id_memory_isolation_enabled in custom ov.conf files.profile=1 as a debugging tool, not a high-traffic production default. Profile output is capped at about 16 KiB./api/v1/console/dashboard/summary, /tokens, and /context-commits now accept an IANA timezone query parameter and return viewer-timezone buckets from the server. Consumers should treat returned date and hour fields as already localized instead of shifting them again on the client.date_utc, hour_utc, and created_at values, with read-time re-bucketing through zoneinfo for DST and half-hour timezone support.memory.session_skill_extraction_enabled, Hermes OpenViking LoCoMo benchmark scripts, an OAuth docs correction for the new Studio OAuth setup entry, and a LiteLLM dependency refresh./api/v1/console/* should send timezone=<IANA name> where appropriate and remove client-side UTC-to-local bucket shifting.date / hour buckets from tokens and context-commits are viewer-timezone buckets. audit.created_at remains UTC ISO and should only be formatted for display.timezone parameter is available.timezone is omitted, Console BFF falls back to server.observability.usage_audit.timezone (default local); set it explicitly for server-side integrations that need stable user-facing day boundaries.web-studio console workspace, shipped it in Docker and pip distributions, served it at /studio, moved OAuth authorize UI into it, and retired the legacy console while keeping favicon compatibility routes.ov, and MCP; added progressive single-entrypoint local-file upload; added code_outline, code_search, and code_expand; and tightened upload-only and zip --ignore-dirs handling.ov_dream was added as an OpenClaw skill, and oversized OpenClaw tool results can be externalized to OpenViking.role_id retrieval, and parallelized hierarchical child search.mv not found, URI remapping, S3 grep performance, VectorDB Unicode recovery, oversized byte rows, embedding error surfacing, and VLM LiteLLM native routes./studio migration.8020 references should migrate to Web Studio at /studio; update custom reverse proxies, bookmarks, and deployment docs.openviking.integrations.langchain (OpenVikingRetriever, with_openviking_context(), OpenVikingChatMessageHistory, OpenVikingContextMiddleware, OpenVikingStore as a LangGraph store, create_openviking_tools()); revamped Codex / OpenCode plugins use lifecycle hooks for auto-recall, incremental capture, and PreCompact commit, and connect directly to the native /mcp endpoint.ov export / ov import support v2 manifests, file checksums, portable index scalar fields, optional dense vector snapshots, and conflict policies; new ov backup / ov restore cover full public-scope migration.@openviking/cli npm package installs the platform ov binary via npm i -g @openviking/cli; Rust CLI release pipeline adds Linux musl artifacts, npm trusted publishing, and a broader integration test suite.find / search accept a level filter for L0 abstracts, L1 overviews, and L2 file hits. Resource files gained a Phase 1 WebDAV adapter, and observer.filesystem exposes filesystem-level observability./api/v1/console/* BFF aggregate token usage, retrieval counts, context commit heatmaps, request audit logs, and context inventory from the existing observability event bus.add_resource(wait=false) returns a reserved root_uri plus persistent task progress while ingestion completes.storage.task_tracker is deprecated and ignored. Task records are always persisted under each account's _system/tasks directory.vlm.backup is a single-tier failover and only triggers on retryable errors (rate limit, 5xx, connection failure, timeout). Auth, authorization, and billing failures do not trigger failover.vlm.extra_request_body is merged into the OpenAI SDK / LiteLLM extra_body, useful for Ollama, OpenAI-compatible gateways, and providers requiring extra JSON fields.OPENVIKING_* environment variables for tuning; the legacy codex.* block in ov.conf remains supported for backward compatibility but is no longer recommended.