Commit Graph
181 Commits
Author SHA1 Message Date
Xubin Ren 35dde8a30e refactor: unify voice transcription config across all channels
- Move transcriptionProvider to global channels config (not per-channel)
- ChannelManager auto-resolves API key from matching provider config
- BaseChannel gets transcription_provider attribute, no more getattr hack
- Remove redundant transcription fields from WhatsAppConfig
- Update README: document transcriptionProvider, update provider table

Made-with: Cursor
2026-04-06 06:07:30 +00:00
Ben LenartsandXubin Ren 202938ae73 feat: support ${VAR} env var interpolation in config secrets
Allow config.json to reference environment variables via ${VAR_NAME}
syntax. Variables are resolved at runtime by resolve_config_env_vars(),
keeping the raw templates in the Pydantic model so save_config()
preserves them. This lets secrets live in a separate env file
(e.g. loaded by systemd EnvironmentFile=) instead of plain text
in config.json.
2026-04-06 13:43:26 +08:00
Xubin Ren a8707ca8f6 Merge origin/main into feat/best_skill_and_hook (resolve 4 conflicts)
Made-with: Cursor
2026-04-05 18:53:17 +00:00
6bd2950b99 Fix: add asyncio timeout guard for DuckDuckGo search
DDGS's internal `timeout=10` relies on `requests` read-timeout semantics,
which only measure the gap between bytes — not total wall-clock time.
When the underlying HTTP connection enters CLOSE-WAIT or the server
dribbles data slowly, this timeout never fires, causing `ddgs.text` to
hang indefinitely via `asyncio.to_thread`.

Since `asyncio.to_thread` cannot cancel the underlying OS thread, the
agent's session lock is never released, blocking all subsequent messages
on the same session (observed: 8+ hours of unresponsiveness).

Fix:
- Add `timeout` field to `WebSearchConfig` (default: 30s, configurable
  via config.json or NANOBOT_TOOLS__WEB__SEARCH__TIMEOUT env var)
- Wrap `asyncio.to_thread` with `asyncio.wait_for` to enforce a hard
  wall-clock deadline

Closes #2804

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-06 02:21:51 +08:00
JiajunandXubin Ren 7e1ae3eab4 feat(provider): add Qianfan provider support (#2699) 2026-04-05 16:52:37 +08:00
Xubin RenandXubin Ren 9ef5b1e145 fix: reset ssrf whitelist on config reload and document config refresh 2026-04-04 19:43:18 +08:00
04cbandXubin Ren 5f08d61d8f fix(security): add ssrfWhitelist config to unblock Tailscale/CGNAT (#2669) 2026-04-04 19:43:18 +08:00
Xubin Ren 0a3a60a7a4 refactor(memory): simplify Dream config naming and rename gitstore module 2026-04-04 10:01:45 +00:00
Xubin Ren 30ea048f19 Merge remote-tracking branch 'origin/main' into pr-2717-review 2026-04-04 04:42:52 +00:00
Xubin Ren 652377bee9 Merge origin/main into feat/web-disable-flag
Made-with: Cursor
2026-04-03 18:41:43 +00:00
imfondofandXubin Ren 896d578677 fix(restart): show restart completion with elapsed time across channels 2026-04-04 02:21:42 +08:00
imfondofandXubin Ren ba7c07ccf2 fix(restart): send completion notice after channel is ready and unify runtime keys 2026-04-04 02:21:42 +08:00
Lingao Meng cf6c979339 feat(provider): add Xiaomi MiMo LLM support
Register xiaomi_mimo as an OpenAI-compatible provider with its API base URL,
add xiaomi_mimo to the provider config schema, and document it in README.

Signed-off-by: Lingao Meng <menglingao@xiaomi.com>
2026-04-03 14:42:57 +08:00
chengyongruandchengyongru b9616674f0 feat(agent): two-stage memory system with Dream consolidation
Replace single-stage MemoryConsolidator with a two-stage architecture:

- Consolidator: lightweight token-budget triggered summarization,
  appends to HISTORY.md with cursor-based tracking
- Dream: cron-scheduled two-phase processor that analyzes HISTORY.md
  and updates SOUL.md, USER.md, MEMORY.md via AgentRunner with
  edit_file tools for surgical, fault-tolerant updates

