# Agent environments from recorded captures For a first environment, start with the [quickstart](agent-environments-quickstart.md): record an app or use a saved session, build and run the environment, and add tasks and reward checks. The [implementation index](specs/agent-environments/README.md) links the contributing PRs and their verification records. This page is the detailed command and behavior reference. Use `rea environment-build` to turn one recorded capture into an agent environment bundle in one offline step: a folder `agent-env run` builds and runs, whose MCP server answers from what the capture observed. See [Build a bundle in one step](#build-a-bundle-in-one-step). The steps it composes are separate commands too. `rea environment-serve` serves an environment manifest as an agent environment: an MCP server whose tools answer from what one retained web network capture observed, plus the environment card the agentenv framework reads to discover it. By default the server derives the [state the capture observed](#the-state-a-capture-observed) at startup and answers read tools from it, and the write tools whose effect the capture confirmed by changing it; `--replay-only` replays the capture's records instead. Nothing is fetched from the recorded application; every answer comes from retained Evidence. `rea environment-export` writes the same pair as a bundle folder; see [Export a bundle](#export-a-bundle). ```sh rea inspect-web-network-capture /absolute/session.har har --format json > capture.json rea inspect-analysis-view view.json --format json > manifest.json rea environment-serve manifest.json --evidence capture.json --port 8765 ``` The first command inspects the capture; the second projects the [environment manifest](web-network-captures.md#environment-manifest) view from it, where `view.json` wraps the capture Evidence as the inline source: ```json { "source": { "kind": "inline", "evidence": { "evidence_id": "ev_…" } }, "view": { "kind": "environment-manifest", "template_rules": ["after-uid-literal", "opaque-token", "sibling-variance"] } } ``` The third command serves that manifest from the state it derives from the capture; see [Serve from the state](#serve-from-the-state). Both served files are complete REA Evidence JSON as the commands write it with `--format json`; the `evidence` member of `view.json` is the whole of `capture.json`. A `view.json` can also name the capture file as `{"kind": "evidence-file", "path": "capture.json"}`, which projects it as retained Evidence instead of charging the whole capture as inline input. ## Build a bundle in one step ```sh rea environment-build grafana.har ./grafana --json agent-env run ./grafana ``` `rea environment-build [directory]` takes a `.har` file, or capture Evidence JSON from `inspect-web-network-capture` (HAR) or `capture-browser-scenario`, and writes the bundle [Export a bundle](#export-a-bundle) describes. It inspects a HAR as `inspect-web-network-capture` does (Evidence input skips this), projects the environment manifest from that Evidence as retained Evidence, authenticates the pair, prepares the state the bundle's server derives at startup, and writes the bundle with the export. For the same capture path, every file it writes is byte-identical to what `inspect-web-network-capture`, `inspect-analysis-view` and `environment-export` write, Evidence ids included, when `view.json` lists the same rules in the views' order and the export is given the build's name. It reads one file and writes one folder: it fetches nothing and launches no browser (HAR inspection runs REA's own decoder process), so record a browser scenario with `capture-browser-scenario` first and pass its Evidence. Other capture formats are refused, as the manifest view refuses them, and a HAR document saved as `.json` is refused with a hint to name it `.har`. - `--template-rule `, repeated, replaces the default opt-in rules `after-uid-literal`, `opaque-token`, `sibling-variance` and `prefix-variance`, the rules the published capture-built environments use; `--format-rules-only` applies none, the views' own default. Rules apply in the views' fixed order, the report lists them, and a repeated rule is refused as the views refuse it. - `--name` names the env folder and env id. Without it the name is the manifest's, unless the capture's origin is a loopback name or an IP literal: the capture file then names it (`grafana.har` and `grafana.capture.json` become `grafana`) and a `name-from-file` warning says so. A file name that yields no portable label (kebab-case, at most 63 characters for a DNS service label, not a Windows device name or a label interpreted as an IP address) is refused; pass `--name`. - `--package-tarball` works as for the export, and `--capture-timeout-ms` as for `inspect-web-network-capture`. - `--dry-run` runs every stage and prints the report with `status: "planned"` and the files a build would write, but writes nothing and does not check the directory, which may then be omitted. It reads