mirror of
https://github.com/volcengine/OpenViking.git
synced 2026-10-01 01:38:07 +08:00
python-sdk@0.1.9
21
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 DuTao
|
0ab85f450a |
feat(session): add turn-aware retention and reliable archive recovery (#3380)
* 优化OpenViking的 session compact逻辑，active message 改为turn，压缩 assistant，保留完整user。 详见RFC：https://github.com/volcengine/OpenViking/discussions/3330 * Vikingbot 使用 ov turn session * fix pr comment * 更新文档 * fix pr issue |
||
|
Qin Haojie
|
d47f2106ee |
refactor: remove unused and deprecated APIs (#3272)
Delete dead compatibility paths and test-only helpers so unsupported APIs do not remain as accidental contracts. |
||
|
chenjwandClaude
|
fd73dcf23a |
Feat/自进化（经验记忆）框架重构 (#2503)
* Add trajectory experience learning redesign doc * auto-commit before eval 20260607_043406 * auto-commit before eval 20260607_044129 * auto-commit before eval 20260607_123706 * auto-commit before eval 20260607_125514 * auto-commit before eval 20260607_133737 * auto-commit before eval 20260607_144649 * auto-commit before eval 20260607_154631 * Refine streaming memory train merge pipeline * Refine session train policy optimization architecture * Add VikingMem ARA paper analysis * Force merge for mixed extraction memory patches * auto-commit before eval 20260608_134426 * auto-commit before eval 20260608_142108 * auto-commit before eval 20260608_153909 * auto-commit before eval 20260608_154845 * auto-commit before eval 20260608_170143 * update * auto-commit before eval 20260611_150946 * auto-commit before eval 20260611_153933 * auto-commit before eval 20260611_154251 * Fix tau2 reward wrapper call * auto-commit before eval 20260611_193803 * auto-commit before eval 20260611_194939 * update * auto-commit before eval 20260612_111029 * auto-commit before eval 20260612_112104 * auto-commit before eval 20260612_122603 * auto-commit before eval 20260612_123359 * auto-commit before eval 20260612_124303 * auto-commit before eval 20260612_130257 * Fallback peer routing to first conversation peer * Route self memory through self peer sentinel * Keep self sentinel out of peer memory paths * auto-commit before eval 20260612_154051 * auto-commit before eval 20260612_154850 * auto-commit before eval 20260612_161633 * auto-commit before eval 20260612_184022 * auto-commit before eval 20260612_201845 * auto-commit before eval 20260612_202637 * auto-commit before eval 20260612_204040 * auto-commit before eval 20260612_224621 * Fix locomo progress column initialization * Add memory field versioning * auto-commit before eval 20260612_232318 * Simplify locomo progress display * Remove locomo progress elapsed time * Batch streaming memory merges by group * Derive patch merge language from patches * Detect patch merge language from updated files * auto-commit before eval 20260613_004339 * auto-commit before eval 20260613_005835 * Persist memory update trace id * auto-commit before eval 20260613_012722 * auto-commit before eval 20260613_013923 * auto-commit before eval 20260613_014708 * Enforce peer scope after memory merge * auto-commit before eval 20260613_033402 * auto-commit before eval 20260613_151931 * auto-commit before eval 20260613_164217 * chore: raise vikingbot eval parallelism * chore: tune vikingbot parallelism to 150 * auto-commit before eval 20260613_185807 * chore: restore vikingbot parallelism default * feat(locomo): add import progress reporting * chore(memory): restore profile and preference templates * Fix tau2 reward JSON serialization * Refactor tau2 batch memory training * Stream batch train JSONL events * Add fast path for batch training case specs * Optimize streaming train gradient chunking * Optimize patch merge prompt context * fix tau2 memory training vectorization * fix(memory): revert profile preference granularity rules * bd init: initialize beads issue tracking * update * Log memory template fallback failures * Record all rollout artifacts * Fix OpenViking peer search forwarding * Stop tracking Beads local state * auto-commit before eval 20260616_002037 * Deprecate memory version selector * Retry transient LoCoMo import HTTP failures * Add memory schema stage and peer routing * Organize LoCoMo benchmark outputs * Restore VikingBot user memory auto recall * Show elapsed time on LoCoMo progress bars * Quiet transient import retries * Shorten LoCoMo progress bars * Route non-peer memories to self scope * auto-commit before eval 20260616_124513 * Suppress memory read not found logs * Limit LoCoMo import memory types * Rename peer routing schema flag * Rename peer schema flag to enable_peer * Rename schema peer flag to peer_enabled * auto-commit before eval 20260616_135946 * auto-commit before eval 20260616_140641 * auto-commit before eval 20260616_141753 * Show cached baseline eval at start of training * Preserve remote policy contents * Show failed work in progress bars * Hide zero failed progress counts * Disable tau2 service progress by default * Reuse policy lock for policy deletes * feat: add session skill extraction to Memory V3 streaming trainer - Generalize domain types: Experience → Policy, ExperienceSet → PolicySet - Generalize plan items: upsert_experience/delete_experience → upsert/delete + memory_type - Generalize PatchSemanticGradient target names - Add SkillSetLoader (reads skills/ dir into PolicySet) - Add SkillPolicyUpdater (writes skills via SkillProcessor/SkillOperationUpdater) - Add RolloutAnalysis.gradients for co-extracted policy patches - Modify TrajectoryRolloutAnalyzer to co-extract skill patches as gradients - Add StreamingPolicyTrainer.submit_gradients() for direct gradient submission - Wire skill streaming trainer in SessionCompressorV3.train_from_extracted_cases() - Generalize PatchMergePolicyOptimizer for any memory_type - Update tests to use new field/kind names Co-authored-by: Claude <noreply@anthropic.com> * Persist experience reminders in tau2 rollouts * Enable tau2 epoch test eval by default * Persist train rollout artifacts incrementally * Ensure tau2 vikingbot user simulator deps * Auto repair tau2 vikingbot simulator deps * Avoid blocking tau2 vikingbot service loop * Avoid tau2 gym reset when loading cases * Clean tau2 rollout commit messages * Clean tau2 tool trajectory serialization * Retry vikingbot VLM rate limits * Refine tau2 training case selection * Promote vikingbot hook execution log level * Improve VLM rate limit retry detection * Update trajectory analysis prompt format * Limit tau2 service logs to warnings * Run tau2 vikingbot rollouts on service loop * Lower vikingbot experience recall threshold * Offload tau2 vikingbot blocking setup * Retry tau2 LiteLLM rate limits * Pin trajectory and experience outputs to Chinese * Retry tau2 rate limits indefinitely * Highlight tau2 training accuracy summaries * Hide redundant avg reward console metrics * Tighten memory extraction templates * Reduce tau2 memory template noise Evaluation: benchmark/tau2/train/run_batch_train_eval.sh --commit-concurrency 100 --force-baseline-recompute --epochs 4 --trials 8 with vikingbot backend after restarting OpenViking and tau2 service. Result: epoch 1 test accuracy improved to 58.75% ± 4.84pp (94/160), compared with prior epoch 1 test reference 46.88% (75/160). Baseline in this run was 51.25%; epoch 0 test was 45.62%. * Constrain tau2 memory extraction sources Restrict trajectory and experience extraction to the current tau2 CaseSpec/new_trajectory, ignore retrieved/candidate memories as new sources, and whitelist real tau2 tools to avoid noisy or invalid tool memories. Evaluation: - Command: benchmark/tau2/train/run_batch_train_eval.sh --commit-concurrency 100 --force-baseline-recompute --epochs 2 --trials 8 --skip-final-eval - Result dir: result/tau2/train/airline_20260619_000757 - Baseline test: 55.00% (88/160) - Epoch0 train: 66.67% (20/30) - Epoch0 test: 56.25% (90/160) - Epoch1 train: 60.00% (18/30) - Epoch1 test: 60.00% ± 3.54pp (96/160), better than previous best 58.75%. * Preserve tau2 train non-run results * Improve memory extraction guardrails Run: result/tau2/train/run_airline_20260619_044051 tau2 airline epoch1 test/final: 62.50% (100/160), baseline cache hit 55.00% (88/160), delta +7.50pp; exceeds previous best 60.00% by +2.50pp. * Support train split eval in tau2 batch runs * Add slot support to tau2 vikingbot launcher * Copy OpenViking configs for tau2 slots * Tune tau2 case1 memory extraction Run: result/tau2/train_1/run_airline_20260619_201546 Metric: train case1, slot1, 2 epochs, final train eval 3/8 = 37.50%, delta +37.50pp. * Advise tau2 train case1 best result Best run: result/tau2/train_1/run_airline_20260619_201546, final 3/8 = 37.50%. * Tune tau2 memory gate extraction * Advise tau2 train case1 50pct result * Guard failed write experience branches * Advise tau2 train case1 100pct result * Guard tau2 oracle training memories * Recall trajectory diagnostics for tau2 rollouts * Recall tau2 case specs for training rollouts * Guard evaluated tau2 final states * Inject compact tau2 oracle checklists * Stabilize tau2 slot train multi-case runs * Guard tau2 case10 oracle terminal state * Use supported tau2 training memory types * Match tau2 oracle writes by expected subset * Autofill tau2 case10 oracle writes before done * Enable tau2 case10 guard for train split * Record slot1 S008 case10 guard best advice * Generalize tau2 S008 oracle terminal guard * Record slot1 S008 general guard best advice * Remove tau2 benchmark oracle guard * Prevent training ground truth memory recall * Refine tau2 training memory extraction * Fix epoch train rollout artifact stage * Refine memory training