--vector-mode auto or fail under --vector-mode require.headers for traces, logs, and metrics, enabling direct connection to backends that require extra auth or gRPC metadata..gitignore rules, reducing noise from build artifacts and temp files.search and find now accept multiple target URIs for cross-directory and cross-repo retrieval.agent_prefix as prefix-only; OpenCode memory plugin adds tenant header forwarding.headers across all three exporter types (gRPC metadata in gRPC mode, HTTP headers in HTTP mode)..gitignore by default — previously imported temp/generated files may be excluded after upgrade.agent_prefix is now prefix-only and no longer treated as a full agent identifier; docs migrate agentId → agent_prefix.openviking-server now exposes /mcp on the same port as the REST API, reusing API-Key auth and providing 9 tools (search, read, list, store, add_resource, grep, glob, forget, health)./api/v1/privacy-configs API and openviking privacy CLI for managing sensitive skill settings with version history and rollback.server.observability config enables Prometheus /metrics and OpenTelemetry exporters for metrics, traces, and logs.embedding.text_source, embedding.max_input_tokens, retrieval.hotness_alpha, and retrieval.score_propagation_alpha controls.viking:// URI validation; standard error envelopes for processing/zip/HTTP errors./app/.openviking; missing ov.conf returns 503 initialization guide instead of crashing.encryption.api_key_hashing.enabled must now be configured explicitly (defaults to false). If you relied on implicit hashing, add it to your config.agentId → agent_prefix, recallTokenBudget → recallMaxInjectedChars.vlm.timeout for per-request HTTP timeouts.volcengine.api_key data-plane mode for accessing pre-created cloud VikingDB collections and indexes with an API key.write(mode="create") for creating new text resource files and automatically refreshing related semantics and vectors.OPENCLAW_STATE_DIR support for the OpenClaw plugin.recallTokenBudget and recallMaxContentChars to reduce the risk of overlong OpenClaw auto-recall context injection.ov add-memory now returns OK for asynchronous commit workflows instead of implying the background task has already finished.ov chat now reads authentication from ovcli.conf and sends the required request headers.role_id handling with the server multi-tenant model.toolResult errors caused by incompatible OpenClaw tool-call message formats.add_resource target fields, repo target URIs, filesystem mkdir, and the reindex maintenance route..bat environment read/write, shell escaping, ov.conf validation, and hardcoded paths.cache_control 400 errors for Gemini + tools and added support for OpenAI reasoning model families.ov_import and ov_search in the plugin, and extended Phase 2 commit wait timeout.openviking-server init wizard for local Ollama deployment and added a default file/dir ignore config for ovcli.conf.Memory V2 is now the default memory pipeline, featuring a redesigned format, refactored extraction and dedup flow, and improved long-term memory quality.
openviking-server init).extra_headers).upload.ignore_dirs in ovcli.conf to reduce noisy uploads.ov init / ov doctor → openviking-server init / openviking-server doctor.extra_headers for required headers.storage.agfs.s3.disable_batch_delete.disable_batch_delete option to S3FS for OSS compatibility and improved RAGFS path scope fallback to prefix filters.afterTurn stores messages with correct roles while skipping heartbeat entries.recallPreferAbstract and ingestReplyAssist now false); eval scripts and recall query sanitization added.main on release, Docker Hub push, Gemini optional dependency in image.recallPreferAbstract and ingestReplyAssist now default to false — enable explicitly if needed.gateway.mode, e2e healthcheck tool, bypass session patterns, fault isolation from OpenViking.session_id; CLI chat endpoint priority and grep --exclude-uri/-x enhanced.gateway.mode — manage explicitly after upgrade.--with-bot failures now return error codes; scripts relying on "fail-but-continue" need adjustment.embed().litellm dependency updated to >=1.0.0,<1.83.1.ov.conf on auto install.agent-only memory scope, multi-tenant usage guide..cc file recognition, duplicate title filename conflict fix, upload-id based HTTP upload flow.parent_uri removal, Docker doctor alignment, eval token metrics./bot/v1/chat and /bot/v1/chat/stream now require authentication.temp_upload → temp_file_id flow.openclaw >= v2026.3.22.This patch release stabilizes the server shutdown sequence by properly handling CancelledError, rolls back a bot configuration regression, and tightens the Docker build by switching to uv sync --locked for reproducible dependency resolution.
ov reindex, ov doctor, Prometheus exporter, memory health stats API, trusted tenant header mode, Helm Chart.litellm security policy: temporarily disabled, then restored as <1.82.6 — pin your dependency version explicitly.Emergency hotfix due to a supply chain security incident in the upstream LiteLLM dependency. All LiteLLM-related entry points are temporarily disabled.
litellm is installed in your environmentLiteLLM features will remain unavailable until a trusted upstream fix is released.
