Ling0925
/
suna
mirror of https://github.com/kortix-ai/suna.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
2,543 Commits 30 Branches 7 Tags 406 MiB
Commit Graph

147 Commits

Author SHA1 Message Date
marko-kraemer 504ac13e18 fix 2025-08-23 18:39:40 -07:00
Saumya 4a89aa4855 cleanup llm based code and agent builder prompt 2025-08-23 12:26:38 +05:30
Saumya edc347cfef refactor agent builder 2025-08-22 11:16:00 +05:30
marko-kraemer 60059eaa9b revert accidental changes 2025-08-19 16:36:28 -07:00
marko-kraemer 2d88091258 gpt 5 mini as default 2025-08-19 16:33:14 -07:00
Saumya 49393e9b56 topup credits 2025-08-19 13:50:47 +05:30
marko-kraemer 19765f56c0 context window defs 2025-08-17 12:24:37 -07:00
marko-kraemer 1896208f12 refactor wip 2025-08-16 19:10:56 -07:00
Vukasin e779ae0fe4 feat: playbook fixes and unified modal 2025-08-10 17:41:36 +02:00
marko-kraemer 1f73aa25ef rm temp readme 2025-07-30 22:18:51 +02:00
marko-kraemer 0f36b6e953 update tool decorator to have usage_example 2025-07-30 22:13:46 +02:00
marko-kraemer 99e4ba0574 merge 2025-07-30 16:54:54 +02:00
marko-kraemer ba455ef5f7 Merge branch 'main' into agentpress-sdk-refactor 2025-07-30 16:33:11 +02:00
marko-kraemer f140634859 wip 2025-07-30 16:10:42 +02:00
marko-kraemer 0063d72f2a wip 2025-07-29 14:45:21 +02:00
marko-kraemer b876a4007f wip 2025-07-29 14:33:32 +02:00
LE Quoc Dat 0215b81b09 AI: How can we stream the edit_file tool when it generating like create_file ? Also the edit_file tool show this 
"""Invalid File Edit

Could not extract the file changes from the tool result."""

Check the state of code base and make to sure implement fully
 2025-07-28 22:06:04 +02:00
LE Quoc Dat cb424d8fe7 AI: How can we stream the edit_file tool when it generating like create_file ? Also the edit_file tool show this 
"""Invalid File Edit

Could not extract the file changes from the tool result."""

Check the state of code base and make to sure implement fully
 2025-07-28 21:55:45 +02:00
LE Quoc Dat deb442cbf7 AI: How can we stream the edit_file tool when it generating like create_file ? Also the edit_file tool show this 
"""Invalid File Edit

Could not extract the file changes from the tool result."""

Check the state of code base and make to sure implement fully
 2025-07-28 21:40:07 +02:00
LE Quoc Dat 9a0dc4e200 AI: can we streamline the edit-file just like the create_file tool, in the front end ? 
like stream the code-edit output of the agent; Then we should be able to show the diff as well, when the tool complete. We get the original file content, and the full updated code (output of morph) and some how send it to the front end.

the front end should show this properly , concisely so user can see the changes in green / red.

This shouldn't change the content feed to the model btw. Like it will pollute the context.

make a plan what to do first, not make changes yet
 2025-07-28 20:46:21 +02:00
marko-kraemer 696dd3722f wip 2025-07-28 19:25:52 +02:00
marko-kraemer bb60569193 wip 2025-07-28 16:38:53 +02:00
marko-kraemer 4bce5d799f wip 2025-07-28 14:08:56 +02:00
marko-kraemer b9a4beb136 wip 2025-07-28 13:13:42 +02:00
marko-kraemer 2b31379b89 wip 2025-07-28 12:53:36 +02:00
marko-kraemer a660919dec wip 2025-07-28 11:53:10 +02:00
mykonos-ibiza f4df0087b1 fix model name for anthropic model before fallback to OpenRouter 2025-07-25 12:59:08 +05:30
Krishav Raj Singh f99027b848 remove multiple var should_auto_continue 2025-07-24 20:51:21 +05:30
Krishav Raj Singh e4a6f5a1ef fix: auto continue response if finish_reason is length 2025-07-24 20:22:44 +05:30
Sharath 8cbaf3d44a
fix(backend): anthropic overloaded fallback failure (#929) 2025-07-11 18:36:15 +05:30
marko-kraemer b0ab413866 fix: optimize blocking command execution with marker-based completion detection 
- Use unique completion markers instead of unreliable prompt detection
- Reduce polling from 2s to 0.5s intervals for faster response
- Fix SessionExecuteRequest import path
- Commands now return immediately upon completion vs waiting full timeout
 2025-07-06 20:07:26 +02:00
marko-kraemer dc5496ae94 wip 2025-07-06 16:40:27 +02:00
marko-kraemer 4bbc03f674 wip 2025-07-06 06:40:44 +02:00
marko-kraemer 6a6b9d8e85 refactor wip 2025-07-05 18:07:35 +02:00
Soumyadas15 18057a4db6 chore(dev): agent agnostic threads 2025-06-26 16:59:04 +05:30
sharath 38f4355838
fix(thread_manager): implement batching for message retrieval to enhance database performance and mitigate db limits 2025-06-22 16:42:55 +00:00
sharath 6501543814
feat(thread_manager): implement middle-out message compression to optimize message handling 2025-06-19 18:05:45 +00:00
sharath 184b54fc8f
fix(thread_manager): enhance content validation to include interactive elements 2025-06-19 14:19:48 +00:00
sharath e8dbc55165
fix(thread_manager): add message compression by omitting messages to handle token limits 2025-06-18 21:25:32 +00:00
sharath 05a80e5f55
fix(thread_manager): adjust truncation logic and improve token compression handling 2025-06-18 07:25:29 +00:00
sharath 3507230ed0
fix(compress_messages): truncate the middle of last msg and reduce token size 2025-06-18 05:53:51 +00:00
Sharath 85cb4b032b
Update backend/agentpress/thread_manager.py 2025-06-16 14:39:13 +05:30
sharath e7ef1c64c5
fix(thread_manager): enhance message content parsing and ensure proper compression of prepared messages 2025-06-16 09:07:47 +00:00
sharath 2a49ad8936
fix(thread_manager): improve message handling and update max_tokens calculation 2025-06-16 07:06:24 +00:00
sharath 0e41358047
fix(context): context window compression 2025-06-15 21:14:09 +00:00
sharath c00497865f
fix(thread_manager): adjust max_tokens calculation for deepseek model 2025-06-06 18:48:55 +00:00
Soumyadas15 ed97fc1682 update content length fix - prod 2025-06-06 17:01:07 +05:30
Soumyadas15 3f771c2a70 Merge branch 'main' into content-length-fix 2025-06-06 16:40:51 +05:30
Soumyadas15 4d7bff34c5 fix content length issue 2025-06-06 15:49:47 +05:30
sharath b5ae395fed
refactor(thread-manager): standardize max_tokens parameter in message compression methods 2025-06-06 09:18:34 +00:00