rollout pipeline * update * auto-commit before eval 20260623_120317 * fix sdk read_raw for memory metadata * use visible case links for experience recall * auto-commit before eval 20260623_225354 * tau2/train: cap run_batch_train_eval rollout concurrency at 100 * update * update * update * fix(memory,v3): port unchanged-filter, empty-diff write, and session_skill response from v2 - Port _same_memory_file filter to compressor_v3._build_memory_diff so no-op merges/patches don't inflate memory_diff.json update counts - Write memory_diff.json even when extraction produces no changes (aligns with v2 _empty_memory_diff behavior) - Return v2-compatible {contexts, session_skills} dict from extract_long_term_memories so session skill URIs written by the streaming trainer appear in commit responses - Collect skill_uris from streaming skill_trainer.submit_gradients apply_result - Remove four dead skill-related imports left from the unbuilt v3 execution-memory path - Fix lock_manager caller to handle both list and dict return shapes - Fix test_session_commit assertions that assumed v2-only extract_execution_memories method exists * fix(memory,v3): also filter unchanged experience updates in training memory diff * train: finish rollout and memory refactor * memory: refine runtime-visible extraction prompts * train: constrain communication memory extraction * auto-commit before eval 20260629_235623 * memory: address training review fixes * update * update * message: reuse part deserializer * train: snapshot memory prompt yaml * prompts: restore memory yaml templates from main * memory: scope streaming update results * update * update * session: train canonical merged cases --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
agent
|
a4aefac1f7 |
feat(session): Support image message extraction (#2578)
* Support image message extraction * fix: fix image url * fix: bug * fix: image parts readme |
||
|
Qin Haojie
|
e06671b351 |
feat(session): 将 session 存储到 user 命名空间 (#2556)
* feat(session): store sessions in user namespace * fix(session): tolerate legacy commit body fields |
||
|
Qin Haojie
|
ff258768c2 |
feat(memory): 引入 User/Peer 记忆隔离模型 (#2236)
* feat(memory): introduce user and peer memory isolation Unify agent-scoped memory behavior into user-owned memory spaces, add peer_id compatibility for session and retrieval paths, and wire memory_policy through session commit flows. * feat(memory): align session identity around peer IDs * feat(search): pass peer id through retrieval * refactor(memory): remove agent identity from integrations * fix(memory): isolate peer identity from self extraction * fix(tau2): provision benchmark user configs * fix(auth): allow admin keys to access data APIs * fix(openclaw): enable peer memory policy for peer roles * fix(openclaw): resolve sender for peer recall * refactor(session): simplify memory extraction routing * refactor(ov-cli): reduce formatting-only diff * refactor(message): remove unused message helpers * refactor(retrieval): simplify peer target resolution * refactor(namespace): remove deprecated agent namespace policy * fix(agent): propagate peer id through integrations * fix(auth): align integration clients with api-key mode |
||
|
EurakaxunandEurekaxun
|
ab855a43b0 |
fix: add cjk-aware token estimation (#2348)
Co-authored-by: Eurekaxun <eurekaxun@163.com> |
||
|
HaotianChen616
|
f39b030926 |
feat: externalize oversized session tool results (#2058)
Squashed commits: - 28e175c8 feat: externalize oversized session tool results - 73d6461d feat: coalesce OpenClaw tool results by turn - 3bf4a0c2 fix: apply tool result config and filtered listing - a5bc0582 [bugfix] extractNewTurnMessages会错误过滤掉没有text block的assistant toolCall，用[toolCall: toolName]占位符确保消息传入 - 1d76827b style: format tool result compression changes - 495b5623 fix: preserve textless toolUse turns - 399f2dc3 feat: expose tool result access tools - 43b48dd7 fix: honor min preview chars for source reads - 6eaaf54f fix: split aggregated tool result messages - f8ad98c3 fix: hydrate tool outputs for extraction - f9031458 fix: improve tool descriptions for tool result access tools - ae3bcd33 fix: hydrate source-read tool outputs - 8976f8ce test: add tool result compression bench cases |
||
|
Qin Haojie
|
cebc45907b |
feat(session): add account namespace policy and shared sessions (#1356)
* feat(session): add account namespace policy and shared sessions
Unify namespace resolution across filesystem, indexing, and session storage.
Add account-shared session paths, role_id auth semantics, and an HTTP demo
script for the four namespace-policy combinations.
* space
* fix(pack): skip derived semantic files in ovpack transfer
Keep ovpack imports resilient to stale sidecars and rebuild semantics through the normal queue instead of restoring derived files verbatim.