and hashes a `--package-tarball` as a build does before copying it, so it refuses the tarballs a build refuses, including one whose contents cannot be read. The directory must be absent or empty, as for the export; the build never replaces a folder. A refusal before the write leaves nothing behind. A capture Evidence file, an inspected HAR's Evidence and the projected manifest must each fit the live heap headroom for parsing and sealing, checked before the file is read or the Evidence serialized; one that does not is refused as `resource_constraint`. Each refusal names its stage: `environment-build` for the build's own checks, `inspect_web_network_capture` and `inspect_analysis_view` for inspection and projection, `environment-export` for the bundle. SIGINT cancels the build (`cancelled`); before the bundle stage nothing is written, and a cancellation during the write names the bundle it wrote. Stage progress is logged to stderr at info level; the report is the only output on stdout: ```json { "status": "built", "directory": "/work/grafana", "name": "grafana", "capture": { "evidence_id": "ev_…", "operation": "inspect_web_network_capture", "records": 105, "input": "har" }, "manifest": { "evidence_id": "ev_…", "tools": 48, "excluded_groups": 0, "template_rules": [ "after-uid-literal", "opaque-token", "sibling-variance", "prefix-variance" ] }, "state": { "served": true, "evidence_id": "ev_…" }, "coverage": { "reads": { "state": 36, "recorded": 6, "recorded_reasons": { "query-varies": 3, "…": 1 } }, "writes": { "served": [{ "tool": "delete_folders_by_uid", "effect": "delete" }], "withheld": [ { "tool": "post_folders", "effect": "create", "reason": "unconfirmed", "hint": "No later read showed the effect. Read the entity and its list after the write.", "exemplar_ordinal": 94, "contradicted_by": null } ] } }, "tool_count": 37, "package_source": { "kind": "registry", "specifier": "rea-agents@…" }, "files": [{ "path": "README.md", "bytes": 4210 }], "warnings": [{ "code": "name-from-file", "message": "…" }], "next": ["agent-env run /work/grafana"] } ``` `coverage` is the state's read views and write plans summarized, and `null` when the state is unavailable and the bundle serves replay. The [environment coverage](web-network-captures.md#environment-coverage) view reports the same summary for any capture without building, so an agent can check it after each recording. The view summarizes the state as derived; it does not apply the serve-time admission checks, so for an environment whose served catalog exceeds the discovery budget, or whose state exceeds what `data/add` loads, it still reports the state while the build reports `coverage: null` and the bundle serves replay. Each withheld write carries a hint about what to record next; hints never change what is served: | Reason | Hint | | --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | `no-state-target` | The write's path names no collection or item the capture reads. Read the collection or item it changes. | | `no-call` | No recorded call of this tool was modelled, for example because every call failed. Record a successful call. | | `body-unusable` | The retained request or response cannot be modelled. Record a successful call with a complete supported request and reproducible response. | | `no-observation` | Nothing showed the entity or document this write changed. Read a created entity back by id right after the write; for an update or delete the state must already hold the entity, so read it before the write or record the create that made it. | | `unexplained-change` | The write changed fields it did not send, in a way no rule explains. A second, different call of the same tool can show the pattern. | | `contradicted` | A later read disagreed with the modelled effect. Check the read at contradicted_by. | | `side-effect` | The write changed something besides its own entity, which the environment does not model. | | `unconfirmed` | No later read showed the effect. Read the entity and its list after the write. | | `incomplete-entities` | The write is confirmed, but the views that show its entity cannot render it in full. Read the written entity through every view that lists it. | The bundle ships `evidence.json`, the whole capture Evidence, response bodies included. Inspection excludes the values of the standard authentication headers (`Authorization`, `Cookie` and `Set-Cookie` among them) and URL userinfo; a custom key header such as `X-Api-Key`, a token in the query string and tokens an application returns in bodies remain. The environment views refuse captures inspected with `--sensitive-value`, so scrub a capture before building it. The report's `credential-named-members` warning counts recorded header names, query parameter names and JSON or form body members whose names look like credentials (whole name segments such as `token`, `secret`, `password`, `api_key`, `authorization` or `session`) and hold a value, and lists the first 20 by record and pointer, never by value. A body is read as a form or as JSON by its recorded media type, or by its shape when it has none or one naming neither. A browser scenario is scanned by event (`event 4 response /token` names `normalized_result.events.items[4]`): every retained request and response content event, including a response whose request began before the browser was attached and a transaction no record represents, and each transaction URL's query once. Bodies larger than 4 MiB of UTF-8 text are not scanned; `credential-scan-incomplete` counts them and lists up to 20 record or event pointers, including base64 bodies whose decoded scan was cut. An empty name warning does not establish that these bodies were checked. Names do not establish sensitivity, so the build never refuses on them. Capture Evidence also records the capture file's absolute path (`subject.local_path`, `parameters.capture_path`, `locations`, `artifact.path`), and the bundle carries it: build from a neutral folder when that path should not ship. Over MCP, `export_environment_bundle` builds the same bundle and returns the same report. Its `source` is capture Evidence the session retained (`{"kind": "retained-evidence", "evidence_id"}`), such as a `capture_browser_scenario` or `inspect_web_network_capture` result, or a capture Evidence file (`{"kind": "evidence-file", "path"}`); inspect a HAR with `inspect_web_network_capture` first. Retained Evidence is written into the bundle as `--format json` writes it, so the bundle is the one `environment-build` writes from that file. `output_directory` must be an absolute path that does not exist yet, whose parent does; the tool creates it and refuses an existing directory, empty or not. `name`, `template_rules`, `package_tarball` and `dry_run` work as `--name`, `--template-rule`, `--package-tarball` and `--dry-run` do, and retained Evidence has no file to name the environment after, so a loopback or IP origin needs `name`. Unlike `--dry-run`, `dry_run` still checks `output_directory`. Destination refusals name `export_environment_bundle`; the others name their stage as `environment-build`'s do. ## From a browser scenario The capture can also come from REA itself: a [browser scenario](browser-scenario-contract.md) records a scripted session in a browser REA launches, and its Evidence is a manifest parent like a HAR inspection. Select the `network` event family and response bodies. A replayed reply carries up to 256 KiB of a recorded body, but the scenario keeps at most `max_network_body_bytes` of each body (64 KiB by default), and only within its allocation budgets: base64 is charged about 11 bytes per body byte, and redaction more the shorter a declared secret is (about 35 bytes per body byte for a 12-character `admin_password`). A body over `max_network_body_allocation_bytes` (1 MiB by default) is kept as `unavailable` with that reason; one over `max_event_allocation_bytes` (4 MiB) or `max_total_event_allocation_bytes` (16 MiB) loses its whole content event, headers included, which the capture lists among its omissions. Either way its tool replays no body. The example raises all four so that 256 KiB bodies are kept when the declared secret has at least 12 characters: ```json { "browser": { "mode": "launch", "executable_path": "/usr/bin/chromium" }, "start_url": { "url": "http://127.0.0.1:5230/auth", "query": [] }, "secrets": [ { "secret_id": "admin_password", "environment_variable": "APP_PASSWORD" } ], "actions": [ { "step_id": "user", "action": "fill", "locator": { "kind": "css", "selector": "input[name=username]" }, "value": { "source": "literal", "value": "admin" } }, { "step_id": "password", "action": "fill", "locator": { "kind": "css", "selector": "input[type=password]" }, "value": { "source": "secret", "secret_id": "admin_password" } }, { "step_id": "sign-in", "action": "press", "locator": { "kind": "css", "selector": "input[type=password]" }, "key": "Enter" }, { "step_id": "first-memo", "action": "goto", "destination": { "url": "http://127.0.0.1:5230/m/1", "query": [] }, "wait_until": "load" } ], "capture": { "events": ["network"], "network": { "request_body": true, "response_body": true, "header_values": false }, "limits": { "max_network_body_bytes": 262144, "max_network_body_allocation_bytes": 12582912, "max_event_allocation_bytes": 12582912, "max_total_event_allocation_bytes": 67108864 } } } ``` ```sh APP_PASSWORD=… rea capture-browser-scenario scenario.json --format json > capture.json rea inspect-analysis-view view.json --format json > manifest.json # view.json wraps capture.json as before rea environment-serve manifest.json --evidence capture.json --port 8765 ``` Each network transaction becomes one record, in request order, and the record's ordinal is its zero-based position; a transaction whose URL carried a redacted secret is left unrepresented rather than templated, and one the capture cannot attribute to a single request and response is left unrepresented too. Tools are chosen by response media type, so a scenario that selected neither