e8e4dac038
add base latency model param
2025-02-17 18:11:33 -05:00
66aa13f6ee
Version bump.
2025-02-13 09:50:00 -05:00
93a3f8ccd7
remove reference to write_file_tool
2025-02-13 09:47:19 -05:00
1084faaf0b
normalize/dedupe files for programmer tool
2025-02-13 09:45:32 -05:00
972ea5284a
be more conservative with external process i/o to prevent hung situations
2025-02-13 09:00:29 -05:00
09e30f2a24
validate expected_runtime_seconds
2025-02-13 08:37:43 -05:00
098f4a9c53
integrate expected_runtime_seconds with run_shell_command
2025-02-13 08:34:38 -05:00
abfa5a1d6a
add expected_runtime_seconds and shutdown processes w/ grace period that run too long.
2025-02-13 08:29:17 -05:00
c5c27c9f87
enforce byte limit in interactive commands
2025-02-13 08:03:16 -05:00
e6b34e4ebc
normalize related file paths
2025-02-12 22:12:55 -05:00
10ad8aa8d5
FIX aider flags ( #89 )
2025-02-12 21:46:14 -05:00
9bd0edfd10
FEAT print config at the beginning ( #88 )
2025-02-12 18:52:24 -05:00
23dfc024e3
Version bump.
2025-02-12 18:09:38 -05:00
e3d0de332f
use parent tty width
2025-02-12 18:07:38 -05:00
3d3b3cfba4
set env vars to disable common interactive modes
2025-02-12 18:04:27 -05:00
18b0ce230e
handle raw input in interactive
2025-02-12 17:59:34 -05:00
7bae09e829
add pyte; improve status panel output
2025-02-12 17:21:03 -05:00
1fbaeac308
use aider from the current env
2025-02-12 17:17:30 -05:00
4d14b9747f
fix interactive command input
2025-02-12 17:08:37 -05:00
0c8a4009dc
fix bug where completion message was wiped too early
2025-02-12 16:58:39 -05:00
a169ed8517
disable put_complete_file_contents; improve prompts; improve status panel output
2025-02-12 16:20:24 -05:00
905ed2c8fc
improve expert model auto detection
2025-02-12 15:55:47 -05:00
e3a705eb9b
auto detect openai expert models
2025-02-12 15:40:21 -05:00
94f0d96654
lower interactive shell history to conserve context; improve prompts
2025-02-12 15:26:36 -05:00
6f9ed9562d
increase history; fix test
2025-02-12 15:01:02 -05:00
dc079c5d0e
improve interactive tty process capture
2025-02-12 14:58:58 -05:00
7598d42cf9
set temperature param on all initialize_llm calls
2025-02-12 14:15:05 -05:00
a1371fc7e0
support default temp on a per-model basis; show status panel
2025-02-12 13:38:52 -05:00
264f5025ed
Refactor write file tool so it is easier for LLMs to use properly.
2025-02-12 11:51:19 -05:00
149e8e2251
set timeouts on llm clients
2025-02-10 11:41:27 -05:00
00a455d586
FIX do not default to o1 model ( #82 )
2025-02-08 20:28:10 -05:00
0c86900ce4
Reduce tool count to make tool calling more reliable.
2025-02-08 18:26:08 -05:00
13016278e5
prompt improvements
2025-02-08 16:10:24 -05:00
4c0c2e2ccf
prompt improvements
2025-02-08 15:54:18 -05:00
f40e11ee21
improve work logging; use reasoning_effort=high for openai expert models; improve prompts
2025-02-08 14:36:08 -05:00
5fad3fc755
make cwd/current date available to more agents
2025-02-08 13:58:16 -05:00
ea992960c1
prompt improvements
2025-02-08 13:36:30 -05:00
c27a75bc26
get rid of pointless truncation message
2025-02-08 12:44:55 -05:00
5861f3a2bf
Adjust token/bytes ratio to resolve errors on swebench-lite.
2025-02-08 08:07:37 -05:00
0270a9a349
Version bump.
2025-02-02 18:54:27 -05:00
53ccc46392
Add model params for o1 and o3-mini.
2025-02-02 18:48:41 -05:00
1cc5b8e16c
refactor: clean up imports and improve code formatting for better readability
...
fix: ensure proper error handling and logging in WebSocket connections
feat: enhance WebSocket server to handle streaming and error messages more effectively
chore: update model parameters and configurations for better performance and maintainability
test: improve test coverage for model token limits and agent creation logic
2025-02-01 13:00:15 -08:00
c2ba638a95
feat(agent_utils.py): enhance get_model_token_limit to support agent types for better configuration management
...
test(agent_utils.py): add tests for get_model_token_limit with different agent types to ensure correct functionality
2025-02-01 12:55:36 -08:00
dd8b9c0d30
Improve prompts.
2025-01-31 17:45:47 -05:00
e95c13a6d0
Fix temperature param handling.
2025-01-31 17:10:49 -05:00
e3414890ff
Add logic to handle whether a model supports temperature or not.
2025-01-31 17:04:52 -05:00
1c463fca17
Add supports_temperature model param.
2025-01-31 16:35:43 -05:00
a387f70a74
Get rid of obsolete models_tokens.py
2025-01-31 16:06:30 -05:00
f7e02fc98e
Refactor models_tokens to be models_params so we can track multiple parameters on a per-model basis.
2025-01-31 16:05:44 -05:00
e059ba3c49
Fix token estimation
2025-01-31 14:39:02 -05:00
AI Christianson
Jose M Leon
Ariel Frischer