This release focuses on stability and developer experience improvements. Key fixes address RocksDB lock contention by sharing a single adapter across account backends, restore previously lost plugin bug fixes, and improve vector store incremental updates. New features include a bot debug mode with /remember command support, summary-based file embedding in the semantic pipeline, and comprehensive PR-Agent review rules for CI. Documentation also received Docker Compose and Mac port forwarding guidance.
agentId.used() tracking interface..doc/.xls parser support, path locking and crash recovery.<think> tag cleanup.ov chat with rustyline line editing, Markdown rendering, chat history.wait parameter, configurable worker count.add-resource tool, Feishu progress notifications.add_resource now supports index control with refactored embedding logic and correctly handles ZIP-based container formats.add_message() adds parts parameter support; semantic indexing triggered for parent directories after memory extraction.VikingURI support, git@ SSH URL format in the CLI, and GitHub tree/<ref> URL for code repository import.agfs gains ripgrep-based grep acceleration and async grep support with optional binding client mode; automated PR review workflows using Doubao model with severity classification.uv pip install -e ..Datasets and indexes generated by previous versions are incompatible with this release and cannot be reused. A full rebuild is required after upgrading to avoid retrieval anomalies, inconsistent filtering, or runtime errors. Stop the service, remove your workspace directory (rm -rf ./your-openviking-workspace), then restart with openviking-server.
This release delivers CLI optimizations including glob -n flag support and cmd echo, alongside README updates for both English and Chinese documentation.
Before upgrading, stop the VikingDB Server and clear your workspace directory. Indexes from prior versions are not forward-compatible with this release.
This release adds C# AST extractor support for code parsing, fixes multi-tenant filtering, normalizes OpenViking memory target paths, and improves git repository detection with git@ SSH URL support. The agfs dependency libraries and binaries are now pre-compiled, eliminating the need for a build step at install time. Documentation adds Qwen model usage instructions.
openclaw-openviking-plugin installation, opencode plugin introduction.ov command wrapper, add-resource enhancements, ovcli.conf timeout support, --version flag.Updated CLI binary release with cross-platform support for macOS and Linux, aligned with the v0.1.18 feature set including the Rust-based implementation and expanded file parser capabilities.
This release brings major new capabilities to OpenViking. A high-performance Rust CLI is introduced alongside a terminal UI for filesystem navigation. File parsing is significantly expanded with support for Word, PowerPoint, Excel, EPub, and ZIP formats. Multi-provider support is added for embedding and VLM backends. Memory handling is redesigned with conflict-aware deduplication and a new extraction flow.
ov tui).Initial CLI binary release with cross-platform support for macOS and Linux, providing a standalone distributable for OpenViking server management and resource operations.
A stability-focused patch release. Reverts dynamic project name configuration in VectorDB due to instability, fixes CI workspace cleanup, and resolves a tree URI output error with added validation of ov.conf on startup.
A focused bug-fix and improvement release. Fixes VectorDB connectivity issues and a server conflict between uvloop and nest_asyncio. Temporary URIs are now human-readable, resource add timeouts are enlarged, and dynamic project name configuration is introduced for VectorDB and Volcengine backends.
This release focuses on architectural refactoring and reliability improvements. The HTTP client is split into distinct embedded and HTTP modes for cleaner separation of concerns. The CLI launch speed is improved through directory restructuring. VectorDB timestamp and collection creation bugs are resolved.
ls and tree output.A major infrastructure release. An HTTP server and Python HTTP client are introduced, enabling remote access to OpenViking services. The OpenClaw skill adds MCP integration support. Directory pre-scan validation, DAG-triggered embedding, and parallel resource addition improve performance and reliability.
~/.openviking.This release improves search quality, storage reliability, and code maintainability. Sparse logit alpha search is added for enhanced retrieval. Query embeddings are reused in the hierarchical retriever for better performance. Native VikingDB deployment is now supported. A critical Zip Slip path traversal vulnerability (CWE-22) is patched.
Adds support for ingesting small GitHub code repositories, enabling OpenViking to index and search public codebases directly.
Patch release fixing a compilation error and resolving a Windows binary release packaging issue.
The initial public release of OpenViking. This release establishes the core project structure with cross-platform support including Linux and Intel Mac. It introduces the service layer architecture, separating embedding and VLM backends into configurable providers. Memory deduplication is improved and retrieval recursion bugs are fixed. Python 3.13 compatibility, S3FS support, and usage examples for chat and memory workflows are included.