|
|
5e9c31595e
|
fix: Forgot to automatically add the bidirectional communication back up to parent agents from sub-agents (i.e. need to be able to check inbox and send messages)
|
2026-02-17 16:11:35 -07:00 |
|
|
|
39d9b25e47
|
feat: Added an agent configuration property that allows auto-injecting sub-agent spawning instructions (when using the built-in sub-agent spawning system)
|
2026-02-17 15:49:40 -07:00 |
|
|
|
b86f76ddb9
|
feat: Auto-dispatch support of sub-agents and support for the teammate pattern between subagents
|
2026-02-17 15:18:27 -07:00 |
|
|
|
7f267a10a1
|
docs: Initial documentation cleanup of parallel agent MVP
|
2026-02-17 14:30:28 -07:00 |
|
|
|
cdafdff281
|
fix: Agent delegation tools were not being passed into the {{__tools__}} placeholder so agents weren't delegating to subagents
|
2026-02-17 14:19:22 -07:00 |
|
|
|
60ad83d6d9
|
feat: Full passive task queue integration for parallelization of subagents
|
2026-02-17 13:42:53 -07:00 |
|
|
|
44c03ccf4f
|
feat: Implemented initial scaffolding for built-in sub-agent spawning tool call operations
|
2026-02-17 11:48:31 -07:00 |
|
|
|
af933bbb29
|
feat: Initial models for agent parallelization
|
2026-02-17 11:27:55 -07:00 |
|
|
|
d2f8f995f0
|
feat: Supported the injection of RAG sources into the prompt, not just via the .sources rag command in the REPL so models can directly reference the documents that supported their responses
CI / All (macos-latest) (push) Has been cancelled
CI / All (ubuntu-latest) (push) Has been cancelled
CI / All (windows-latest) (push) Has been cancelled
|
2026-02-13 17:45:56 -07:00 |
|
|
|
d2e541c5c0
|
docs: Updated todo-system docs
|
2026-02-13 15:13:37 -07:00 |
|
|
|
b11797ea1c
|
fix: Improved continuation prompt to not make broad todo-items
|
2026-02-09 15:36:57 -07:00 |
|
|
|
70c2d411ae
|
fix: Allow auto-continuation to work in agents after a session is compressed and if there's still unfinish items in the to-do list
|
2026-02-09 15:21:39 -07:00 |
|
|
|
a935add2a7
|
feat: Implemented a built-in task management system to help smaller LLMs complete larger multistep tasks and minimize context drift
|
2026-02-09 12:49:06 -07:00 |
|
|
|
8a37a88ffd
|
feat: Improved tool and MCP invocation error handling by returning stderr to the model when it is available
|
2026-02-04 12:00:21 -07:00 |
|
|
|
8f66cac680
|
feat: Added variable interpolation for conversation starters in agents
CI / All (ubuntu-latest) (push) Failing after 5m27s
CI / All (macos-latest) (push) Has been cancelled
CI / All (windows-latest) (push) Has been cancelled
|
2026-02-04 10:51:59 -07:00 |
|
|
|
d5e0728532
|
feat: Implemented retry logic for failed tool invocations so the LLM can learn from the result and try again; Also implemented chain loop detection to prevent loops
CI / All (ubuntu-latest) (push) Failing after 5m27s
CI / All (macos-latest) (push) Has been cancelled
CI / All (windows-latest) (push) Has been cancelled
|
2026-02-01 17:06:16 -07:00 |
|
|
|
25c0885dcc
|
fix: Claude tool calls work incorrectly when tool doesn't require any arguments or flags; would provide an empty JSON object or error on no args
|
2026-02-01 17:05:36 -07:00 |
|
|
|
f56ed7d005
|
feat: Added gemini-3-pro to the supported vertexai models
|
2026-01-30 19:03:41 -07:00 |
|
|
|
d79e4b9dff
|
Fixed some typos in tool call error messages
|
2026-01-30 12:25:57 -07:00 |
|
|
|
f2de196e22
|
fix: Fixed a bug where --agent-variable values were not being passed to the agents
|
2026-01-23 14:15:59 -07:00 |
|
|
|
2eba530895
|
feat: Added support for thought-signatures for Gemini 3+ models
CI / All (ubuntu-latest) (push) Failing after 5m25s
CI / All (macos-latest) (push) Has been cancelled
CI / All (windows-latest) (push) Has been cancelled
|
2026-01-21 15:11:55 -07:00 |
|
|
|
3baa3102a3
|
style: Cleaned up an anyhow error
CI / All (macos-latest) (push) Has been cancelled
CI / All (ubuntu-latest) (push) Has been cancelled
CI / All (windows-latest) (push) Has been cancelled
|
2025-12-16 14:51:35 -07:00 |
|
|
|
cec04c4597
|
style: Improved error message for un-fully configured MCP configuration
|
2025-12-13 13:37:01 -07:00 |
|
|
|
9eeeb11871
|
style: Applied formatting
|
2025-12-03 15:06:50 -07:00 |
|
|
|
3b21ce2aa5
|
feat: Improved MCP implementation to minimize the tokens needed to utilize it so it doesn't quickly overwhelm the token space for a given model
|
2025-12-03 12:12:51 -07:00 |
|
|
|
14549afd52
|
refactor: Updated to the most recent Rust version with 2024 syntax
|
2025-11-07 15:50:55 -07:00 |
|
|
|
71d89eaaba
|
refactor: Changed the name of the summary_prompt setting to summary_context_prompt
|
2025-11-07 11:13:58 -07:00 |
|
|
|
9619b7908f
|
refactor: Renamed summarize_prompt setting to summarization_prompt
|
2025-11-07 11:09:48 -07:00 |
|
|
|
304129d793
|
refactor: Renamed the compress_threshold setting to compression_threshold
|
2025-11-07 11:06:20 -07:00 |
|
|
|
5df435c21a
|
style: Applied formatting
|
2025-11-06 18:19:25 -07:00 |
|
|
|
c4f8c6e102
|
feat: Added the agents directory to sysinfo output
|
2025-11-06 13:22:13 -07:00 |
|
|
|
0550de2093
|
Added environment variables for agents for the global_tools and mcp_servers settings
|
2025-11-06 12:16:36 -07:00 |
|
|
|
fea4411aa6
|
feat: Added built-in macros
|
2025-11-05 16:28:56 -07:00 |
|
|
|
b814a38c59
|
bug: Removed deprecated experimentation for MCP sampling
|
2025-11-05 16:12:04 -07:00 |
|
|
|
1a3476e4fb
|
style: Added an import for Anyhow's Result in the macros module
|
2025-11-05 15:52:44 -07:00 |
|
|
|
ecd4d6587c
|
refactor: Factored out the macros structs from the large config module
|
2025-11-05 15:50:39 -07:00 |
|
|
|
0938119e99
|
bug: Fixed a bug with the spacing of info output now that function_calling_support is a longer name
|
2025-11-05 15:41:49 -07:00 |
|
|
|
77c1a06277
|
refactor: Refactored mcp_servers and function_calling to mcp_server_support and function_calling_support to make the purpose of the fields more clear
|
2025-11-04 13:17:58 -07:00 |
|
|
|
600f5d1484
|
refactor: Refactored the use_mcp_servers field to enabled_mcp_servers to make the purpose of the field more clear
|
2025-11-04 12:51:41 -07:00 |
|
|
|
865ef5827b
|
refactor: Refactored use_tools field to enabled_tools field to make the use of the field more clear
|
2025-11-04 12:37:14 -07:00 |
|
|
|
9d363b38c7
|
refactor: Removed the use of the tools.txt file and added tool visibility declarations to the global configuration file
|
2025-11-04 12:07:58 -07:00 |
|
|
|
2f3586cbbf
|
refactor: Agents that depend on global tools now have all binaries compiled and stored in the agent's bin directory so multiple agents can run at once
|
2025-11-04 11:29:59 -07:00 |
|
|
|
843abe0621
|
feat: Secret injection as environment variables into agent tools
|
2025-11-03 15:10:34 -07:00 |
|
|
|
474c5bc76f
|
feat: Removed the server functionality
|
2025-11-03 14:25:55 -07:00 |
|
|
|
b49a27f886
|
feat: Require Vault set up for first-time setup so all passed in secrets can be encrypted right off the bat
|
2025-10-27 12:00:27 -06:00 |
|
|
|
6f77b3f46e
|
style: Re-applied formatting to make Clippy happy
|
2025-10-24 15:05:42 -06:00 |
|
|
|
8a240b1c3f
|
refactor: Renamed the argument for the --completions flag to SHELL
|
2025-10-24 10:58:28 -06:00 |
|
|
|
59a3e3012b
|
feat: Added static completions via a --completions flag
|
2025-10-24 10:56:34 -06:00 |
|
|
|
a468ee1154
|
bug: Fixed a bug when passing tools to Claude for tools that don't have any inputs
|
2025-10-21 10:04:38 -06:00 |
|
|
|
1b504e211a
|
bug: Fixed a bug that was duplicating entries of all the functions for agents between MCP and tools
|
2025-10-20 15:30:29 -06:00 |
|