response bodies nor header values is refused; one that selected header values but no response bodies yields a manifest but no state, so it is served by replay. The browser scenario redacts credential headers and the secrets it declares; values the application returns in response bodies, such as session tokens, are kept, and the replayed body is the bytes the browser exposes for each response, with any declared secret replaced by its redaction marker (a body that redaction had to empty replays no body). To record writes, sign in through the UI and then send the application's API calls with [request steps](browser-scenario-contract.md#request-steps): each sends one request to the start origin through the page's own `fetch`, with the session's cookies, and a header can carry the CSRF cookie or stored token the application's own requests send. A write is served only when the capture shows its effect, so read each collection before writing, read every written entity back by id and in its list right after the write, and leave more than a second between a create and its first edit. A request step's path is fixed when the scenario is written and cannot use a value an earlier response returned, so an id must be known before the run: one the caller chooses, such as a `uid` in the create body, or one an earlier scenario created. When the server assigns ids, read the list after each create (the create's response or the list shows the new entity), and record updates and deletes in a second scenario that reads the first one's objects by id before editing them, or make them through the UI. The environment coverage view names each write it withholds and what to record next. A scenario with write requests changes the application's data: record against an instance whose data may change. ```json { "step_id": "create-folder-1", "action": "request", "method": "POST", "path": "/api/folders", "headers": [ { "name": "X-CSRFToken", "value": { "source": "cookie", "name": "csrftoken" } } ], "json": { "title": "Scratch folder 1" }, "expected_status": [200, 201] } ``` Each record takes its start and duration from the browser's timing (the time the scenario observed the request where the browser reported no start), so the state orders and overlaps records as it does a HAR's and learns a write clock: an update the application stamps with a modification time can be served. A scenario captured before these times were recorded has none; its records keep request order and the state learns no clock, so such updates stay `unexplained-change` until it is recorded again. ## What a manifest is An environment manifest is a projection of one application's recorded request lines into a tool surface: one tool per method and path template on the primary origin, with inferred path parameters, observed query parameter names, value-free body shapes and pointers to the parent records each tool cites. It carries no bodies and no headers. The manifest's `parent_evidence_id` names the capture Evidence it was projected from; the serve command refuses a manifest whose parent is not the supplied `--evidence` file with an `invalid_request` error naming both identifiers, so a manifest can never be served from records it did not cite. The MCP catalog and environment card use a 1 KiB UTF-8 budget for each captured display sample. Observation, body-key and cited-record lists show whole values with omission counts; long method, path and query-name displays show a marked prefix. Complete values remain in manifest Evidence. Argument names longer than 64 characters use collision-safe `path_` or `query_` aliases; replay maps those aliases to the complete captured names. Discovery is admitted as a complete catalog under a 1 MiB serialization reservation before the listener binds. Reservation charges up to six bytes per UTF-16 code unit for JSON escaping/UTF-8 expansion, plus schema overhead; a catalog may therefore be refused even when its compact JSON is smaller. This was calibrated with 1500 query fields and eight concurrent SDK discovery requests (183,798-byte card, 507.27 MiB sampled process-family RSS). Over-capacity catalogs return `resource_constraint`, retain complete input Evidence, and require a smaller capture or manifest. Fields and tools are never silently omitted. Served from the state, each description is longer and the card declares the data plane, so a catalog replay admits can exceed the reservation; the state is then unavailable and the server serves replay instead (see [Serve from the state](#serve-from-the-state)). ## What replay means and does not mean Replay answers every tool with `--replay-only` or when the state is unavailable, and, served from the state, each read tool whose view the state does not back. Each such MCP tool call selects one of the records its manifest tool cites and returns that record's recorded response. Selection compares the supplied path parameters against the record's path segments at the parameter indexes, then the supplied query values against the