Adds DR-3 to the v4 r1 plan and rewires §1 + §23 to reflect that the v0.x
release line ships zero Temporal code.
Rationale (DR-3 detail in §22):
- v3 and early v4 r1 drafts had Temporal as the canonical durable-workflow
layer (M5-Py). For 1-user 1-machine CLI/REPL/web-GUI workloads, the same
durability guarantee is reachable with (1) LangGraph AsyncPostgresSaver
(already in deps after v0.2 PR #1) + (2) RunPhaseRow / LlmCallRow state
machine per-commit (already in models) + (3) sweep_orphan_runs at startup
(already in recovery.py).
- Temporal server + worker + deterministic-workflow rules are weight without
proportional payoff at this scale. The decision becomes meaningful only
when v1.0 introduces multi-tenant / multi-machine fanout.
- temporalio NOT added to my-deepagent/pyproject.toml. No apps/worker/.
Patches:
- §1.7 (new): "Workflow Orchestration: NOT USED in v0.x. Deferred to v1.0
multi-tenant ADR (DR-3)." Explains the LangGraph + DB + sweep replacement
path and points at §23 for the v0.2 sequencing.
- §22 DR-3 (new): full decision record with rationale, scope, and the
supersede statement against earlier "M5-Py: Temporal worker NEXT" wording.
- §23 v4 kickoff matrix:
- v0.2 PR #1 row → DONE (e21a524).
- v0.2 PR #2a (new): LangGraph AsyncPostgresSaver engine wiring.
- v0.2 PR #2b (new): `mydeepagent runs resume <id>` real implementation.
- v0.2 PR #3 (new): FastAPI + SSE + minimal Web GUI.
- M5-Py → DEFERRED to v1.0+ per DR-3.
- M8-Py → absorbed into v0.2 PR #3 (no separate apps/api dir; FastAPI
lives inside my-deepagent/src/my_deepagent/api/).
Open question (recorded in DR-3): v1.0 ADR will compare Temporal vs Hatchet
vs in-house Postgres-based workflow runner.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
711d61d245