canon(methods): add dispatch-paths — assistant-orchestrated vs autonomous-trigger

[klappy]

Adds klappy://canon/methods/dispatch-paths as a Tier-2 method naming the two dispatch classes a spawned-agent-session runtime can be invoked through.

What this PR adds

One new file: canon/methods/dispatch-paths.md (1334 words, 104 lines, 6 sections).

The two paths

• Assistant-orchestrated — an assistant (Claude, OpenCode, etc.) in a chat session dispatches a runtime invocation, waits for the result, and consumes it on behalf of an operator who is watching. engagement=assistant permitted. The skills/managed-agents/SKILL.md is the canonical implementation.

• Autonomous-trigger — an external event (webhook, queue message, alarm, object-store notification, AMS frame) wakes the runtime with no assistant in the loop. engagement=agent mandatory per klappy://canon/constraints/mode-discipline-and-bottleneck-respect. Errors emit to configured targets, not into a void. The AMS audit gate (forthcoming) is the first implementation.

Single decision rule

When the runtime returns, who reads the result first? If a human via a chat assistant → assistant-orchestrated. Anything else (webhook responder, PR comment, downstream worker, AMS subscriber, database, email) → autonomous-trigger.

The two paths are not interchangeable. Wiring autonomous-trigger but treating it like assistant-orchestrated (e.g., a persona emitting clarifying questions into a Slack webhook nobody watches) is the most common failure mode this doc exists to prevent.

Pairing with PR #198 (trigger-source-taxonomy)

This doc names the dispatch classes. Trigger-source-taxonomy (#198, drafted but pending merge) names the input edges that wake the autonomous-trigger class. Together they cover the "how does a runtime get invoked" question at two altitudes — class (this doc) and routing convention (#198).

Prior art and confidence

Prior art: messaging architecture's request-reply vs publish-subscribe; serverless platforms' synchronous vs event-driven invocation. The contribution is the specific binding to the persona-shaped runtime's engagement dimension.

Confidence: working belief, two implementations. Consistent with deployed managed-agents skill and in-design AMS audit gate. Retraction conditions stated.

Word budget

Hard cap was ~1500 words. Final: 1334 words. The trigger-source-taxonomy draft hit 5962 words against the same target; this draft was scoped tightly enough to land under-budget. Learning encoded in journal/2026-05-11-trigger-taxonomy-drafting.tsv.

Status

status: proposed. Awaits operator review.

---

Note

Low Risk
Low risk: adds a new Tier-2 canon markdown document only, with no code or runtime behavior changes.

Overview
Introduces canon/methods/dispatch-paths.md, a Tier-2 method that names and defines the two supported dispatch classes for spawned-agent-session runtime invocations: assistant-orchestrated (results consumed inline by a chat assistant, allowing engagement=assistant) vs autonomous-trigger (event-driven invocations with no assistant in the loop, requiring engagement=agent and configured error/result emissions).

Includes a decision rule/tree for selecting the path, plus guidance on expected deployment shapes and failure modes when treating autonomous-trigger flows like assistant-orchestrated ones.

^{Reviewed by Cursor Bugbot for commit 8e86fcd. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

Canon Quality — Frontmatter Schema ✅

All 40 file(s) in writings/ conform to klappy://canon/meta/frontmatter-schema.

_{Validator: scripts/validate-frontmatter.py · Canon: klappy://canon/constraints/frontmatter-validation-before-merge · Run: #133}

[github-actions]

Canon Quality — oddkit_audit ⚠️

8 finding(s) in writings/ (39 files scanned). Mode: soft.

writings/agentic-software-development.md — 1 finding(s)

Line	Rule	Occurrence	Message
242	dead-reference	klappy://writings/nothing-new-even-ai	URI does not resolve

writings/choosing-faith-not-fear.md — 1 finding(s)

Line	Rule	Occurrence	Message
203	dead-reference	klappy://writings/four-questions-that-change-everything	URI does not resolve

writings/getting-started-with-odd-and-oddkit.md — 4 finding(s)

Line	Rule	Occurrence	Message
69	legacy-link-pattern	/page/writings/the-journey-from-ai-tasks-to-ai-augmented-workflows	Use a klappy:// URI instead of /page/ path
202	legacy-link-pattern	/page/docs/oddkit/proactive/proactive-bootstrap	Use a klappy:// URI instead of /page/ path
204	legacy-link-pattern	/page/docs/examples/project-instructions-template	Use a klappy:// URI instead of /page/ path
260	legacy-link-pattern	/page/writings/the-journey-from-ai-tasks-to-ai-augmented-workflows	Use a klappy:// URI instead of /page/ path

writings/the-broken-wall-and-the-buried-talent.md — 1 finding(s)

Line	Rule	Occurrence	Message
332	dead-reference	klappy://draft-zeros/appendix-a-the-biblical-roots	URI does not resolve

writings/the-voice-came-first.md — 1 finding(s)

Line	Rule	Occurrence	Message
244	dead-reference	klappy://writings/four-questions-that-change-everything	URI does not resolve

Soft-block mode — this status is informational; the job will not fail. Hard-block ships in PR-3.2 after the observation cycle.

What to do for each finding:

• Fix the slug if the target now lives at a different klappy:// URI.
• Remove the link if it is no longer needed.
• Allowlist with a reason if the rot is intentional (e.g. forward-ref to an upcoming article): place <!-- audit-allow: dead-reference reason="..." --> on the line above the offending link. The directive is line-level and scopes to the next markdown link.

_{Spec: klappy://docs/oddkit/specs/oddkit-audit · Workflow: .github/workflows/canon-quality.yml · Run: #133}