Skip to content

docs(spec): draft AgentEx subsection for SGP service decomposition ERD#247

Closed
smoreinis wants to merge 6 commits into
mainfrom
agentex-erd-section-design
Closed

docs(spec): draft AgentEx subsection for SGP service decomposition ERD#247
smoreinis wants to merge 6 commits into
mainfrom
agentex-erd-section-design

Conversation

@smoreinis
Copy link
Copy Markdown
Collaborator

Frames the AgentEx backend as a smaller monolith to decompose in mirror of the parent ERD: agentex-state and agentex-conversations extracted as Go services (high-write, latency-sensitive), agentex-tasks as Python, agentex-control-plane as the residual after the three extractions. Includes a committed-conditional Mongo->Postgres evaluation, sequencing, and four open questions.

smoreinis added 6 commits May 22, 2026 15:16
Frames the AgentEx backend as a smaller monolith to decompose in mirror
of the parent ERD: agentex-state and agentex-conversations extracted as
Go services (high-write, latency-sensitive), agentex-tasks as Python,
agentex-control-plane as the residual after the three extractions.
Includes a committed-conditional Mongo->Postgres evaluation, sequencing,
and four open questions.
… exists

PR #146 already established the HTTP checkpoint boundary: the SDK calls
the backend's /checkpoints/* endpoints via HttpCheckpointSaver rather
than connecting to Postgres directly. When agentex-state becomes a
separate Go service, the boundary exists today -- the Go service just
needs to serve the same contract. Renumber remaining open questions
(down to 3).
The SDK already accesses task lifecycle, messages, task states,
checkpoints, events, and agent registration through HTTP endpoints
rather than direct database connections. Surface this as a general
property in the Solution Statement, and expand the agentex-state and
agentex-conversations bullets to reflect that the contract exists for
states and messages, not just checkpoints.
…ut to notes

Replace two open questions with concrete content. The boundary with
sgp-agent-deploy is now spelled out in a dedicated Boundaries section:
sgp-agent-deploy ends at "pod running" (build artifact + Flux CRD),
agentex-control-plane begins at agent self-registration; permissions
are deploy-time vs runtime-credentials. Checkpoint lift-out becomes a
forward-looking note rather than an open question -- something to
revisit as LangGraph usage grows. Open Questions reduces to the one
genuinely undecided item (agentex-auth/sgp-identity via OneAuth).
OneAuth fold-in is a longer-term consideration, not a blocking decision
for this ERD section. Move the awareness to Forward-looking notes
alongside the checkpoint lift-out trigger, and drop the Open Questions
section entirely.
Six discrete tasks: internal AgentEx team review, sgp-agent-deploy
boundary sign-off, OneAuth heads-up, mini-ERD location decision, paste
catalog bullets into parent ERD, announce. Coordination work rather
than software implementation -- subagent-driven and inline-execution
sub-skills do not apply.
@smoreinis smoreinis closed this May 22, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant