|
|
7884adc7c1
|
fix: Clean up orphaned sub-agents when the parent agent
|
2026-02-18 09:12:32 -07:00 |
|
|
|
948466d771
|
fix: Fixed the bash prompt utils so that they correctly show output when being run by a tool invocation
|
2026-02-17 17:19:42 -07:00 |
|
|
|
3894c98b5b
|
feat: Experimental update to sisyphus to use the new parallel agent spawning system
|
2026-02-17 16:33:08 -07:00 |
|
|
|
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 |
|
|
|
1f127ee990
|
docs: Fixed typos in the Sisyphus documentation
|
2026-02-16 14:05:51 -07:00 |
|
|
|
88a9a7709f
|
feat: Added interactive prompting between the LLM and the user in Sisyphus using the built-in Bash utils scripts
CI / All (macos-latest) (push) Has been cancelled
CI / All (ubuntu-latest) (push) Has been cancelled
CI / All (windows-latest) (push) Has been cancelled
|
2026-02-16 13:57:04 -07:00 |
|
github-actions[bot]
|
e8d92d1b01
|
chore: bump Cargo.toml to 0.2.0
CI / All (macos-latest) (push) Has been cancelled
CI / All (ubuntu-latest) (push) Has been cancelled
CI / All (windows-latest) (push) Has been cancelled
|
2026-02-14 01:41:41 +00:00 |
|
github-actions[bot]
|
ddbfd03e75
|
bump: version 0.1.3 → 0.2.0 [skip ci]
|
2026-02-14 01:41:29 +00:00 |
|
|
|
d1c7f09015
|
feat: Simplified sisyphus prompt to improve functionality
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 18:36:10 -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 |
|
|
|
5ef9a397ca
|
docs: updated the tools documentation to mention the new fs_read, fs_grep, and fs_glob tools
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 16:53:00 -07:00 |
|
|
|
325ab1f45e
|
docs: updated the default configuration example to have the new fs_read, fs_glob, fs_grep global functions
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 16:23:49 -07:00 |
|
|
|
4cfaa2dc77
|
docs: Updated the docs to mention the new agents
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 15:42:28 -07:00 |
|
|
|
6abe2c5536
|
feat: Created the Sisyphus agent to make Loki function like Claude Code, Gemini, Codex, etc.
|
2026-02-13 15:42:10 -07:00 |
|
|
|
03cfd59962
|
feat: Created the Oracle agent to handle high-level architectural decisions and design questions about a given codebase
|
2026-02-13 15:41:44 -07:00 |
|
|
|
4d7d5e5e53
|
feat: Updated the coder agent to be much more task-focused and to be delegated to by Sisyphus
|
2026-02-13 15:41:11 -07:00 |
|
|
|
3779b940ae
|
feat: Created the explore agent for exploring codebases to help answer questions
|
2026-02-13 15:40:46 -07:00 |
|
|
|
d2e541c5c0
|
docs: Updated todo-system docs
|
2026-02-13 15:13:37 -07:00 |
|
|
|
621c90427c
|
feat: Use the official atlassian MCP server for the jira-helper agent
|
2026-02-13 14:56:42 -07:00 |
|
|
|
486001ee85
|
feat: Created fs_glob to enable more targeted file exploration utilities
|
2026-02-13 13:31:50 -07:00 |
|
|
|
c7a2ec084f
|
feat: Created a new tool 'fs_grep' to search a given file's contents for relevant lines to reduce token usage for smaller models
|
2026-02-13 13:31:20 -07:00 |
|
|
|
d4e0d48198
|
feat: Created the new fs_read tool to enable controlled reading of a file
|
2026-02-13 13:30:53 -07:00 |
|
|
|
07f23bab5e
|
feat: Let agent level variables be defined to bypass guard protections for tool invocations
|
2026-02-09 16:45:11 -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 |
|
|
|
f82c9aff40
|
fix: fs_ls and fs_cat outputs should always redirect to "$LLM_OUTPUT" including on errors.
|
2026-02-09 14:56:55 -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 |
|
|
|
0a40ddd2e4
|
build: Upgraded to the most recent version of gman to fix vault vulnerabilities
CI / All (ubuntu-latest) (push) Failing after 5m27s
CI / All (macos-latest) (push) Has been cancelled
CI / All (windows-latest) (push) Has been cancelled
|
2026-02-03 09:24:53 -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 |
|
|
|
cdd829199f
|
build: Created justfile to make life easier
CI / All (ubuntu-latest) (push) Failing after 5m26s
CI / All (macos-latest) (push) Has been cancelled
CI / All (windows-latest) (push) Has been cancelled
|
2026-01-27 13:49:36 -07:00 |
|
|
|
e3c644b8ca
|
docs: Created a CREDITS file to document the history and origins of Loki from the original AIChat project
CI / All (ubuntu-latest) (push) Failing after 5m28s
CI / All (macos-latest) (push) Has been cancelled
CI / All (windows-latest) (push) Has been cancelled
|
2026-01-27 13:15:20 -07:00 |
|
|
|
5cb8070da1
|
build: Support Claude Opus 4.5
CI / All (ubuntu-latest) (push) Failing after 5m26s
CI / All (macos-latest) (push) Has been cancelled
CI / All (windows-latest) (push) Has been cancelled
|
2026-01-26 12:40:06 -07:00 |
|
|
|
66801b5d07
|
feat: Added an environment variable that lets users bypass guard operations in bash scripts. This is useful for agent routing
CI / All (ubuntu-latest) (push) Failing after 5m29s
CI / All (macos-latest) (push) Has been cancelled
CI / All (windows-latest) (push) Has been cancelled
|
2026-01-23 14:18:52 -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 |
|
github-actions[bot]
|
2d4fad596c
|
bump: version 0.1.2 → 0.1.3 [skip ci]
v0.1.3
|
2025-12-13 20:57:37 +00:00 |
|
|
|
7259e59d2a
|
ci: Prep for 0.1.3 release
|
2025-12-13 13:38:09 -07:00 |
|