record's query string, and keeps the record with the most matches; ties keep manifest order. A query argument accepts one string or an array of strings for repeated values; the array is matched against every occurrence in captured order. The raw recorded query remains the replay evidence. The result reports where the answer came from: ```json { "status": 200, "content_type": "application/json", "body": { "id": 2, "login": "probe" }, "replay": { "record_ordinal": 5, "evidence_id": "ev_…", "exact_match": true, "recorded_path": "/api/users/2", "recorded_query": null, "recorded_line_truncated": false, "body_recorded": true, "body_encoding": "utf-8", "truncated": false } } ``` `exact_match` is true when every supplied path parameter and query occurrence matches the recorded one; it says nothing about parameters the caller omitted. Comparison probes retain the raw query spelling and its decoded parameter pairs in request order, including the interleaving of repeated values across names. Standalone tool calls express repeated values as per-name arrays; when matching records differ only in cross-name order, `exact_match` is false because those arguments cannot identify that order. Recorded query parsing runs only when supplied query arguments affect selection. A path value matches a recorded segment as written or after percent-decoding; when both kinds of match are available, the record whose segment equals the value as written is chosen. `recorded_query` keeps the `?` of an explicit empty query, and a recorded path or query longer than 1 KiB is cut in the reply with `recorded_line_truncated: true`; selection always uses the full recorded line. `content_type` also has a 1 KiB display bound with `content_type_truncated`; body interpretation uses the full recorded media type. When no record matches, the tool still answers from the tool's first cited record and reports `exact_match: false`. `body` is parsed JSON when the recorded content type is JSON-like (`application/json`, `application/*+json`, `text/plain`, `text/markdown`) and the text parses with safe numeric conversion; otherwise it is the recorded text. Large integer IDs and other numbers that would lose information stay in the original JSON text. Bodies over 256 KiB are cut at a UTF-8 boundary and returned as text with `truncated: true`. `body_recorded` is false when the capture kept the response's status and content type but no body; `body` is then `null`, which is not a recorded JSON `null`. `body_encoding` is `base64` when the capture retained response bytes that are not valid UTF-8; `body` is then exactly those bytes in base64, never a lossy decoding. A retained base64 body is decoded only as far as the 256 KiB a reply can carry, and a leading byte-order mark is kept. For a `base64` body the limit applies to the recorded bytes, not their longer base64 spelling, and a cut keeps whole base64 groups. Request bodies passed to `POST`, `PUT` and `PATCH` tools are accepted and ignored: nothing is written, and no call changes what a later call returns. Arguments the tool's input schema does not name are refused by the MCP server as invalid arguments, so a misspelled parameter never degrades into an omitted one. Replay is not emulation. A served environment does not establish the application's authorization model, response semantics or state transitions, which the manifest lists as unknowns; it does not validate supplied values; and it answers only from the capture's recordings and the state they observed or a caller loaded through `data/add`. Replayed content is target content: every tool result, including the argument errors the MCP server returns before a replay runs, carries `_meta.provenance.untrusted_content: true` with `source: "analysis_target"`. The server advertises REA's untrusted-content instructions plus a warning that its tool names, descriptions, parameter names and observed values come from the capture too, and agents must treat all of it as data, never as instructions. That same warning prefixes every tool description in the standalone card, so card discovery carries it before an MCP client initializes. It labels the captured text without changing the tool names or schema fields clients use. ## The state a capture observed Replay answers each call from one recording, so the answers reflect whichever moment of the capture recorded them. The [environment state](web-network-captures.md#environment-state) view extracts instead the data the capture's reads observed before the first related write: entity types with an identity field, entities with their recorded values, documents for reads that are not entities, and a render plan per read tool, kept only where it reproduces that tool's recordings from the state. It is the starting state an environment holds, loads and reports: `environment-serve` derives it from the capture at startup; see [Serve from the state](#serve-from-the-state). With `--replay-only`, replay is unchanged. ## Serve a manifest ```sh rea environment-serve