Jochen
ff8b3e7c7b
Implement planning mode
2025-12-09 17:03:53 +11:00
Jochen
4aa84e2144
disable thinking if there is no token budget
2025-12-09 16:45:28 +11:00
Jochen
2283d9ddbf
small fix to provider name check
2025-12-09 14:43:35 +11:00
Jochen
fb2cf6f898
fix for thinking budget and hardcoded max token on summary
2025-12-09 12:41:52 +11:00
Jochen
696c441a47
validate max_tokens for call, also fallbacks for summary
...
When the CW is full, max_tokens is often passed at 0 or tiny. The LLM will fail. For Anthropic with thining, there is also the thinking budget.
This can happen during summary attempts, in that case
first try thinnify, skinnify etc..
2025-12-09 10:15:32 +11:00
Dhanji R. Prasanna
48e6d594bc
tweak todo tool output
2025-12-08 11:05:01 +11:00
Dhanji R. Prasanna
678403da35
add a force thinnify cmd
2025-12-05 15:32:13 +11:00
Jochen
928f2bfa9d
actually record coach feedback and use it
2025-12-02 21:23:50 +11:00
Jochen
21af6ba574
fix temperature for summary request too.
2025-12-02 21:20:16 +11:00
Jochen
ae16243f49
Fix temperature param + add thinking for anthropic
...
The temperature param was not passed to the llm.
Now support anthropic models in 'thinking' mode.
2025-12-02 17:24:55 +11:00
Dhanji R. Prasanna
9ee0468b87
test for system message
2025-12-02 14:45:12 +11:00
Dhanji R. Prasanna
d9ad244197
add markdown format only to final_output and fix todo duplication
2025-12-02 14:26:22 +11:00
Dhanji R. Prasanna
a6537e4dba
todo_write outputs entire list
2025-12-02 13:48:05 +11:00
Dhanji R. Prasanna
df3f25f2f0
test for resume unfinished todos
2025-12-02 11:07:13 +11:00
Dhanji R. Prasanna
f8f989d4c6
resume unfinished TODOs
2025-12-02 11:06:58 +11:00
Dhanji R. Prasanna
1b4ea93ba4
token counting bugfix
2025-12-01 14:52:10 +11:00
Dhanji R. Prasanna
4496eee046
fix compaction to restore system message
2025-12-01 14:38:21 +11:00
Dhanji R. Prasanna
81fd2ab92f
unused var
2025-11-29 15:44:30 +11:00
Jochen
dcfd681b05
add summary context window
2025-11-28 16:33:31 +11:00
Jochen
52f78653b4
add context window monitor
...
Writes the current context window to logs/current_context_window (uses a symlink to a session ID).
This PR was unfortunately generated by a different LLM and did a ton of superficial reformating, it's actually a fairly small and benign change, but I don't want to roll back everything. Hope that's ok.
2025-11-27 21:00:02 +11:00
Jochen
7e1ce36a4b
Merge pull request #35 from dhanji/jochen_write_existing_file
...
remove check for whether a file exists in the workspace
2025-11-27 13:44:45 +11:00
Jochen
99125fc39e
completely remove the skipping first player logic
2025-11-27 13:21:40 +11:00
Jochen
5170744099
add cache_control to user messages
2025-11-27 13:12:42 +11:00
Jochen
c58aa80932
explain what file was found in workspace
2025-11-26 21:43:59 +11:00
Jochen
c837308148
never add more than 4 cache controls
...
Anthropic API throws errors otherwise.
2025-11-26 18:38:30 +11:00
Jochen
1e1702001c
Add logging for discovery
2025-11-26 10:41:35 +11:00
Jochen
bd29addefa
reorder system prompt
2025-11-26 10:26:52 +11:00
Jochen
ad198a8501
add code exploration fast start
...
This tries to short-circuit multiple round-trips to llm for reading code.
It's a precursor to trying to context engineer tailored to specific tasks.
In initial experiments, it's only marginally faster than regular mode, and burns more tokens.
2025-11-25 22:51:32 +11:00
Jochen
a96a15d1fc
add code coverage command
2025-11-21 14:38:58 +11:00
Jochen
a097c3abef
first cut
2025-11-21 13:56:36 +11:00
Jochen
551a577ee1
changed user choice for TODO stale check
...
user can ignore, mark stale or quit.
2025-11-21 12:35:14 +11:00
Jochen
84718223bc
remove minor comment
2025-11-21 12:26:41 +11:00
Jochen
28a83d2dcf
check for stale TODOs
...
on by default, can be disabled
2025-11-21 12:09:01 +11:00
Jochen
9f0d5add1e
remove redundant SYSTEM_NATIVE_TOOL_CALLS_MULTIPLE
2025-11-21 11:04:14 +11:00
Jochen
be6c6bfca4
fix ref to system prompt
2025-11-21 10:49:39 +11:00
Jochen
94a41c5c34
don't write warning to console
2025-11-21 10:49:27 +11:00
Jochen
09dbad2d68
allow multiple tool calls, log warnings if there are duplicate calls.
...
controlled via a flag to the agent config:
allow_multiple_tool_calls = true
2025-11-21 10:49:15 +11:00
Jochen
ffbf410b17
log tool calls
2025-11-21 10:49:02 +11:00
Dhanji Prasanna
14c8d066c9
ensure system prompt is always added first
2025-11-20 08:45:03 +11:00
Jochen
b6e226df67
Merge pull request #23 from dhanji/jochen-add-code-instructions
...
system prompt now includes code style guide
2025-11-19 16:25:20 +11:00
Jochen
1069664e16
fix bad max_tokens and context_window logic
...
for non-databricks code
2025-11-19 13:51:16 +11:00
Jochen
3f21bdc7b2
fix tests
2025-11-19 12:42:37 +11:00
Jochen
9bffd8b1bf
cache_control removed from databricks
2025-11-19 12:15:49 +11:00
Jochen
bfee8040e9
regression tests added
2025-11-19 11:32:14 +11:00
Jochen
a150ba6a55
adds ttl to cache control
2025-11-18 23:23:49 +11:00
Jochen
296bf5a449
adds cache_control
2025-11-18 22:38:52 +11:00
Jochen
7f73b664a3
system prompt now includes code style guide
2025-11-18 18:21:16 +11:00
Michael Neale
81cd956c20
allow openai to be used to name named compatible providers
2025-11-10 16:12:33 +11:00
Jochen
dce0d08f8c
fix OpenAI max_token config read
2025-11-10 11:58:34 +11:00
Dhanji Prasanna
1f12ff6ca0
fix refresh and max_tokens bug
2025-11-07 09:50:43 +11:00
