lkn
/
ollie
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
2,482 Commits 2 Branches 0 Tags 32 MiB
Commit Graph

9 Commits

Author SHA1 Message Date
Ollie Agent 6c7e5864c4 agents: set reasoningEffort per profile; rename thinkingBudget tag 
Reasoning effort is part of an agent's behavior definition, so set it
on all 14 profiles keyed to role (planning/review high, general medium,
lightweight assist low). Also rename the ThinkingBudget json tag from
the confusing bare "reasoning" to "thinkingBudget", distinct from the
reasoningEffort string knob. No config migration needed — no profile or
backends.conf used the old "reasoning" key.
 2026-09-07 13:27:33 +02:00
Ollie Agent 9395a0e07b config: rename agent autoLoad field to tools 
The autoLoad name implied an automatic tool-loading path that no longer
exists; tools now come only from agent config plus the /tool_load ctl
command. Rename the AgentConfig.AutoLoad field (json autoLoad) to Tools
(json tools), rename LoadAutoLoadTools to LoadTools, and update all 14
agent JSON profiles and the tool-not-loaded error message.
 2026-09-07 13:23:17 +02:00
Ollie Agent 86db9c797b agents: autoload all memory tools 2026-09-05 11:58:12 +02:00
Levi Neely 6b5d3fd0b6 agents: align autoLoad with agent roles 
Each agent now has tools matching its purpose:

- Read-only agents (explorer, navigator, observer, theo, copilot):
  No shell, file_write, file_edit. Code analysis tools only.

- Workflow agents (author, reviewer, panelist, foreman):
  9p client for peer messaging and goalstatus.
  Analysis tools for verification.

- Orchestration agents (conductor):
  subagent_spawn, 9p client, analysis tools.
  No direct file editing (delegates to sub-agents).

- Full coding agents (default, driver):
  Complete toolset including shell, file ops, LSP, code intel.

- Support agents (librarian, taskmanager):
  Scoped to their domain (docs, task files).

Removed tools that violate agent constraints.
 2026-08-21 10:14:42 +02:00
Ollie Agent 94b4c4be3f Integrate OptMem wake into agent memory prompting 2026-08-18 14:01:18 +02:00
Levi Neely 74ba5ae7ac remove maxSteps and ResetsCounter entirely 
The step budget mechanism is gone. Agents run until they finish,
are interrupted by the user, or (for sub-agents) hit the timeout.

No replacement. The human is the kill switch.
 2026-08-17 09:48:58 +02:00
Ollie Agent f82b36ea80 Integrate OptMem memory backend 2026-08-16 11:10:50 +02:00
Ollie Agent 50e465336e Add Tree-sitter code intelligence tools 2026-08-15 21:13:40 +02:00
Levi Neely 81e78a952d add observer agent: read-only watcher with git-based feeder script 
- observer.json: read-only tool set (file_read, file_grep, file_glob, reasoning_think)
- agent-observer.md: terse observation-only prompt
- observer-feed: polls git diff, feeds changes to agent prompt
- justfile: install new files
 2026-08-13 14:28:20 +02:00