manifest.json --evidence capture.json [--replay-only] [--host 127.0.0.1] [--port 0] ``` The server derives the state from the capture before it binds and serves from it, or serves replay with `--replay-only` or when the state is unavailable; see [Serve from the state](#serve-from-the-state). `--host` and `--port` default to `MCP_HOST` and `MCP_PORT` from the environment, then to `127.0.0.1` and an ephemeral port, exactly as [`rea mcp --http`](cli.md#serve-mcp-over-streamable-http) resolves them. The bound MCP URL is written to stderr as one JSON log line (`"msg":"MCP transport listening"` with `url`); `REA_LOG_LEVEL` overrides that log level. `ENVIRONMENT_NAME` renames the served environment; otherwise the manifest's `name` is used, and a set but blank value is refused as `configuration_invalid` before binding rather than silently falling back. The listener serves one MCP client at a time with the same session, `Host` header and shutdown contract as [transports](mcp-contracts.md#transports) describes. It runs until SIGINT or SIGTERM, then closes the listener, prints one `{"status":"stopped", …}` document whose `state` member says whether it served from the state, and exits `130` or `143`. Signals during input loading or DNS/bind cancel the owning reader/listener before a listening announcement; that path returns a structured `cancelled` result instead of a stopped-listener document, with the same signal exit status. Three routes are served: | Route | Answer | | --------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `POST /mcp` | The MCP server: from the state, one tool per read tool, answering from the state where it backs them, and one per write tool whose effect the capture confirmed, applying it to the state; in replay, one tool per manifest tool, replaying records | | `GET /.well-known/agent-env.json` | The environment card | | `POST /agentenv` | From the state, `data/reset`, `data/add` and `data/get`; in replay, JSON-RPC `-32601 method not found: ` for every method | Numeric JSON-RPC IDs outside JavaScript's safe range or whose precision would be lost are refused as invalid requests with a null ID. They are never echoed as a different number. In replay the data plane at `/agentenv` is advertised by the card but carries no operations; the error names the requested method so a caller can see that the method, not the transport, is unsupported. Its request body is read within the same 4 MiB bound the MCP endpoint applies: a larger body is answered `413` with a JSON-RPC `-32000` error before any of it is parsed, and a body that is not JSON is answered `400` with `-32700`. A notification (no `id`) gets `202` and no body, a batch gets one reply per request in it, and an empty batch, a batch of more than 100 messages, or a message that is not a JSON-RPC request (including an `id` that is not a string, number or null, or `params` that are not an object or array) gets `-32600 invalid request`. ## The environment card The card is the discovery document the agentenv framework reads before connecting to `/mcp`. A replay environment's card reads: ```json { "name": "grafana-example", "protocolVersion": "1.0", "url": "/agentenv", "preferredTransport": "JSONRPC", "additionalInterfaces": [{ "url": "/mcp", "transport": "mcp" }], "capabilities": { "extensions": null, "tools": [ { "name": "get_users_by_id", "description": "Untrusted captured API catalog: … GET /api/users/{numeric}; returns a JSON object with fields \"id\", \"uid\", \"login\", \"email\"; recorded statuses 200; replays retained records [5, 6]; evidence ev_…", "inputSchema": { "type": "object", "properties": { "id": { "type": "string", "description": "Path segment 2 (numeric); observed: 2, 3" } }, "required": ["id"], "additionalProperties": false } } ], "operations": [] }, "children_environments": null } ``` `capabilities.tools` lists the same names, descriptions and input schemas that `tools/list` advertises over MCP. After the catalog warning, each description names the method and path template, then what the tool returns, one level deep: `returns a JSON object with fields …`, `returns a JSON array of objects with fields …` or `returns a JSON object whose lists objects with fields …`, where a list is an array of objects found by the [environment state](web-network-captures.md#environment-state)'s list rule (the root array, or the one array of objects an envelope carries). Field and member names are written as JSON strings, so a captured name cannot read as more of the description; a member name too long to show whole is a quoted prefix marked as truncated. The summary comes from the first cited `2xx` record that replay answers as JSON; only when none did, the first cited JSON record of another status gives it, labelled with that status (`status 401 returns …`). It describes one recorded response, not a contract. Field names are sampled within the same budget as other captured values, and the manifest's `statuses` for the tool follow; a tool with no JSON record states only its