New files: MemoryStore (pure file I/O), Dream class, DreamConfig,
/dream and /dream-log commands. 89 tests covering all components.
2026-04-02 22:42:25 +08:00
Xubin Ren fbedf7ad77 feat: harden agent runtime for long-running tasks 2026-04-01 19:12:49 +00:00
Shiniese 7f1dca3186 feat: unify web tool config under WebToolsConfig + add web tool toggle controls
- Rename WebSearchConfig references to the new WebToolsConfig root struct that wraps both search config and global proxy settings
- Add 'enable' flag to WebToolsConfig to allow fully disabling all web-related tools (WebSearch, WebFetch) at runtime
- Update AgentLoop and SubagentManager to receive the full web config object instead of separate web_search_config/web_proxy parameters
- Update CLI command initialization to pass the consolidated web config struct instead of split fields
- Change default web search provider from brave to duckduckgo for better out-of-the-box usability (no API key required)
2026-03-30 16:22:11 +08:00
Xubin Ren 5635907e33 feat(api): load serve settings from config
Read serve host, port, and timeout from config by default, keep CLI flags higher priority, and bind the API to localhost by default for safer local usage.
2026-03-29 15:32:33 +00:00
longyongshenandXubin Ren 813de554c9 feat(provider): add Step Fun (阶跃星辰) provider support
Made-with: Cursor
2026-03-25 22:43:47 +08:00
Xubin RenandXubin Ren f0f0bf02d7 refactor(channel): centralize retry around explicit send failures
Make channel delivery failures raise consistently so retry policy lives in ChannelManager rather than being split across individual channels. Tighten Telegram stream finalization, clarify sendMaxRetries semantics, and align the docs with the behavior the system actually guarantees.
2026-03-25 22:37:11 +08:00
chengyongruandXubin Ren 5e9fa28ff2 feat(channel): add message send retry mechanism with exponential backoff
- Add send_max_retries config option (default: 3, range: 0-10)
- Implement _send_with_retry in ChannelManager with 1s/2s/4s backoff
- Propagate CancelledError for graceful shutdown
- Fix telegram send_delta to raise exceptions for Manager retry
- Add comprehensive tests for retry logic
- Document channel settings in README
2026-03-25 22:37:11 +08:00
Xubin RenandXubin Ren 13d6c0ae52 feat(config): add configurable timezone for runtime context
Add agent-level timezone configuration with a UTC default, propagate it into runtime context and heartbeat prompts, and document valid IANA timezone usage in the README.
2026-03-25 22:07:14 +08:00
Xubin RenandXubin Ren 3dfdab704e refactor: replace litellm with native openai + anthropic SDKs
- Remove litellm dependency entirely (supply chain risk mitigation)
- Add AnthropicProvider (native SDK) and OpenAICompatProvider (unified)
- Merge CustomProvider into OpenAICompatProvider, delete custom_provider.py
- Add ProviderSpec.backend field for declarative provider routing
- Remove _resolve_model, find_gateway, find_by_model (dead heuristics)
- Pass resolved spec directly into provider — zero internal lookups
- Stub out litellm-dependent model database (cli/models.py)
- Add anthropic>=0.45.0 to dependencies, remove litellm
- 593 tests passed, net -1034 lines
2026-03-25 01:58:48 +08:00
Xubin Ren 14763a6ad1 fix(provider): accept canonical and alias provider names consistently 2026-03-24 03:03:59 +00:00
Xubin Ren 186357e80c Merge branch 'main' into fix/workspace-scoped-cron-store
Keep cron state workspace-scoped while only migrating legacy jobs into the default workspace. This preserves seamless upgrades for existing installs without polluting intentionally new workspaces.
2026-03-24 02:41:58 +00:00
Xubin RenandXubin Ren 2056061765 refine heartbeat session retention boundaries 2026-03-24 00:33:43 +08:00
Desmond SowandXubin Ren f64ae3b900 feat(provider): add OpenVINO Model Server provider (#2193)
add OpenVINO Model Server provider
2026-03-23 11:07:46 +08:00
Matt von RohrandXubin Ren 7878340031 feat(providers): add Mistral AI provider
Register Mistral as a first-class provider with LiteLLM routing,
MISTRAL_API_KEY env var, and https://api.mistral.ai/v1 default base.

Includes schema field, registry entry, and tests.
2026-03-23 11:07:46 +08:00
Xubin RenandXubin Ren bd621df57f feat: add streaming channel support with automatic fallback
Provider layer: add chat_stream / chat_stream_with_retry to all providers
(base fallback, litellm, custom, azure, codex). Refactor shared kwargs
building in each provider.

Channel layer: BaseChannel gains send_delta (no-op) and supports_streaming
(checks config + method override). ChannelManager routes _stream_delta /
_stream_end to send_delta, skips _streamed final messages.

AgentLoop._dispatch builds bus-backed on_stream/on_stream_end callbacks
when _wants_stream metadata is set. Non-streaming path unchanged.