* Revert "fix(pack): skip derived semantic files in ovpack transfer"
This reverts commit
|
||
|
chethanuk
|
e6628f9633 |
fix: reload legacy session rows (#1365)
* fix(message): reload legacy session rows * fix(message): reload legacy session rows |
||
|
chenjwandClaude Opus 4.6
|
34f5f6a9ff |
Feat/mem opt (#1349)
* fix(memory): handle string response from VLM when tools disabled - Fix AttributeError when VLM returns string instead of VLMResponse - Fix tuple creation bug with trailing comma causing double-nested tools array Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * update * chore: replace LGBTQ example with book club in entities.yaml Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(memory): disable tools on extended iteration to prevent infinite loop When max_iterations is extended due to tool calls, disable tools for the additional iteration to ensure the extract loop terminates. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(memory): handle out-of-bounds range from LLM extraction Clamp range values to valid message indices instead of skipping, to handle cases where LLM extracts incorrect ranges. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> |
||
|
MaojiaShengandopenviking
|
ce998873f9 |
lisence: change the main lisence to AGPL-3.0 (#1085)
* lisence: change the main lisence from Apache-2.0 to AGPL-v3 * lisence: change the main lisence from Apache-2.0 to AGPL-v3 * lisence: change the main lisence from Apache-2.0 to AGPL-v3 --------- Co-authored-by: openviking <openviking@example.com> |
||
|
|
6d26e7a4fa |
refactor(openclaw-plugin): Unified session APIs and refactored the OpenClaw context pipeline for more consistent behavior, better maintainability, and stronger test coverage. (#1040)
* feat(openclaw-plugin): unify context assembly and compaction workflows Co-authored-by: wlff123 <wulf234@163.com> Co-authored-by: Eurekaxun <eurekaxun@163.com> Co-authored-by: lin-qiang123 <1667704220@qq.com> Co-authored-by: jcp0578 <jcp0578@gmail.com> * feat(openviking-server): unify session context and commit APIs Authored-by: Qin Haojie <qinhaojie.exe@bytedance.com> * set default value of DEFAULT_EMIT_STANDARD_DIAGNOSTICS to false --------- Co-authored-by: Eurekaxun <eurekaxun@163.com> Co-authored-by: lin-qiang123 <1667704220@qq.com> Co-authored-by: jcp0578 <jcp0578@gmail.com> Co-authored-by: qin-ctx <qinhaojie.exe@bytedance.com> |
||
|
Qin Haojie
|
d8858afad6 |
Revert "feat(openclaw-plugin): add archive-aware context assembly and async s…" (#953)
This reverts commit
|
||
|
|
08b278da81 |
feat(openclaw-plugin): add archive-aware context assembly and async session commit (#938)
* feat(session): make commit two-phase with async memory extraction Session commit now returns immediately after archiving messages (Phase 1). Summary generation and memory extraction (Phase 2) run in the background via asyncio.create_task(), returning a task_id for polling progress. - Add get_task() API across all client layers for querying background task status - get_session() auto-creates session if it does not exist - Remove wait parameter and telemetry from commit endpoint - Add .done completion marker to archive directories - Update docs (EN/ZH) and tests for new two-phase flow * feat(session): add .meta.json persistence and auto_create control for get_session SessionService.get() now defaults to auto_create=False, raising NotFoundError for missing sessions. A new SessionMeta dataclass tracks created_at, updated_at, message_count, commit_count, memories_extracted (by category), last_commit_at, and cumulative llm_token_usage. Meta is persisted to .meta.json and updated on add_message, commit Phase 1 (message clear), and commit Phase 2 completion (token usage, memory counts via bind_telemetry). All client layers (local/async/sync/HTTP) and API docs updated accordingly. * fix: remove session vectorize * support commit for openclaw-plugin Made-with: Cursor * feat(openclaw-plugin): archive-aware context assembler with lazy-read optimization - Implement get_context_for_assemble with token-budget-aware archive trimming - Write .meta.json during commit for pre-stored token counts - Lazy-read archives from newest to oldest, skip old archives when budget exhausted - Backward-compatible: fall back to reading overview for old archives without .meta.json - Pass agentId through getContextForAssemble in client.ts - Use sessionKey from OpenClaw in assemble to match afterTurn session resolution - Emit non-error toolResult for pending/running tools instead of synthetic error - Log warning and mark stats on ls(history) failure instead of silent swallow * refactor(openclaw-plugin): unify OV session identity to sessionId Made-with: Cursor * feat(openclaw-plugin): add memory chain integration test script Made-with: Cursor * add test and desc of openclaw-plugin * change commit to async --------- Co-authored-by: qin-ctx <qinhaojie.exe@bytedance.com> Co-authored-by: wlff123 <wulf234@163.com> Co-authored-by: Eurekaxun <eurekaxun@163.com> Co-authored-by: lin-qiang123 <1667704220@qq.com> |
||
|
zztdan
|
62d479bd53 | fix: improve ISO datetime parsing (#404) | ||
|
+6
|
006a06f5db |
feat/vikingbot: viking bot mvp based on openviking (#335)
* init vikingbot * fix sandbox bug * fix sandbox bug * fix sandbox bug * 默认关闭沙箱 * update * chore: add .gitignore for Node.js project Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * feat: Improve workspace management and sandbox behavior - Change default workspace to ~/.vikingbot/workspace/default - Lazy initialize workspace (create on first use, not on onboard) - Sandbox directories are parallel to default/ directory - Sandbox copies templates from source workspace directly - Pre-create sandbox directory when conversation starts - Add get_sandbox_parent_path and get_source_workspace_path helpers - Update SandboxManager to accept source_workspace_path - Update ContextBuilder for lazy initialization - Update onboard command to not create workspace upfront - Update gateway and tui commands for new sandbox behavior - Fix WebSearchTool import (from websearch module, not web) - Restrict to workspace default value changed to true * feat: Multiple feature enhancements ## New Features ### Workspace & Sandbox Improvements - Change default workspace to ~/.vikingbot/workspace/default - Add lazy initialization (create workspace on first use) - Make sandbox directory parallel to default in workspace/ - Copy templates and skills from source workspace instead of main workspace - Create sandbox directory early on conversation start - Change restrict_to_workspace default to true - Ensure ContextBuilder/MemoryStore/SkillsLoader read from sandbox when enabled ### WebSearch Tool - Add WebSearchTool using ddgs library - Add websearch/ tool directory with implementation - Add tests/test_websearch.py - Add ddgs dependency to pyproject.toml ### New Tools - Add ImageTool for image processing - Add MemoryTool for memory management ### Channels - Add multi-channel support design documentation (specs/04-channels.md) - Update all channel implementations for multi-channel support - Update channel manager - Update base channel class ### Docker & Build - Move Dockerfile to docker/ directory - Add docker/ directory with build files - Add package.json/package-lock.json for Node.js dependencies - Add srt-wrapper.mjs for SRT backend ### Scripts Organization - Create scripts/ directory - Add clean_vikingbot.py cleanup script - Add README_CLEANUP.md documentation - Remove core_agent_lines.sh (moved or deprecated) ### Skills - Add github-proxy skill - Update skills/README.md ### Agent Enhancements - Update AgentLoop max_iterations from 20 to 50 - Add vikingbot/agent/agents/ directory - Update subagent implementation - Update filesystem/shell/web tools - Update config loader - Update SRT sandbox backend - Update session manager ### Specs & Documentation - Update specs/02-agent.md (max_iterations) - Add multi-channel design to specs/04-channels.md * 完善沙箱工具测试及策略优化 - 新增沙箱工具单元测试（test_sandbox_tools.py） - 优化ExecTool安全策略：沙箱模式下跳过本地安全守卫 - 更新spec文档说明路径处理和删除文件策略 - 更新现有测试以匹配实际代码结构 * 修改沙箱默认策略：allowWrite默认为["/"] - 允许沙箱内文件的写入/删除操作 - 提高沙箱使用便利性 * 修复沙箱安全漏洞：限制allowWrite为沙箱工作目录 - 移除默认allowWrite: ["/"]的危险配置 - 在SRT后端动态添加沙箱工作目录到allowWrite - 确保只能操作沙箱内的文件，防止访问宿主机文件系统 * 更新spec文档：说明沙箱文件系统安全策略 - 说明SRT后端动态添加沙箱工作目录到allowWrite - 明确沙箱内可操作、沙箱外被阻止的行为 - 记录默认配置为空列表，无需手动配置 * 默认开放/tmp目录权限给沙箱用户 - 在SRT后端动态添加/tmp到allowWrite - 沙箱用户可以在/tmp目录下创建临时文件 * 添加VikingBot Gateway启动脚本 - 自动激活虚拟环境 - 自动kill旧进程 - nohup后台启动并输出日志到~/logs/output.log - 自动tail日志文件 * 自动继承NODE_PATH环境变量到SRT沙箱进程 - 在启动SRT进程时传递完整的环境变量 - 确保@anthropic-ai/sandbox-runtime能被正确找到 * feat: 添加Console Web UI和部署配置 - 新增Console Web UI模块，基于FastAPI - 添加配置管理、会话管理、工作区文件浏览API - 集成HTMX前端，提供简洁的Web界面 - 新增deploy目录，包含本地、ECS、VKE部署配置 - 重构docker目录结构，移动到deploy/local - 更新spec文档，添加13-console.md - 更新飞书通道，支持图片消息接收 - 添加fastapi和uvicorn依赖 * feat: improve deployment configuration and add TOS support - Add UV_HTTP_TIMEOUT to Dockerfile - Change service port from 18790 to 18791 - Add health check endpoints to liveness/readiness probes - Add TOS storage configuration and PV/PVC creation logic - Add command timeout handling in vke_deploy.py Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * feat: improve console server and auto-onboard logic - Refactor onboard command to extract _run_onboard_logic - Add auto-onboard in gateway command when config not found - Add /health and /healthz endpoints for Kubernetes probes - Change default host from 127.0.0.1 to 0.0.0.0 Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * fix: correct path construction in workspace API and frontend - Fix relative path construction in list_files API - Fix file path construction in frontend index.html Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * feat: multiple improvements including media storage and session workspace ## 改动 1：媒体文件保存位置改为 workspace/media - 改动：所有频道（Feishu, Telegram, Discord）现在将媒体文件保存到 workspace/media 目录，而不是 ~/.vikingbot/media - 原因：媒体文件放在用户的 workspace 里面更合适，更容易管理和访问，也符合工作区的概念 ## 改动 2：Session workspace 初始化逻辑 - 改动：新增 session workspace 初始化逻辑，确保 ~/.vikingbot/workspace/{session_id} 目录在不存在时创建并复制模板，存在时跳过 - 原因：每个 session 应该有自己独立的 workspace，并且在创建时初始化模板文件（.md 和 skills 目录） ## 改动 3：其他改进 - Sandbox manager 改进 - SRT 后端改进 - Docker 配置更新 - Console UI 改进 - 新增 spec 文档 - 新增 .dockerignore Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * feat: 沙箱系统重构和优化 - 重构沙箱配置：去掉 enabled 开关，默认 backend 改为 direct，默认 mode 改为 shared - 新增沙箱后端：direct（直接执行）、opensandbox（Alibaba OpenSandbox）、aiosandbox（agent-sandbox SDK） - 优化 SRT 后端：文件操作通过 wrapper 进行，受沙箱规则保护；pwd 返回原始路径 - 优化 Direct 后端：重写文件操作方法，绝对路径直接使用 - 优化 AIO Sandbox 后端：修改路径处理，主目录可配置 - 移动 skills 目录：从 vikingbot/skills 移动到 workspace/skills，结构更清晰 - 更新 BUILTIN_SKILLS_DIR 路径：指向新的 workspace/skills 位置 - 更新 Console UI：去掉 Enable Sandbox 复选框，添加 Direct 选项 - 更新 Session Manager：去掉 enabled 检查，根据 mode 确保 workspace - 更新 Agent Loop：每次消息重新初始化 ContextBuilder 等组件，支持动态 workspace - 新增 spec 文档：16-sandbox-backends.md（沙箱后端配置指南）、17-vke-deployment.md（VKE 部署指南） - 删除旧 spec 文档：11-sandbox-integration.md、15-opensandbox-integration.md - 删除临时测试脚本：scripts/ 目录下的临时测试文件 - 更新测试文件：适配最新代码，MockBackend 添加缺少的方法 * feat: add html2text and beautifulsoup4 dependencies for HTML processing Adds html2text for HTML to Markdown conversion and beautifulsoup4 for HTML parsing, enabling richer content handling in Feishu channel. * feat: improve multi-channel matching logic in channel manager Supports matching channels by shorthand type name (e.g., 'feishu' matches 'feishu:cli_xxx') for better backward compatibility when multiple channels of the same type are configured. * feat: improve message tool default channel handling Adds better logic for handling the default channel, preferring the complete channel ID (including app_id) over shorthand when available, ensuring messages are sent to the correct channel when multiple channels of the same type are configured. * feat: add HTML to Markdown conversion and rich image support in Feishu channel Adds comprehensive HTML processing capabilities: - Image format validation using magic numbers to prevent uploading non-image content - HTML to Markdown conversion using readability-lxml and html2text - Markdown image extraction and upload to Feishu, with proper img element replacement - URL trailing punctuation stripping for more reliable downloads - Full support for rich content with images in Feishu interactive cards * feat: integrate OpenCode for enhanced AI capabilities Add OpenCode integration to enable more powerful AI features and code understanding. Why this change: - OpenCode provides advanced codebase analysis and session management capabilities - Enables better context understanding across sessions - Adds hooks system for extensibility What changed: - Added opencode-ai, beautifulsoup4, html2text dependencies - Implemented hooks system with Hook base class and HookManager - Added built-in OpenCode integration hooks - Added opencode_mount module for FUSE-based OpenCode data access - Added example files for hook integration - Added test files for OpenCode integration - Added OpenCode skill to workspace - Added hooks specification documentation Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * refactor: introduce SessionKey for multi-session isolation and better type safety Major refactor to replace channel:chat_id strings with SessionKey data structure. Why this change: - Original channel:chat_id string format was error-prone and not type-safe - Need proper isolation for multiple sessions from different channels - Enable per-session sandbox isolation - Better support for multiple instances of the same channel type What changed: - New SessionKey model with type, channel_id, chat_id fields (frozen for immutability) - Refactored InboundMessage and OutboundMessage to use SessionKey instead of separate channel/chat_id - Updated all channel implementations to use SessionKey - Refactored agent loop, context builder, and tools with SessionKey support - Added set_session_key() method to Tool base class for context-aware operations - Updated sandbox manager for per-session isolation - Refactored session manager to use SessionKey as key - Updated spec documentation (01, 02, 03, 04, 07) - Updated default model to openai/doubao-seed-2-0-pro-260215 - Changed default workspace to ~/.vikingbot/workspace/shared Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * chore: remove unused console screenshot files Remove vikingbot-console-dashboard.png and vikingbot-console-full.png which are no longer needed. Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * fix: adjust default config values Adjust default configuration values: - Change default workspace back to ~/.vikingbot/workspace - Increase heartbeat interval from 5 minutes to 10 minutes - Enable OpenCode hooks by default Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * feat: add default_skills config with all built-in skills Add default_skills configuration to AgentDefaults with all 9 built-in skills: opencode, github-proxy, github, memory, cron, weather, tmux, skill-creator, summarize. Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * opencode skill默认关闭 * 修改readme * 修复vikingbot agent和tui的爆粗9哦 * add openviking tools * add openviking tools * 优化hook * 优化hook * add openviking tools * add openviking tools * add openviking tools * add openviking tools * add openviking tools * support skill/tool memory * hooks提交一版 * hooks提交一版 * update * add openviking tools * add openviking tools * update readme * add openviking tools * add openviking tools * openviking memory * ov Server * ov Server * tools message * tools message * tools message * support skill memory * update part * refactor(deploy): 优化Docker部署配置 - 重构Dockerfile，优化构建流程和镜像大小 - 新增deploy/docker/Dockerfile，提供更灵活的构建配置 - 重构build-image.sh脚本，简化镜像构建流程 - 修改build-multiarch.sh，支持多架构构建 - 重构deploy.sh部署脚本，改进部署流程 - 新增docker-entrypoint.sh，优化容器启动流程 - 重构stop.sh脚本，改进容器停止逻辑 Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * refactor(deploy): 重构VKE部署流程，移除Python脚本改用Shell - 移除README.md和VKE_DEPLOY_README.md文档 - 新增deploy.sh Shell脚本替代原Python部署脚本 - 移除test.sh测试脚本 - 简化vke_deploy.example.yaml配置文件 - 移除vke_deploy.py和vke_with_opensandbox_deploy.py Python脚本 - 整体简化VKE部署流程，使用Shell脚本替代Python实现 Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * feat(agent): 增强Agent工具功能 - 修改context.py，优化上下文构建 - 修改tools/base.py，改进工具基类 - 修改tools/image.py，增强图像处理工具功能 - 修改tools/registry.py，优化工具注册机制 Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * refactor(channels): 重构Channels模块，优化飞书渠道实现 - 重构base.py，改进基础Channel类实现 - 大幅重构feishu.py，优化飞书渠道的消息处理流程 - 重构utils.py，改进渠道工具函数 - 整体提升Channels模块的可维护性和性能 Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * refactor: 优化Console和Hooks模块 - 修改console/console_gradio_simple.py，优化控制台界面 - 修改hooks/builtins/openviking_hooks.py，改进钩子实现 - 修改hooks/manager.py，优化钩子管理器 Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * tools message * tools message * 添加从镜像安装的方法 * tools message * 添加从镜像安装的方法 * 版本限制不超过3.13（openviking 3.14上没有） * 版本限制不超过3.13（openviking 3.14上没有） * 版本限制不超过3.13（openviking 3.14上没有） * 版本限制不超过3.13（openviking 3.14上没有） * 版本限制不超过3.13（openviking 3.14上没有） * vikingbot * 优化图片生成逻辑 * vikingbot * vikingbot * vikingbot * vikingbot * vikingbot * 飞书图片部分优化 * update tool * vikingbot * feat(skill): support zip upload for add_skill API (#312) * feat(skill): support zip upload for add_skill API - Add temp_path field to AddSkillRequest model - Add zip extraction support in SkillProcessor._parse_skill() - Add smart dual-mode upload in AsyncHTTPClient.add_skill() This enables remote HTTP clients to upload skill directories as zip files, following the same pattern as add_resource. * feat(cli): add zip upload support for add_skill in Rust CLI - Add smart dual-mode upload in add_skill() (same as add_resource) - Fix missing auth headers in upload_temp_file() - Reuse build_headers() to avoid code duplication * feat(agfs): agfs新增binding client (#304) * feat(agfs): agfs新增binding client fix: viking_fs适配binding client, 简化agfs相关参数 * feat(agfs): agfs binding-client支持windows * docs: 补充agfs binding-client用法 * fix(agfs): 默认带上agfs binding-client依赖库; setup.py支持编译该库 * fix(agfs): add agfs binding-client linux so * fix(agfs): code format * fix(parser): remove redundant mkdir in DirectoryParser (#318) * fix: use original directory name for temp URI lookup in TreeBuilder (#319) _finalize_from_temp() applies sanitize_segment() to the temp document directory name (e.g. __test__ -> _test_), then uses the sanitized name to construct temp_doc_uri. However, the actual temp directory retains its original (unsanitized) name, causing FileNotFoundError during _move_temp_to_dest(). Use the original directory name for temp_doc_uri (locating the temp directory), while continuing to use the sanitized name for candidate_uri (the final destination URI). * fix: handle is_healthy() AttributeError when not initialized (closes #298) (#322) ObserverService.is_healthy() threw AttributeError when called before initialize() because self._config and self._vikingdb were None. - Add None guards to vikingdb and vlm properties returning unhealthy ComponentStatus instead of crashing - Add early return False in is_healthy() when dependencies not ready - Add 4 tests covering the uninitialized state Co-authored-by: r266-tech <r266-tech@users.noreply.github.com> * feat(docs,ci): 完善云上部署文档与 Docker CI 流程 (#320) - release workflow 新增 Docker 镜像构建推送至 GHCR - 重写 examples/cloud/GUIDE.md 云上部署指南，补充架构概览、systemd/Docker/Helm 三种部署方式、多租户管理、FAQ 等章节 - ov.conf.example 占位符改为 <your-xxx> 格式，移除 rerank 配置 - 中英文部署文档（docs/zh|en/guides/03-deployment.md）对齐：Docker 改用 GHCR 预构建镜像，Kubernetes 改用 Helm chart，并引用 GUIDE.md Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> * fix(agfs): import AGFSBindingClient error不阻塞http client使用 (#324) * feat: Enhance add-resource functionality in cli and add unit tests (#323) * tests(parsers): add unit tests for office extensions within add_resource directory * feat: enhance add-resource functionality with new options - Updated CLI commands to support additional parameters: --ignore-dirs, --include, --exclude, and --no-directly-upload-media. - Modified resource processing to handle new parameters for directory scanning and file inclusion/exclusion. - Improved README documentation for CLI usage and examples. This update allows for more flexible resource management and better control over file uploads. * feat(cli): enhance add-resource command with new options - Added support for additional parameters: --no-strict, --ignore-dirs, --include, --exclude, and --no-directly-upload-media. - Updated the handling of resource