Agent Platform · work tracking proposal

One framework, many agents — the work, mapped

A proposed Linear shape for the TS agent platform: the planning spike, what shipped in the first pass, and the upcoming work — drawn as a dependency graph that separates what I'm driving (the core spine) from what's open for someone to help with, flagging which open pieces are independent and startable now.

01Where it lives

No existing LEX project fits. Lawrence 2.0 MDP is launch-polish (Sedona), Skills MDP is product-scoped, the rest are features. This is platform/enablement work — a framework anyone builds agents on — so it deserves its own home.

Proposal: new Agent Platform project (LEX team, lead: Adolfo). Holds the framework + capability-sequence work, distinct from the Lawrence-2.0 product projects. Can roll under the existing “Lawrence 2.0” initiative for now, since full Lawrence-2 TS migration is the headline payoff. The skills-migration ticket also cross-links to Skills MDP.

02The tickets

Six tickets, not one-per-PR. The 11-PR stack collapses into one framework-core ticket; observability is its own (last PR) with a deferred follow-up; the spike carries all the docs and decisions; then four upcoming pieces.

Shipped / in review

Spike: agents-backend capability sequenceLEX-646planningmine

The umbrella planning + decision record. Description carries all the architecture docs; progress tracked as comments. Keep as the single place the thinking lives.

Framework core (Cap-01 + Cap-02)in reviewmine

The keystone: generalised agent API (route by slug, optional matter), defineAgent builder, sealed registry, model-provider registry, run + chat transports, plus the two trial agents and a dev dogfooding switch. The whole stack in one ticket.

Langfuse observabilityin reviewmine

Agent runs trace to the dedicated agents Langfuse project via the AI SDK v7 telemetry integration: generation + tool spans, prompt-version link, environment (local/dev/prd), and per-agent metadata. Last PR of the stack.

Spawns: the deferred instrumentation ticket below.
Deferred: richer agent instrumentationbacklogopenindependent · startable now

First pass deliberately uses the default AI SDK instrumentation to keep complexity down — it isn't yet at the level of the Python agent (custom span shaping, trace naming, tags, session/user attribution). Follow-up: post-run trace naming/tags and richer spans toward Python-agent parity.

Depends on: Langfuse observability.Coupling: low — can run any time, by anyone.

Upcoming

Generalise the VFS for non-matter namespaceslateropen · downstream

The VFS is matter-scoped (matterId from context). Generalise to firm-scoped namespaces and a matter-creation namespace (create a matter, not just read within one). Scope resolves from the now-generalised thread.

Depends on: VFS reshape + thread generalisation.
Port production tools: Python → TSlatermine

Migrate the live tools (search, create, edit, citations…) from the Python agent framework into the TS framework — the unlock for running full Lawrence 2 on the TS platform. Parallelisable per-tool once the new VFS shape lands.

Depends on: framework core + VFS reshape (+ non-matter namespaces for some tools).
Migrate static skills → TS frameworklateropen · downstream

The static skills currently living in the Python repo move to TS defineAgent definitions. Composes the migrated tools.

Depends on: framework core + tool migration.Cross-link: Skills MDP.

03Dependency map & what's open to parallelise

Top lane is the core spine I'm driving; bottom lane is open for someone to help with. Left-to-right is dependency order, and green-dotted nodes are independent — startable now (they only need work that's already shipped, so they don't wait on my active track).

shipped / in review next later independent · startable now depends on spans core ↔ open
What's open to help with: the two green-dotted ones — generalise threads and the deferred instrumentation — are independent and could start today without blocking on my core track. Non-matter VFS namespaces and the skills migration are also open but downstream: they unblock once the core spine (VFS reshape, then tool migration) lands. I'm not assigning anyone yet — just flagging what's grabbable.

04Open questions to settle

#QuestionLeaning
1New Agent Platform project, or fold into an existing one?New project, under the Lawrence 2.0 initiative.
2Relabel LEX-646 away from “Spike”, or keep the label for cycle history?Keep LEX-646; enrich description, log progress as comments.
3Do the upcoming four want point estimates / a target cycle now?Estimate the two “next” ones; leave “later” unsized.
4Which open item do we want picked up first?One of the two independent ones — generalise threads or deferred instrumentation — since neither blocks on my core track.