CLI: clean up spinner ANSI workarounds, simplify commands.py flow.
Made-with: Cursor
2026-03-23 10:20:41 +08:00
Xubin RenandXubin Ren 32f4e60145 refactor(providers): hide oauth-only providers from config setup
Exclude openai_codex alongside github_copilot from generated config,
filter OAuth-only providers out of the onboarding wizard, and clarify in
README that OAuth login stores session state outside config. Also unify
the GitHub Copilot login command spelling and add regression tests.

Made-with: Cursor
2026-03-21 03:20:59 +08:00
Harvey MackieandXubin Ren e029d52e70 chore: remove redundant github_copilot field from config.json 2026-03-21 03:20:59 +08:00
Xubin Ren 1c39a4d311 refactor(tools): keep exec enable without configurable deny patterns
Made-with: Cursor
2026-03-20 17:46:08 +00:00
Xubin Ren 3825ed8595 merge origin/main into pr-1824
- wire tools.exec.enable and deny_patterns into the current AgentLoop
- preserve the current WebSearchTool config-based registration path
- treat deny_patterns=[] as an explicit override instead of falling back
  to the default blacklist
- add regression coverage for disabled exec registration and custom deny
  patterns

Made-with: Cursor
2026-03-20 17:21:42 +00:00
Xubin RenandXubin Ren f44c4f9e3c refactor: remove deprecated memory_window, harden wizard display 2026-03-20 18:46:13 +08:00
chengyongruandXubin Ren f127af0481 feat: add interactive onboard wizard for LLM provider and channel configuration 2026-03-20 18:46:13 +08:00
mamamiyearandXubin Ren d70ed0d97a fix: nanobot onboard update config crash
when use onboard and choose N,
maybe sometimes will be crash and
config file will be invalid.
2026-03-20 13:16:56 +08:00
Sihyeon JangandXubin Ren 8aebe20cac feat(slack): update reaction emoji on task completion
Remove the in-progress reaction (reactEmoji) and optionally add a
done reaction (doneEmoji) when the final response is sent, so users
get visual feedback that processing has finished.

Signed-off-by: Sihyeon Jang <sihyeon.jang@navercorp.com>
2026-03-17 16:19:08 +08:00
kinchahoy 7913e7150a feat: sandbox exec calls with bwrap and run container as non-root 2026-03-16 23:55:19 -07:00
Xubin RenandXubin Ren a1241ee68c fix(mcp): clarify enabledTools filtering semantics
- support both raw and wrapped MCP tool names
- treat [\"*\"] as all tools and [] as no tools
- add warnings, tests, and README docs for enabledTools
2026-03-14 18:33:48 +08:00
lihuaandXubin Ren 4dde195a28 init 2026-03-14 18:33:48 +08:00
Xubin RenandXubin Ren dbdb43faff feat: channel plugin architecture with decoupled configs
- Add plugin discovery via Python entry_points (group: nanobot.channels)
- Move 11 channel Config classes from schema.py into their own channel modules
- ChannelsConfig now only keeps send_progress + send_tool_hints (extra=allow)
- Each built-in channel parses dict->Pydantic in __init__, zero internal changes
- All channels implement default_config() for onboard auto-population
- nanobot onboard injects defaults for all discovered channels (built-in + plugins)
- Add nanobot plugins list CLI command
- Add Channel Plugin Guide (docs/CHANNEL_PLUGIN_GUIDE.md)
- Fully backward compatible: existing config.json and sessions work as-is
- 340 tests pass, zero regressions
2026-03-14 16:13:38 +08:00
Xubin Ren ca5047b602 feat(web): multi-provider web search + Jina Reader fetch 2026-03-13 05:44:16 +00:00
Re-bin 3467a7faa6 fix: improve local provider auto-selection and update docs for VolcEngine/BytePlus 2026-03-12 15:22:15 +00:00
gaoyiman 556cb3e83d feat: add support for Ollama local models in ProvidersConfig 2026-03-12 14:58:03 +08:00
gaoyiman 8865b6848c Merge branch 'main' into feat-volcengine-tuning 2026-03-12 14:56:05 +08:00
Re-bin bd1ce8f144 Simplify feishu group_policy: default to mention, clean up mention detection 2026-03-12 04:45:57 +00:00
Re-bin 94e9b06086 Merge branch 'main' into pr-1768 2026-03-12 04:38:49 +00:00
Re-bin 4478838424 fix(pr-1863): complete Ollama provider routing and README docs 2026-03-11 08:42:12 +00:00
Re-bin a6f37f61e8 Merge remote-tracking branch 'origin/main' into pr-1863 2026-03-11 08:22:02 +00:00
Re-bin d0b4f0d70d feat(wecom): add WeCom channel with SDK pinned to GitHub tag v0.1.2 2026-03-11 07:57:12 +00:00
Re-bin eb6310c438 merge origin/main into pr-1327
Made-with: Cursor
2026-03-11 07:30:38 +00:00