reasoningEffort (low|medium|high) is now the single human-facing control
for model deliberation. Backends that speak a discrete level (OpenAI,
OpenRouter, Copilot, Gemini, Kiro) send it verbatim; Anthropic, which
needs a numeric budget, translates via documented thresholds
(low=4096, medium=8192, high=16384). thinkingBudget remains an advanced
explicit override that wins when set.
- Add EffortLow/Medium/High, threshold consts, ValidReasoningEffort,
EffortThinkingBudget, and GenerationParams.ResolvedThinkingBudget.
- Anthropic: derive budget from effort, grow max_tokens above the budget
(Anthropic requires budget < max_tokens), and force temperature=1 when
thinking is enabled (both are Anthropic requirements).
- Validate reasoningEffort at config load so typos fail loudly instead
of silently no-opping.
- theo: drop explicit thinkingBudget/inflated maxTokens; reasoningEffort
high now implies the 16384 budget.
- Document thresholds and per-backend behavior in data/agents/README.md;
fix stale autoLoad/maxSteps references.
- Add unit tests for the mapping and Anthropic thinking behavior.
Theo is a security auditor reasoning about injection, TOCTOU races,
crypto misuse, and confused-deputy problems — adversarial edge-case work
that needs deep deliberation, not the low effort it was set to. Bump to
reasoningEffort=high and add thinkingBudget=16384 so depth carries over
to Anthropic extended thinking. Raise maxTokens to 24576 so it stays
above the thinking budget (Anthropic requires budget < max_tokens).
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.
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.
user-preferences.md is meant to be prepended to every user message,
not part of the system prompt. Moved from 'prompt' to 'userPrompts'
in: author, conductor, default, foreman, panelist, reviewer.
Other agents already had it in the correct location.
- Add MEMO_TOOLS=1 env var to memo script; when set, all printed
instructions reference native tool names instead of memo paths
- Set MEMO_TOOLS=1 in all memory tool .meta wrappers
- Add memory_nap tool for compressions
- Add memory_zoom tool for tree navigation
- Add part/T pagination args to memory_wake
- Update system prompt to use memory_zoom tool call
- Fix inject ctl: submit as user message when agent is idle
Write to session/{s}/goal to set a session-level objective.
A conductor agent is spawned automatically in the background,
decomposes the goal, spawns sub-agents, and reports completion.
- goal file: write sets goal + starts conductor; read returns status
- goalwait file: blocks until goal status changes (BlockOnce)
- Conductor writes status=complete/blocked back to goal when done
- Session.Goal() / SetGoal() / GoalSignal() on Session struct
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.
- Move user-preferences.md from data/prompts/ to data/agents/.
- Remove it from prompt arrays in all agent JSON configs.
- Add userPrompts field referencing the file via $XDG_CONFIG_HOME path.
- Update justfile install target accordingly.
tool_load was a built-in intercept in the agent loop — the only
'tool' that didn't run in toolsrv. Removed entirely:
- Intercept in loop.go (25 lines)
- Script + .meta in data/tools/
- autoLoad references in agent configs
Loading tools is now exclusively via ctl (which already existed):
echo 'tool_load X' | ollie-9p write .../ctl
System prompt updated to show the ctl pattern.
The sandbox escape mechanism is a bypass, not privilege elevation.
The old name caused the agent to confuse it with sudo.
- elevate/ → bypass/ (package, types, tests)
- elevate_notify.go → bypass_notify.go
- Namespace: /elevate → /bypass, session/*/elevate → session/*/bypass
- Tool arg: "elevated" → "bypass"
- Env: OLLIE_ELEVATE_SOCKET → OLLIE_BYPASS_SOCKET
- File: elevate-policy.yaml → bypass-policy.yaml
- All docs, prompts, and scripts updated
Tools like file_write, file_edit, and shell now reset the agent's step
counter when called successfully. This allows the agent to continue
working without hitting the soft step-budget guardrail as long as it's
making active progress (writing files, running commands) rather than
looping on research/reading.
Changes:
- Add ResetsCounter bool to ToolInfo and MetaFile structs
- Parse resetsCounter from .meta JSON files
- Reset step counter in agent loop when ResetsCounter tool succeeds
- Add resetsCounter: true to file_write, file_edit, shell
- Reduce maxSteps from 50 to 25 (resetsCounter makes this safe)
- Remove "hooks" blocks from all 8 agent JSON files (copilot, default, driver, explorer, librarian, navigator, taskmanager, theo)
- Remove beads shell one-liner from prompt arrays in default.json and driver.json
- Hooks mechanism is dead code; these empty blocks are just noise
- Remove all OLLIE_*_PATH vars (TOOLS_PATH, CFG_PATH, DATA_PATH, etc.)
Use XDG_CONFIG_HOME/ollie/* and XDG_DATA_HOME/ollie/* instead
- Replace OLLIE_<TAG>_LOG per-component logging with single OLLIE_LOG={level}
- Replace OLLIE_USAGE_LOG with XDG_DATA_HOME-based path
- Replace OLLIE_OLLAMA_URL with standard OLLAMA_HOST (or omit entirely)
- Rename protocol markers: OLLIE_LISTEN_READY → ListenReady, OLLIE_9P_OPEN → Open
- Remove freeloader hooks from agent configs
- Update sandbox YAMLs to use XDG paths instead of OLLIE_*_PATH tokens
- Update shell tools to use $(dirname "$0") fallback instead of OLLIE_TOOLS_PATH
- Update docs and prompts accordingly
Add a tool_load tool that writes a tool name to the session's 9P
tools file via ollie-9p, enabling on-demand tool loading.
Reduce autoLoad lists in default.json and theo.json to bare
essentials — everything else is loaded via tool_load.
Ollie Agent
Levi Neely