rea/docs/specs/agent-environments

Agent environment implementation index

This index covers all 26 PRs authored by earakely-scale in morluto/rea, checked on 2026-10-25 against main 5d428390996498bc4dcca4da934641557f9109bc. Twenty-five were merged; #5722 was closed without merging. The table describes the resulting work rather than treating each original PR proposal as the current contract.

Start with the quickstart for a user workflow or the reference for current contracts. Design issue #4933 records the original four-part proposal. Its stateless replay description predates state serving and confirmed writes.

PR map

All entries are merged unless marked otherwise. Verification links point to the corresponding slice's recorded checks, with their original versions, platforms, failures, and limitations.

PR	Contribution	Verification
#4954	Project HAR Evidence into an environment manifest with inferred tool templates and explicit unknowns.	Manifest view
#4955	Add explicit streamable HTTP serving for REA MCP; stdio remains the default.	HTTP transport
#4975	Serve retained exchanges as MCP tools, with the environment card and replay data-plane stub.	Environment serve
#4999	Export authenticated capture/manifest pairs as pinned AgentEnv bundles with a verifier and smoke task.	Environment export
#5182	Accept browser-scenario Evidence as a manifest, serve, and export input.	Scenario capture
#5293	Accept Evidence-file sources for richer captures and add opt-in sibling-pair path templating.	Rich captures
#5319	Extract initial entities, documents, and checked read plans with the environment-state view.	State view
#5351	Make state serving the default; add reset/load/get operations, replay fallback, and --replay-only.	State serve
#5352	Back more read shapes with state and describe tool responses and annotations.	State coverage
#5600	Apply create, update, delete, and document effects only when later reads confirm them without contradiction.	State writes
#5664	Share inferred path positions across tools with opt-in prefix-variance, connecting literal writes to templated reads.	Prefix variance
#5699	Compare the environment offline against separately recorded probe sequences from the application.	Fidelity compare
#5722 (closed, unmerged)	Proposed independently reset recording sessions. The author closed it after six applications showed no held-out agreement gain; identified model gaps took priority.	Closure explanation
#5787	Decide whole-list membership per request line so mixed filtered/unfiltered tools can show new entities.	List lines
#5800	Learn supported list filters, substring search, sorting, paging, and counters from recordings.	List queries
#6136	Explain copied or renamed values and regenerated scalar or nested UUIDs while withholding unsupported links.	Assigned values
#6138	Preserve the clock spelling and precision each read view shows after a write.	View clock spelling
#6169	Handle bodiless write replies, proven omitted fields, projected reads, and digit-group sequences.	Write coverage
#6385	Find more state targets, distinguish read-only POSTs, and handle variant views and differing create/read paths.	State targets
#6897	Extend evidence-gated rules for bulk writes, item actions, generated values, query constraints, and ordering.	Write rules
#6929	Bound create learning and invalidate stale write proofs. The original branch also developed the one-step builder and coverage report, integrated through stacked #6946 before this PR merged.	Build workflow and verification, final PR scope
#6946	Complete the agent workflow with same-origin scenario request actions, export_environment_bundle, and recording instructions; integrate environment-build and coverage from its stack.	Environment from a prompt
#6967	Retain browser request timing so scenario-derived environments can learn write clocks.	Scenario timing
#7025	Explain composed response strings, trimmed fractional clocks, and generated integer identities.	Derived values
#7034	Learn compatible create variations across calls, sorted echoes, referenced entities, and nested view projections.	Create calls
#7080	Reconcile lighter create responses with read-backs and learn re-derived slugs and clocks in whole-object updates.	Write views

Multi-session capture fusion from #5722 is not a shipped capability. Repeated calls inside one supported capture, as learned by #7034, are a separate feature.

Evidence to use when describing the feature

The contributor's example repository contains the original capture/export/evaluation pipeline and links to published bundles. Its Grafana row records 105 exchanges and 48 manifest tools, matching the capture count in the demo. The README describes an earlier replay workflow; its counts and model scores should remain attributed to that snapshot.

The prompt workflow verification records five applications built by an agent from individual prompts: every exported bundle passed smoke, while three of the five served writes. Later timing, derived-value, and create-call work addresses specific gaps found in those recordings. The earlier write counts are not current limits.

The write-view verification records a later held-out round where 10 of 20 targeted write tools were served, up from 8. Its original census retained 132 served writes across 69 existing captures. These are source-reported measurements at the recorded revisions. The merged PR's review follow-up explicitly says its real-application census and agent tasks were not rerun after the final fixes; the local CLI/MCP regressions cover those fixes.

Smoke checks demonstrate bundle/framework compatibility for the tested configuration. Retrieval rewards demonstrate particular task outcomes. environment-compare measures agreement on recorded probes, with explicit normalizations and omissions. Keep these claims separate, and retain the version and coverage limits when quoting any result. This index is a source and PR review; it does not constitute a new real-application or benchmark run.