Session.Submit now forwards directly to Agent.Submit. Slash commands
are agent-level concerns handled by Agent.HandleCommand.
Session-level operations (save, resume, kill, rename, cwd) are ctl
verbs issued via the ctl file — they are NOT slash commands and do
not flow through the prompt path.
This eliminates the artificial session/agent command routing and
makes the prompt path clean: everything in the prompt goes to the agent.
Agent is now in ollie/agent with proper encapsulation:
- Unexported fields, exported methods as the API
- Own constructor (agent.NewAgent)
- Owns: turn execution, history, runtime, hooks, commands, compaction
- Session never reaches into agent internals
Session (ollie/session) is a thin host:
- Owns: persistence, session ID, env, detach delegation
- Delegates all agent operations through exported Agent methods
- handleCommand dispatches to agent.HandleCommand for agent-level commands
Agent-level commands (/model, /backend, /compact, /agent, etc.) live
in agent/commands.go and access internals directly (same package).
Session-level commands (/sessions, /save, /resume, /cwd, /help)
remain in session/commands.go.
Test files temporarily removed pending rewrite against new API.
The fifo_test.go passes as a sanity check.
Agent now owns the full turn lifecycle: Submit, executeTurn, turnError,
autoCompactLimit, autoWarnLimit, spawnContext, and runCompact all live
on *Agent in turn.go.
Session.Submit is a thin dispatcher: slash commands are handled at
session level (they need sessionsDir, listHandlers, etc.), then
non-command input is delegated to Agent.Submit.
Session.IsRunning and Session.Interrupt delegate to Agent methods.
turnError is an overridable func field on Agent (default: hook-based
implementation in defaultTurnError). saveSession and flushSave are
injected as callbacks from Session into Agent at construction time.
This completes the agent/session ownership separation for the turn
execution path. The Agent is now a self-contained entity that can
run turns independently given its injected dependencies.
Agent now holds all dependencies needed to run turns independently:
bus, log, auditLog, sessionID, startupMessages, readPlanStep, saveSession.
emit() moved to Agent. Session no longer owns startupMessages/readPlanStep.
- uname is the agent's principal/UID, not a session property
- peers removed entirely from core: the concept needs redesign for
multi-agent. The 9P layer retains its own inter-session routing
at the Manager level.
Core Session now holds only: id, bus, env, plan, prevPrompt.
Agent holds all execution + identity state.
Agent now owns all execution-related state:
- cwd: the directory the agent operates in
- fifo: prompt queue (prompts target a specific agent)
- submitMu: serializes turns for this agent
- toolCallCount: per-agent tool usage metric
- pendingInject: injection targeting the current agent
Session retains only environment state: identity, bus, env, plan, peers,
persistence. This completes the agent/session state separation.
Agent now owns its execution state (state, reply, stateMu, changeMu,
changeCond). Session delegates State()/Reply()/WaitChange() to Agent.
This is the correct ownership: each agent has independent execution
state. In multi-agent, agents can be idle/thinking independently.
Session remains the coordination layer.
Programmable test backend that satisfies Backend interface without
network calls. ChatStreamFunc can be set to control behavior
(blocking, custom responses, errors).
- Session.Agent() returns the active *Agent
- Agent.Name(), Agent.BackendName(), Agent.ModelName() — first-class
- Session proxy methods delegate to Agent
Consumers can now access the agent directly:
sess.Agent().Name()
sess.Agent().BackendName()
The Session struct is defined in session.go — named after what it is.
No more 'harness' concept; that was an artifact of the interface+impl
pattern we removed.
Session is now an exported struct with unexported fields.
Methods ARE the API — no interface declaration in the package.
Consumers that need mockability define their own interface
(implicit satisfaction, standard Go pattern).
The agent/ package is now session/ — because a session is the
top-level concept. The package contains:
- harness: implements Core, the session orchestrator
- Agent: the reasoning entity (history, runtime, tools)
- History: conversation accumulator
- Fifo, loop, compaction, hooks, commands
The old session/ package (which just held extracted fields) is
dissolved back into the harness. One package, clean ownership.
