Agent names may contain colons (e.g., src:ollie), so slash must
be the primary separator. Colon separator is only for the rare
case where session names contain slashes.
default/src:ollie now correctly parses as:
session = default
agent = src:ollie
- Sanitize tmux session name (replace / and : with -)
- Include agent name in tmux session for uniqueness
- Quote context arg in spawned o commands
- Use colon separator for robustness
- session:agent works as alternative to session/agent
- Colon takes precedence (allows slashes in session names)
- Quoted arguments with spaces now work: o "my session:agent" prompt
- Removed set -- $* which broke quoted arguments
- Updated help with examples
Added Output sections with explicit bans on narration, hedging, and
verbose summaries to all agent-*.md files:
- author, conductor, copilot, foreman, observer, panelist, reviewer, theo
- Strengthened existing Output sections in explorer, librarian, navigator, taskmanager
All agents now have consistent brevity guidelines.
Added concrete examples of banned output patterns:
- Preambles (Great question!, I'd be happy to help!)
- Narration (Let me..., I'll now...)
- Hedging (It seems like, It appears that)
- Over-explaining and self-congratulation
- Summaries that restate what was just done
Added positive guidance: start with the answer, state task
completion in one sentence, end when information is delivered.
Models respond better to explicit prohibitions with examples than
to general instructions to 'be brief'.
Match ollie-session-here behavior: update cwd for existing agents,
not just on creation. Ensures agent cwd reflects current project root
when invoked from a different context.
- Agent cwd is optional; empty = inherit session cwd (the common case)
- Session cwd is required at creation and is the inheritance root
- toolsrv maintains agentCWD map, resolved per call from agent= field
- Override set via agent cfg (cwd=...) or ctl (cwd [<dir>|-])
- Agent.SyncCwdToToolServer re-pushes on every (re)connect
- GUI NewAgentDialog shows '(inherit: <sessionCwd>)' as placeholder
- proc_test.go covers per-agent cwd isolation
- Kate and acme scripts updated for new session/agent creation flow
- AGENTS.md documents the architecture
Agent names derived from cwd using parent:prefix format:
- /home/user/src/ollie -> src:ollie
- /home/user/proj/ABC-123_feature/repo -> abc-123:repo
Updates:
- Kate plugin: one agent per project, git root fallback if no project plugin
- acme-ollie-ensure: single 'acme' session, per-project agents
- ollie-session-here: single 'default' session, per-project agents
Also fixed write -> rdwr for session/agent creation endpoints
o sess approve [id] - approve pending, optionally verify id
o sess deny [id] - deny pending, optionally verify id
Shows request id in output: [42] approving: cmd
Errors if specified id doesn't match pending request.
Works at session or agent context (bypass is session-level).
Reads pending request from session/{s}/bypass, extracts ID,
writes '{id} approve' or '{id} deny' to resolve.
CreateEmpty now returns (session, created, error): if a session with the
given name already exists it is returned untouched instead of erroring,
and only a freshly created session receives the provided cwd/workflow/
variant. The o script no longer suppresses errors from session/new, so
real failures surface while re-creating an existing session stays a
no-op success.
Make the namespace explain itself instead of requiring prior knowledge.
- ctl is self-describing: reading it (empty write) or writing 'help'
returns the valid verbs with one-line descriptions; an unknown verb
errors with the valid list. Refactor dispatch to an ordered []ctlCmd
carrying descriptions; drop the undocumented '.' alias and the
drift-prone hardcoded help verb. Keep 'i' (drop 'inject') for fast
injects. o's ctl usage now reads the live listing.
- Errors carry severity + remediation. backend.ClassifyError maps the
typed errors to transient/config/fatal with a one-line fix; the error
event renders [[[error:<severity>]]] and a 'remediation:' line so a
human knows whether to wait or intervene.
- Add a human status file: 'thinking · 12s', 'calling shell · 3s',
'idle' — distinct from the machine-facing raw state. Wire the TUI bar
to it.
- Bare 'o' shows an overview of running sessions/agents with status, so
you don't need to know any names to get oriented.
Tests: dispatch help/unknown/routing, ClassifyError severity table.
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.
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.'
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)
- Add quirks package for stupid model behavior workarounds
- ShellInvokesNativeTool blocks shell(cmd="tool_name") patterns
- Add client_9p tool: native wrapper for ollie-9p operations
- Block ollie-9p in shell — use client_9p instead
- Update all prompts to use client_9p, not shell+ollie-9p
- Clarify 9P namespace is complete (tools are NOT in 9P)
- Registry.All() lists all available tools for validation
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.
Timeout fix:
- Add Timeout field to ToolInfo (protocol) and MetaFile (metadata)
- proc.go respects tool-declared timeout before falling back to 30s default
- subagent_spawn.meta declares timeout=0 (no timeout) so the tool is
never killed prematurely while waiting for the sub-agent to finish
- Tool schema declares timeout with 'do not set' guidance to prevent
the LLM from adding a short timeout
Premature response fix:
- Inject behavioral prefix into sub-agent prompt: complete all work
before responding, report results not intentions
- Sub-agent's final text is returned to parent; this instruction ensures
it contains accomplished work, not a plan
- runWorkflow accepts a variant parameter; sources {workflow}-{variant}.conf
as env vars before exec'ing the script
- Session stores variant; persisted and restored
- session/new accepts variant= parameter
- 'run' ctl command accepts optional variant as second arg
- workflows file now lists variants: name<TAB>default,variant1,...
- review workflow reads AUTHOR_PROFILE/REVIEWER_PROFILE env vars
- Add review-code.conf and review-writing.conf example variants
All tool logic lives in the multicall main.go at each family root.
Move .meta files to data/tools/ (single canonical location).
Expand test-core to cover all tools.
Levi Neely
Ollie Agent