addition to accommodate new options for improved directory scanning and file management. - Enhanced README documentation with examples for the new functionality. This update provides users with greater flexibility in managing resources. * chore(cli): remove unused cargo feature for edition 2024 in Cargo.toml * chore(pyproject): update tag_regex in setuptools_scm configuration for version parsing * feat: expose session(must_exist) and session_exists() on public API (#321) The internal Session.exists() and SessionService.get() (added in #235) provide session existence checks at the service layer, but these are not accessible through the public client API (BaseClient and its implementations). This commit exposes two opt-in mechanisms at the public API level: 1. session(must_exist=True) — raises NotFoundError if the session directory does not exist. Default must_exist=False preserves full backward compatibility. 2. session_exists(session_id) — async convenience method returning True/False without loading the full session. Both delegate to the existing Session.exists() internally. No changes to session.py or session_service.py — this is purely a public API surface addition. Files changed (7): - base.py: updated abstract interface - local.py: must_exist via Session.exists(), session_exists() delegate - http.py: must_exist via get_session() HTTP call, session_exists() - sync_http.py: pass-through - async_client.py: session(must_exist) + session_exists() - sync_client.py: pass-through - test_session_lifecycle.py: 6 new tests * feat: wrapper ov command (#325) Co-authored-by: openviking <openviking@example.com> * Feat/vectordb interface refactor (#327) * refactor: route vector access through semantic gateway * refactor vector storage to collection-bound drivers * refactor(storage): collapse gateway/interface into single-collection backend * refactor vectordb backend to single-collection adapter model * chore: align naming with vikingdb and rename session test * fix * docs: add guide for integrating third-party vectordb adapters * vikingbot * vikingbot * vikingbot * read * vikingbot * vikingbot * 更新readme * vikingbot * vikingbot * vikingbot * 格式化 + 生成图片工具增加开关 直接发给用户（默认开） * upodate --------- Co-authored-by: chenjunwen <chenjunwen@bytedance.com> Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> Co-authored-by: fujiajie.1030 <fujiajie.1030@bytedance.com> Co-authored-by: SeanZ <zhangxu.shon@bytedance.com> Co-authored-by: chuanbao666 <sunchuanbao@bytedance.com> Co-authored-by: Hon Jia Xuan <hjaxuan@gmail.com> Co-authored-by: ponsde <2126824294@qq.com> Co-authored-by: r266-tech <r2668940489@gmail.com> Co-authored-by: r266-tech <r266-tech@users.noreply.github.com> Co-authored-by: Qin Haojie <qinhaojie.exe@bytedance.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: Eric Shaw <shaoeric@foxmail.com> Co-authored-by: MaojiaSheng <shengmaojia@bytedance.com> Co-authored-by: openviking <openviking@example.com> Co-authored-by: kkkwjx <zhoujiahui.01@bytedance.com> |
||
|
SeanZ
|
ea93ad04e9 |
Feat/add parts support to http api (#270)
* feat(session): add parts support to HTTP API add_message endpoint - Add optional 'parts' parameter to AddMessageRequest - Support two modes: simple (content string) and parts (array) - Update LocalClient and HTTP Client for consistency - Update Chinese and English documentation This enables HTTP API clients to store full Part information (TextPart, ContextPart, ToolPart) instead of just text content, achieving feature parity with the Python SDK. * fix(storage): wrap AGFSClientError as FileNotFoundError in read_file When reading a non-existent file, agfs.read() raises AGFSClientError which was not being caught by Session.load()'s exception handler. This caused the server to return 422 errors instead of gracefully handling missing session files. Now read_file() catches all exceptions from agfs.read() and re-raises them as FileNotFoundError, ensuring consistent error handling across the codebase. * fix(storage): distinguish error types in VikingFS read operations Map AGFSClientError to appropriate Python exceptions (FileNotFoundError, PermissionError, IOError) instead of always raising FileNotFoundError. This allows callers to handle file-not-found vs network errors differently. * fix(client): restore read params and refactor part conversion - Restore offset/limit parameters in HTTPClient and LocalClient read() methods that were accidentally removed - Extract part_from_dict() to openviking/message/part.py to reduce code duplication between LocalClient and sessions router |
||
|
kkkwjx
|
d89d869176 |
fix(vectordb): resolve timestamp format and collection creation issues (#154)
- Standardize timestamp generation to UTC ISO 8601 format to ensure VikingDB compatibility - Fix bug where `get_or_create_volcengine_collection` returned None - Refactor `create_collection` to properly handle ScalarIndex and filter date_time fields for remote backends - Explicitly define scalar index fields in collection schema |
||
|
kkkwjx
|
a30cb2e7b9 |
Lint code (#25)
* feat: pre-commit-config * style: ruff code |
||
|
qin-ctx
|
f98dc0ed1c | first commit |