Johan Holm
c7858c2eb4
Make sure to only include fallback search engines
2025-03-18 09:53:30 +01:00
Johan Holm
9fa12e594c
update from pre-commit
2025-03-17 11:05:03 +01:00
Johan Holm
711c2805e4
feat(search): Add robust fallback system with configurable retries and enhanced error handling
...
- Implement multi-engine failover system with configurable fallback order
- Add retry logic with exponential backoff and rate limit detection
- Introduce search configuration options:
* fallback_engines: Ordered list of backup search providers
* retry_delay: Seconds between retry batches (default: 60)
* max_retries: Maximum system-wide retry attempts (default: 3)
- Improve error resilience with:
- Automatic engine switching on 429/Too Many Requests
- Full system retries after configurable cooldown periods
- Detailed logging for diagnostics and monitoring
- Enhance engine prioritization logic:
1. Primary configured engine
2. Configured fallback engines
3. Remaining available engines
Example configuration:
[search]
engine = "Google"
fallback_engines = ["DuckDuckGo", "Baidu"] # Cascading fallback order
retry_delay = 60 # 1 minute between retry batches
max_retries = 3 # Attempt 3 full system retries
This addresses critical reliability issues by:
- Preventing search failures due to single-engine rate limits
- Enabling recovery from transient network errors
- Providing operational flexibility through configurable parameters
- Improving visibility through granular logging (INFO/WARN/ERROR)
2025-03-17 10:43:42 +01:00
liangxinbing
114bd46720
update config.example.toml and format file_saver.py
2025-03-17 00:04:17 +08:00
mannaandpoem
0d4cedd51d
Merge pull request #50 from obiscr/wuzi/generated-files
...
place the generated file in the workspace directory
2025-03-16 18:57:53 +08:00
liangxinbing
5e35f01ea8
format code
2025-03-16 12:57:06 +08:00
mannaandpoem
337adf011c
Merge pull request #635 from a-holm/avoid-Validation-error-when-using-gemini
...
fix(llm): improve message handling to support LLMs without content/tool_calls
2025-03-15 17:11:19 +08:00
mannaandpoem
5641c9bf8a
Merge pull request #598 from ca-ke/refactor/web-search-tool
...
refactor(web_search): enhance web search functionality with engine fallback
2025-03-15 17:06:32 +08:00
a-holm
60268f1696
reformat with precommit
2025-03-15 09:48:52 +01:00
liangxinbing
65a3898592
format code and remove max_input_tokens for ToolCallAgent
2025-03-15 14:43:07 +08:00
mannaandpoem
3bb8f8fe71
Merge pull request #642 from matengm1/bug/fix-temperature-defaulting
...
Fix temperature using default if 0
2025-03-15 14:16:46 +08:00
mannaandpoem
d35cd5ccf0
Merge pull request #573 from nezhazheng/main
...
Use the max_input_tokens configuration to constrain the agent’s token usage.
2025-03-15 14:11:19 +08:00
Matt Eng
49ccd72815
Reformat
2025-03-14 21:41:43 -07:00
Matt Eng
b17c9d31a9
Fix temperature using default if 0
2025-03-14 20:39:23 -07:00
a-holm
350b0038ee
fix(llm): improve message handling to support LLMs without content/tool_calls
...
This commit improves the message handling in the LLM class to gracefully handle
messages without 'content' or 'tool_calls' fields. Previously, the system would
raise a ValueError when encountering such messages, causing crashes when working
with models like Google's Gemini that sometimes return messages with different
structures.
Key changes:
- Reordered message processing to check for Message objects first
- Changed validation approach to silently skip malformed messages instead of crashing
- Removed the strict ValueError when content/tool_calls are missing
This change maintains compatibility with correctly formatted messages while
improving robustness when working with various LLM providers.
2025-03-14 21:01:13 +01:00
Caique Minhare [Cake]
6ea5a4d1ef
Merge branch 'main' into refactor/web-search-tool
2025-03-14 15:04:55 -03:00
xiangjinyu
c0c03c0bef
fix _handle_special_tool bug
2025-03-14 13:25:43 +08:00
zhengshuli
9b0b69a5e1
Use the max_input_tokens configuration to constrain the agent’s token usage.
