Deep dives

Use these articles to understand how Agentweaver v1 works across service boundaries. Start with the system overview, then follow the subsystem that interests you. The pages describe checked-in behavior; they do not imply that a planned feature or a deployment is available.

The architecture pages explain component boundaries. The reference records contracts and endpoints. These deep dives connect those boundaries to request flow, state, and failure handling.

System and orchestration

• System overview — Trace requests, identify state owners, and distinguish history from execution state.
• Gateway — Follow authentication, allowlisted routing, browser access, and journal-backed event streams.
• Orchestration — Understand decision gates, validated WorkPlans, explicit dispatch, and recovery.
• Events and sessions — Learn how the journal, addressed messages, session material, and usage records work.
• Agent runtime — Follow runtime bootstrap, SDK turns, tool authorization, and recovery.
• MCP server — See how Gateway operations become authenticated MCP tools, and how acceptance differs from completion.

Identity, configuration, and execution resources

• Identity and secrets — Understand broker identity, purpose-bound grants, secret references, and credential redemption.
• Projects and configuration — Learn how project authority, revisioned settings, skills, and accepted run selections work.
• Environment and sandbox — Follow environment lifecycle, workspace volumes, network egress, and runtime placement.
• Providers and models — Understand provider selection, capability negotiation, resource pins, and model bindings.
• Source Control — Follow repository pins, isolated workspaces, output capture, pull requests, and approval-bound merges.

Data and operations

• Knowledge and memory — Learn how records, proposals, accepted decisions, context compilation, and Memory providers work.
• Persistence — Understand service-owned PostgreSQL schemas, object bytes, outboxes, inboxes, and retry boundaries.
• Telemetry — Learn how OpenTelemetry signals and exporters relate to durable product evidence.
• Infrastructure and deployment — Review Azure and Kubernetes source, workload configuration, images, and release boundaries.
• Testing strategy — Choose checks for service logic, PostgreSQL behavior, harnesses, and acceptance evidence.