Macro is a unified workspace for teams: email, chat, docs, tasks, agents, calls, and CRM — @-linked together with shared AI memory.
agent_inmem
What it is
Part of agent sessions: the lightweight alternative to agent_harness's
sandboxed containers — serves the agent side of ACP in-process, running
the same agentic loop behind the same ACP contract, so a session starts in
milliseconds instead of waiting on container provisioning.
Start here
src/rig_engine.rs:RigTurnEngine— the production composition root, runs one turn overagent::AgentLoopand the Macro toolset.src/domain/engine.rs:TurnEngineport — the seamrig_enginefills.src/outbound/manager.rs:InMemAgentManager— provisions per-session agent tasks, implements the container-manager port the harness expects.src/domain/tool_stream.rs: throttled, bounded argument previews for pending calls; replay ignores previews and retains only calls that began execution.src/domain/session.rs/src/domain/replay.rs: in-process session state and log replay on reconnect.src/domain/admission.rs+src/outbound/approval_gate.rs: usage/plan admission and tool-approval gating for in-memory sessions.src/domain/model_access.rs(SessionModels) andAgentState::turn_agent_key: an agent with its own usable API key (agent_api_keys) runs every turn on it without admission, and its session offers only that provider's models.
Scope
- Owns: running the agentic loop in-process behind the same ACP contract as the sandboxed harness, so session log/fold/UI code is runtime-agnostic.
- Not here: sandboxed container sessions →
agent_harness; the ACP wire shapes themselves →agent_runtime_protocol.
Boundaries
- Depends on:
agent(the turn loop),ai_toolset,agent_egress(egress_mcp.rs),ai_billing,ai_usage. - Used by:
agent_harness_service(its sole host, alongsideagent_harnessfor sandboxed sessions).
Recipes
- Add compaction/summarization behavior:
src/domain/engine.rs→src/rig_engine.rs. - Add a new tool gate or admission check:
src/domain/tool_gate.rs/src/domain/admission.rs→src/outbound/approval_gate.rs.
Native user tools bypass the ordinary gate only when the final-draft review finisher is installed; otherwise dispatch must resolve their actor normally.
Session tool schemas require acting_as: requester | owner for tools using
account access, including deferred tools. The gate resolves the selected account
through TurnPrompter::acting_user() and requests owner approval only when that
account differs from the turn's requester. System invocations have no requester.
Reviewed user tools retain the selection through confirmation and execute with
that account. Billing, memory, and session lifecycle remain owner-scoped. Model-context replay
retains notification ACP inputs and their replies; the transcript fold separately
omits system input from its message projection. PresentReview, GetReview and
DecideReview are eager internal tools in both standard and code modes.
- Owner memory is composed by the memory domain on each read; daily generation is hosted by cognition, not agent turns.
Checks
cargo test -p agent_inmem(SQLX_OFFLINEunset).
Gotchas
- Owners with
auto-skills(domain::entity_routing) route SDK entities on code-mode turns: the prompt isrouted_prompt(no area guidance) and the entitiesselect_documentationpicks bring their@agentguide with their index into the turn part. Everyone else keepsprompt, which inlines every guide. autois a picker entry, not a routable id:RigTurnEngineasks itsAutoModelSelector(Jev through cognition's named decisions, 1 s budget) per turn and runs Opus 5.5 (hard), GPT-6.1 Sol (mid) or Gemini 3.8 Flash (simple, and whenever Jev is unavailable). Capability lookups go throughmodels::resolve.- Owners with the
auto-skillsflag route each turn's request to their skills (skills::domain::selection, Jev, 1 s). Loaded skills are appended to the user message that loaded them in the model's copy only, and remembered per session inSessionSkills(memory; lost on restart). Eval:route_evaluation(ignored; needsTYPESAFE_API_KEY). - Keep session-aware
NameSearch,ContentSearch, andListEntitiesnative in code mode; legacyReadChatmust not appear in either runtime tool catalog. - Every turn cuts tool results over
agent::ToolResultLimit's limit (about 25k tokens) for the model and offersReadToolResultto page through them. The stream, log and history keep the whole result; replay cuts it again, so build turn messages withto_rig_messages_limited, notto_rig_messages. rig_engine::system_promptorders text from most to least stable for the prompt cache: the static Macro prompt (the cached shared block, the same for every agent), then the session's part, then the turn's (with_turn). Put anything that changes per turn in the turn part, never in the shared block; measure withmeasure_prompt_cache_turns.- Replay tool calls using
_meta.macro.toolName; ACP titles may be human-readable MCP labels, so only use the title for older frames without tool-name metadata.
Related
- Rules:
.agents/rules/rust/architecture.md