GitSpawn class (Sep 2026): a repo's .git/config can set core.fsmonitor to
a command that executes on any git index refresh, silently and as the
user. Ollie never spawns git in its own plumbing (repo detection is
os.Stat), but model-run git inside a malicious repo would fire it.
- exec: force core.fsmonitor=false via GIT_CONFIG_* in sandboxed tool env
- turn: wrap repo AGENTS.md in <context> markers (untrusted data,
filtered by KDE chat rendering)
- AGENTS.md: document the no-git-in-plumbing invariant (lesson 16)
Session names like 'r7.20' caused 'duplicate session' errors because
tmux interprets dots as window.pane separators.
Fix: Use '=' prefix for exact match in all tmux -t arguments.
From tmux(1): 'If the session name is prefixed with an =, only an
exact match is accepted.'
Implement proper Plan 9/Acme mouse chording in the input area:
- B1 = select (TextArea default)
- B2 = execute selection as prompt
- B3 = plumb selection or context menu
- B1+B2 = cut (chord while selecting)
- B1+B3 = paste (chord while selecting)
Uses MouseArea overlay that detects when B1 is held while B2/B3
is pressed to trigger chord actions. Context menu items now show
the chord shortcuts (Cut B1+B2, Paste B1+B3).
Placeholder text shows the mouse action reference.
- Remove chatPane property from delegate (was shadowing id, causing binding loop)
- Remove contentArea MouseArea from inside Column (invalid anchor)
- Simplify hovered property to use only headerArea
- Edit button now copies to clipboard instead of trying to access chatPane
Add table rendering support to ChatBlockModel:
- isTableLine(): detect pipe-delimited table rows
- renderTable(): convert table lines to HTML <table>
- renderProse(): split prose into text/table segments
- incrementalAppend: handle table state transitions during streaming
Tables render with header row detection (before |---|---| separator)
and proper incremental updates as content streams in.
Add per-model pricing to /models output. Format:
backend<tab>model[<tab>in<tab>out<tab>cache_read<tab>cache_write]
Pricing sources:
- Anthropic: hardcoded from official pricing, includes cache rates
- OpenRouter: parsed from API response pricing field
- Other backends: static lookup table fallback, marked with (e)
Changes:
- backend: Add ModelPricing/ModelInfo types, ModelLister interface,
static price table (Claude, GPT, Gemini, DeepSeek), LookupStaticPricing()
- openai: Parse pricing from API, implement ModelsInfo()
- anthropic: Implement ModelsInfo() with hardcoded cache rates
- fs/cache: Use ModelsInfo when available, fall back to static lookup,
format prices per 1M tokens with (e) suffix for estimates
- agent/cost: Use shared LookupStaticPricing instead of duplicate table
Add a ▶ button next to the text area for mouse-based submission.
Extract shared doSubmit() on the input RowLayout. Button uses
focusPolicy: Qt.NoFocus so it doesn't steal focus from the TextArea.
Replace MouseArea overlay with TapHandler inside TextArea.
The MouseArea sat on top and intercepted left-button press events,
blocking click-and-drag text selection. TapHandler cooperates with
the TextArea's built-in selection handling.
The old word-boundary check falsely triggered when tool names appeared
in arguments (e.g., git commit messages mentioning native tools).
New logic: split on shell separators and only flag when a tool is the
first token of a sub-command or a path ending with /toolname.
Allows user to background the current foreground tool process
by writing 'detach' to the agent ctl file. The agent can then
continue working without waiting for the tool to complete.
embedding/embedding.go:
- Remove EmbedBatch() (never called in production, test updated to use Embed)
- Remove padID field (written but never read)
embedding/index.go:
- Remove Index.mu mutex (Index is immutable after construction)
skills/skills.go:
- Remove Index.All() (never called)
- Remove Index.Reload() (never called)
virtfs/decl.go:
- Remove RemoveNode() NodeOption (never used)
- Remove RenameNode() NodeOption (never used)
- Remove Alias() NodeOption (aliases set directly on struct)
virtfs/tree.go:
- Remove Tree.Data field (never used)
- Remove Tree.Mount() (never called in production)
- Remove Tree.Child() (never called in production)
- Remove Tree.Children() (never called in production)
- Replace indexOf() with strings.IndexByte
Tests updated to directly manipulate internal children map where needed.
Ollie's core is feature-complete. Every capability (browser automation,
audio, RAG, scheduling, databases, external services) is achievable by
writing a tool. There are no architectural gaps — missing features are
missing tools.
Each('peer', ...) creates a named directory whose children come from
Bindings(). Previously, listDir and findChild only checked Bindings
for template names like {foo}. Now they also handle directories that
have Bindings but no Children.
This fixes the peer/ directory in olliesrv which was listing empty
even though peers were configured via peeradd.
Added test for the non-template Each pattern.
When the 'agent <profile>' ctl command switches profiles, the tool
registry now clears old tools and loads the new profile's autoLoad
list. Previously, switching profiles left the old tools loaded.
Changes:
- registry: add ClearAgent(agentID) to remove all tools for an agent
- server/proc: add ClearAgent wrapper and 'clear <agentID>' ctl command
- toolclient: add ClearTools() method to ToolsrvConn
- agent: SwitchProfile now returns *AgentConfig for tool reload
- fs/spec: agent ctl handler clears and reloads tools after switch
Remove lazy tool loading (load-on-call). Tools must now be explicitly
listed in the agent's autoLoad config. Calling an unloaded tool fails
with a clear error message.
Package structure improvements:
- embedding/index.go: generic Index type for semantic matching
- skills/skills.go: uses embedding.Index internally, keeps Skill type
- agent/skill_match.go: matchSkills() for skill discovery
- agent/tool_match.go: matchTools() for tool hints (new file)
Tool hints now match only loaded tools, not all tools on disk.
This makes agent capabilities explicit and auditable.
Add semantic skill matching using all-MiniLM-L6-v2 sentence embeddings.
Skills are automatically injected into user turns based on relevance.
New packages:
- embedding: ONNX-based text embedding with MiniLM model
- skills: skill discovery, embedding cache, and semantic matching
Integration:
- InitSkillIndex called at startup in fs.NewRoot
- matchSkills called per-turn in executeTurn
- Matched skills injected in <context> block alongside user prompts
Makefile:
- install-models target downloads model and ONNX runtime
- Model files stored in ~/.local/share/ollie/models/
Config:
- Threshold: 0.2 cosine similarity
- Limit: 3 skills per turn
- Skill dirs: ~/.kiro/skills (user), ~/.config/ollie/skills (installed)
Ollie Agent
Levi Neely