byre/TODO.md

Bugs

M1 — One agent end to end

M2 — Seeing the work

M3 — Second vendor and review

M4 — Merging and history

M5 — Workflows

• Workflow definitions and storage A workflow is a sequence of stages, each with a role prompt template, a vendor and model, typed artifact inputs and outputs, an optional gate, and optional review profiles. Definitions, prompt templates and review profiles live on the server, not in repos, and export and import as files. A task freezes its workflow definition at intake, so later edits to the workflow don't change running tasks. No general DAG engine until a real workflow needs one.
• Stages, gates and bounded loops Gates are human approval through the inbox, a review pass or an eval pass. Loops are bounded, for example on_fail: { goto: build, max: 3, then: escalate }.
• Plan artifact A versioned artifact with goal, approach, steps, acceptance criteria, risks and open questions. Humans edit it through the inbox; agents propose edits, which go to the inbox for approval. Stored on the server and attached to merges with git notes, never committed. A plan-conformance review profile compares the diff with it.
• Eval stages Report pass or fail per acceptance criterion of the plan.
• Task intake Pick a workflow, fill its inputs (a brief, attachments, linked GitHub issues, handoff bundles from other tasks), and optionally override vendors, models, prompts or review profiles per stage.
• Mid-task swapping of stage vendors, models, prompts and review profiles At any point a human can swap a stage's vendor, model, prompt or review profiles, and add, remove or reorder the stages of the task's frozen workflow.

M6 — Fan-out

• export_context and handoff bundles An export_context(purpose) MCP tool producing a bundle with the goal, decisions made and why, current state, dead ends tried, open questions and relevant files. Used for cross-vendor forks, stage-to-stage handoff, and the durable record of a task. Compaction already writes the same contents.
• Cross-vendor handoffs Forking a snapshot into a different vendor: the new session starts from a handoff bundle from export_context instead of the vendor's native fork, and the UI labels it a handoff, not a true fork. Same-vendor forks from a snapshot exist (see "Forking" in docs/operations.md).
• Fork-and-compare A fan-out of N forks with different vendors or prompts from one snapshot, followed by a judge stage that produces a comparison with visuals.
• Just-in-time fan-out spawn_stages(stages[]) and collect(stage_ids[]) MCP tools let agents build workflows on the fly, using the same stage definition format. An optional per-workflow human gate on spawning. Spawned stages show in the task's UI tree marked as just-in-time, and a just-in-time structure can be saved as a reusable workflow.

M7 — Inbox triage

• Inbox triage agent An agent that answers questions resolvable from the repo or docs and escalates the rest with its reasoning attached. Tune it on real inbox data.