2025-03-14 12:35:26 +08:00
liangxinbing
9c7834eff2
update readme; format code; update config.example.toml
2025-03-14 12:20:59 +08:00
mannaandpoem
e844dfca34
Merge pull request #510 from the0807/feature/o3-mini
...
Support OpenAI Reasoning Models (o1, o3-mini)
2025-03-14 11:47:34 +08:00
xRay
89c9d904db
将工具选择从 ToolChoice.REQUIRED 更新为 ToolChoice.AUTO，以优化规划代理和规划流程的工具调用逻辑。
2025-03-14 09:46:46 +08:00
ca-ke
cba275d405
refactor: enhance web search functionality with engine fallback and retry mechanism
2025-03-13 14:17:57 -03:00
Isaac
be5c2646af
Merge pull request #543 from aacedar/thread_safe
...
update python_execute thread safe
2025-03-13 21:15:17 +08:00
Kingtous
2b9ef4ea08
fix: perform search on query
2025-03-13 09:10:14 +08:00
Kingtous
86d2a7d6bf
feat: implement duckduckgo search, abstract further
2025-03-13 09:05:14 +08:00
Kingtous
b7774b18ef
opt: abstract web search interface, code cleanup
2025-03-13 08:31:40 +08:00
Kingtous
f9ce06adb8
opt: remove unnessary print
2025-03-13 00:50:30 +08:00
Kingtous
bbaff4f095
feat: add baidu search tool and optional config
2025-03-13 00:27:48 +08:00
836304831
ed4b78dc37
update python_execute safe
2025-03-12 23:33:37 +08:00
mannaandpoem
3db1a7fb56
Merge pull request #457 from cefengxu/10Mar2025cefengxu
...
base.py, the 'state' and 'current_step' should be reset after every loop
2025-03-12 22:25:31 +08:00
mannaandpoem
881ecaefa6
Update base.py
2025-03-12 22:25:02 +08:00
bubble65
7b48da0c59
add a new tool called terminal
2025-03-12 21:21:01 +08:00
Isaac
6b64b98b12
Merge branch 'main' into refactor/standardize-tool-choice-literals
2025-03-12 20:55:52 +08:00
xiangjinyu
c6cd296108
add pre-commit
2025-03-12 20:52:45 +08:00
xiangjinyu
f197b2e3d2
Merge remote-tracking branch 'origin/main'
...
# Conflicts:
# app/agent/manus.py
2025-03-12 20:35:33 +08:00
xiangjinyu
31c7e69faf
add max_steps
2025-03-12 20:27:14 +08:00
mannaandpoem
cfdeb3ad4c
Merge pull request #465 from nezhazheng/main
...
Support configuring all BrowserConfig parameters within browser-use.
2025-03-12 20:26:14 +08:00
liangxinbing
74a4c8bef0
fix bug of abnormal exit for BrowserUseTool
2025-03-12 20:25:37 +08:00
liangxinbing
e6e31a2c13
update timeout to 300
2025-03-12 20:09:23 +08:00
zhengshuli
3cb4489cd5
Support configuring all BrowserConfig parameters within browser-use.
2025-03-12 17:57:43 +08:00
Matt Eng
eac3a6e24e
Standardize literals for role and tool choice type definitions
2025-03-12 00:15:31 -07:00
the0807
983e8f0d4b
Support OpenAI Reasoning Models (o1, o3-mini)
2025-03-12 14:33:32 +09:00
mannaandpoem
111a2bc6b1
Merge pull request #469 from cyzus/fix-infinite-loop-for-simple-query
...
fix infinite loop for simple query
2025-03-11 19:20:15 +08:00
Yizhou Chi
61d705f6e6
fix prompt order
2025-03-11 17:55:40 +08:00
Yizhou Chi
cafd4a18da
fix infinite loop
2025-03-11 17:39:28 +08:00
xiangjinyu
3a958944a0
Adjust code structure
2025-03-11 16:32:13 +08:00
xufeng8
e183913372
the 'state' and 'current_step' should be reset after every loop , cefengxu
2025-03-11 13:50:10 +08:00
liangxinbing
8d18c05350
replace max_steps to 20 for Manus
2025-03-11 13:14:43 +08:00
liangxinbing
eeefddf6bf
Bug Fixing based on basy.py
...
Repair from Bob Feng8 Xu
2025-03-11 13:13:24 +08:00
liangxinbing
229d6706a4
format code
2025-03-11 07:31:18 +08:00