The harness is the Core implementation that wires a session.Session
to an Agent and drives execution. A session has a harness; the
harness runs the agent.
The struct that implements Core is the session host — it owns a
session.Session and an Agent, orchestrating their interaction.
Renaming makes the architecture self-documenting:
sessionHost (implements Core)
├── sess *session.Session — runtime environment
└── agent *Agent — reasoning entity (swappable)
The inner struct that holds agent-specific state (history, runtime,
backend, tools, hooks) is now called Agent — because that's what it
is. A session owns an Agent; the Agent performs reasoning within
the session's environment.
Extend the core session with fields that are genuinely session
concerns currently duplicated in 9p/session:
- Plan (markdown checklist, survives compaction)
- PrevPrompt (last submitted prompt text)
- Peers (bidirectional session links)
The 9p/session layer can delegate to these in a future change.
Move agent-specific fields into a nested 'reasoning' struct:
- history, runtime, cfg (per-turn params)
- agentName, agentsDir
- baseLayers, promptEnvExtra
- newDispatcher, newBackend
- currentAction, warnedContext, resultCache
The agent struct is now the session host (owns sess + reasoning).
On /agent swap, a new reasoning can be built from the new config
while the session (identity, state, bus, env) remains stable.
The agent struct receiver was historically 's' (from when it was
called 'session'). Now that session is a separate concept, rename
to 'a' to match the type name.
Defines Session (ID, CWD, state, env, bus, FIFO) as the runtime
environment that hosts an agent. This is the foundation for separating
session concerns from agent reasoning concerns.
The Session type in agent/ is purely a conversation accumulator
(message history, token tracking, compaction state). Rename it to
History to free up 'Session' for the runtime environment concept
in the upcoming agent/session split.
- Client sends OLLIE_SESSION_ID in the request JSON payload
- Broker denies requests with no session identity
- Broker denies requests for sessions that don't exist
- Remove dead SO_PEERCRED logic (client is same process, useless)
- Remove allow-unknown bypass from checkTurnLimit
Adds a per-session burst counter that limits elevation requests to 3
per agent turn. Resets on the next user prompt submission.
Rate-limited requests get a distinct error message:
elevate-broker: rate-limited (max 3 per turn)
This guards against runaway agents flooding the notification daemon
(D-Bus is the least robust transport for this).
- executeElevated: add 3-way select (frameCh/ctx.Done/detachCh) so manual
detach works for elevated processes. Previously the default branch called
readFrames synchronously with no way to receive the detach signal.
- README: replace execute_code references with shell, update tool description
to match current single-command interface.
- Add WatchAgent constant to WaitChange fields
- Add WatchAgent case in WaitChange read() function
- Call notifyChange() in /agent command after setting agentName
This enables the D-Bus adapter to detect agent changes and emit
ConfigChanged signals so the GUI can refresh the session list.
Ensures every Server created by the dispatcher factory has registries
wired at construction time, fixing intermittent 'no session registry'
errors from tool_load/skill_load.
Previously, the Output callback set state to 'thinking' on every tool
event (including streaming chunks), so the state flickered immediately
away from 'calling:'. Now:
- Tool events no longer trigger setState('thinking')
- The loop emits a 'state' event with 'thinking' at the top of each
iteration (before calling the backend), which is the correct time
to transition.
- New 'state' event role in Output callback for explicit state transitions.
This keeps the detach button visible in the GUI during tool execution.
Re-adds the detach boolean to the shell tool args. When true, the
process is immediately backgrounded and its PID returned. This was
removed in the simplification commit 2c36c02 but is needed for
long-running commands (builds, servers, etc).
The elevation broker protocol doesn't support stdin piping.
When a promoted tool runs elevated, wrap the command as:
cat <<'OLLIE_EOF' | /path/to/tool
{json}
OLLIE_EOF
This ensures elevated tools receive their JSON args.
- callPromotedTool now pipes raw JSON object to tool stdin instead of
unpacking positional args. Tools parse their own input.
- Default schema changed from positional array to empty object.
- Registry.Discover() skips files without ollie:prompt marker.
- Registry.Summaries() and Loaded() return sorted results (both
tools and skills registries).
Levi Neely
ollie