Each backend is now configured via ~/.config/ollie/backends.conf:
[openrouter]
key = sk-or-v1-...
model = qwen/qwen3-235b-a22b
[anthropic]
key = sk-ant-...
Each backend knows its own default URL (openrouter → openrouter.ai/api,
anthropic → api.anthropic.com, etc). Only key and optional model needed.
Env vars (OLLIE_OPENAI_KEY, OLLIE_ANTHROPIC_KEY, etc) still work as
fallback for backward compatibility, but backends.conf is the canonical
config path going forward.
- Delete openAIName() (URL no longer determines backend identity)
- Delete geminiKey() (config handles fallback)
- Install template with mode 600 (contains API keys)
- Only install template if user hasn't created their own
Switch from 'read -e' to plain 'read' so multi-line paste can be
captured. Readline was consuming pasted lines individually.
Increase drain timeout to 100ms.
- Add 'o log [-n N]' to read last N lines from agent log (default 1000)
- Rename 'o tail' to 'o chatstream' for clarity
- Update TUI to show log history before streaming chat
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
Wrap bold escape sequences in \001/\002 markers so readline
correctly tracks cursor position. Fixes Ctrl+U, Ctrl+W, and
other readline kill commands after typing several characters.
- Remove auto-resolution of session/agent (was slow, unexpected)
- Path classification determines required context level immediately
- Errors are fast and actionable with clear fix instructions
- Root-level paths work without any context
- o env now just prints export statements without requiring context
Supports C-a, C-e, C-u, C-k, M-b, M-f, arrow keys, etc.
Sent prompts and slash commands are added to readline history
so up-arrow recalls previous inputs.
o kill: kills the active session.
Prompt REPL now supports slash commands:
/stop, /compact, /kill, /clear, /model X, /backend X, /cwd X, /help
Slash commands are handled locally without sending to the agent.
o tui: launches a 4-pane tmux layout with:
- chat stream (left, large)
- statewait monitor (top-right, reactive)
- spare shell with session/agent exported (bottom-right)
- prompt REPL (bottom, full width)
o stop: shorthand for 'o ctl stop' to interrupt a running agent.
Nodes in the 9P namespace can now declare alternate names (Aliases)
that resolve during Twalk but are invisible in directory listings.
Session dirs alias their immutable RunnableID(), agent dirs alias
their ID(). Clients can use session/{uuid}/agent/{uuid}/... paths
that remain valid across renames.
Changes:
- fs/fsnode.go: Add Aliases []string field, Alias() NodeOption
- fs/builder.go: findChild checks aliases via matchAlias helper
- fs/sessionfiles.go: Session dirs get Alias(s.RunnableID())
- fs/agentfiles.go: Agent dirs get Alias(a.ID())
- fs/spec.go: Add /aliases file (read-only alias→path table)
- fs/rootfiles.go: readAliases handler
- fs/lifecycle.go: buildIndex includes immutable ID in session/idx
- doc/edsl.md: Document Aliases field and behavior
- prompts: Update session/idx format documentation
The KDE GUI submodule now uses immutable IDs in all 9P paths,
fixing disconnected indicators after session rename.
session/{id}/agent/{aid}/plan → ollie-9p write
session/$OLLIE_SESSION_ID/agent/$OLLIE_UNAME/plan
UNAME is the agent's immutable ID, matching the agent directory
name. Using ollie-9p write instead of a mounted filesystem path.
plan now lives at session/{id}/agent/{aid}/plan instead of
session/{id}/plan. Moved the Leaf declaration from fs/sessionfiles.go
to fs/agentfiles.go. Updated both prompt docs to match.
Each lsp_*.meta now lives in tools/lsp/cmd/<name>/ alongside
main.go, rather than in data/tools/. The lsp-tools just target
was updated to install both the binary and its .meta sidecar.
AGENTS.md updated to document the pattern for compiled tools.
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.
skill_list and skill_load are now external shell scripts (data/tools/).
Removed from builtins: SkillList, SkillLoad, SkillActive.
Removed: toolsrv/skills.go, tools/builtin/skill.go, WithSkillsRegistry,
SkillsRegistry accessor, ListSkillsTools.
ollie-remote no longer initializes a skills registry.
The demarcation: built-ins mutate agent internals (tool schema, context
injection). Skills are just file reads — no special treatment needed.
skill_list and skill_load are now simple shell scripts that read
SKILL.md files from OLLIE_SKILLS_PATH. No built-in registry needed.
skill_load returns the file body as tool result (tier:hot, survives compaction).
skill_active dropped — model uses skill_list instead.
Logseq 2.0.1 has bug #12413 where POST /mcp always returns 400.
Switched to the REST API at POST /api which works correctly.
Requires OLLIE_LOGSEQ_TOKEN env var.
Commands: listPages, getPage, searchBlocks, listTags, listProperties,
upsertNodes, getCurrentGraph
Adds system_logs with two variants:
- journalctl (systemd hosts): unit, since, lines, grep
- dmesg (any Linux): source, lines, grep
Both declare sudo: true — privilege escalation is handled by dispatch.
Also adds OR support in match conditions: array values mean any must
pass. Combined with AND across keys:
{"binary": ["journalctl", "systemd-cat"], "os": "linux"}
= (journalctl OR systemd-cat) AND linux
Ollie Agent
Levi Neely