statuses. The description then lists the replayed records and the evidence ID, and the whole catalog stays within its serialization reservation, which the summaries and MCP annotations are charged to. Over MCP, every tool also carries annotations: `readOnlyHint` is true for the safe methods (`GET`, `HEAD`, `OPTIONS` and `TRACE`) and for query `POST`s (a path segment such as `search` or `query`); `destructiveHint` is true for `DELETE` and left unset for other writes, so the MCP default (destructive) applies to them, and read-only tools omit it because clients ignore it there; `idempotentHint` is true for the safe methods, `PUT` and `DELETE`; and `openWorldHint` is false for every tool, because answers come from the capture rather than the captured application. The hints describe the captured method; replay itself changes nothing. The card keeps the `name`, `description` and `inputSchema` of the echo example's tool shape and carries no annotations. Path parameters are required strings whose description names the segment index, the templating rule and the observed values (sampled within the list budget above; the manifest keeps them all); query parameter names accept an optional string or array of strings (for repeated values in captured order); write methods accept an optional `body` object described by the recorded top-level key types. Each input keeps its own argument: a query name equal to a path parameter's name is advertised as `query_`, a query name longer than 64 characters as `query_` (its position) with the captured name sampled in its description, and the write body as `request_body` when a query parameter is named `body`. Every schema closes with `additionalProperties: false`, a key the echo example's schema does not carry. In replay, `extensions`, `operations` and `children_environments` are fixed to `null`, `[]` and `null`: a replay environment declares no extensions, no data-plane operations and no children. Served [from the state](#serve-from-the-state), the card declares the three data-plane operations and one intake extension instead, and the catalog holds the read tools and only the write tools whose effect the capture confirmed: a read tool is described as answering from the state where the state backs it, and a served write tool by the effect it applies to the state and the quoted body members it accepts. ## Serve from the state ```sh rea environment-serve manifest.json --evidence capture.json ``` Before it binds, the server derives the [environment state](web-network-captures.md#environment-state) the capture observed: it runs the `environment-state` view on the capture in-process with the manifest's `template_rules` in the same order, exactly as `inspect-analysis-view` projects it from the same capture, so the state Evidence id it reports is the one that projection produces. The view's own budget and refusals apply, and the result is checked like the view's Evidence for this manifest: extracted from the served capture, with the manifest's rules, naming only manifest tools. The server keeps one live state, shared by every MCP session and the data plane, starting from the derived state. A state that is unavailable does not stop the server: it logs a warning naming the error `code` and message before it binds, then serves replay. The state is unavailable when it cannot be derived, such as from a `capture_browser_scenario` capture that selected header values but no response bodies or over the view's budget, when `data/get` would write it past the 32 MiB `data/add` intake limit, and when its catalog under the served name exceeds the [discovery reservation](#what-a-manifest-is). That check runs first, so no state is derived for it, and replay is then admitted exactly as with `--replay-only`. `--replay-only` serves replay without deriving anything; the card, tools and `/agentenv` answers are then exactly those of replay. The stopped document's `state` member reports which applied: - `{"served": true, "evidence_id": "ev_…"}`: served from the derived state. - `{"served": false, "reason": "replay-only"}`: `--replay-only` was given. - `{"served": false, "reason": "unavailable", "code": "unsupported_target", "message": "…"}`: the state is unavailable; `code` and `message` are those of the refusal (`resource_constraint` for a catalog over the reservation), as the warning logged them. Each read tool answers according to its view in the state: | View | Answer | | ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | `item` | The entity the path arguments name, rendered into the recorded envelope of `envelope_ordinal`, whose `per_response_members` (such as a request id), like a list's or a document's, keep their recorded values. Arguments match as replay matches them: each collection segment equals the held collection's segment as written or after percent-decoding, and the identity is the last argument percent-decoded, then as written; values are never re-split on `/`. Any entity the state holds answers, including one `data/add` loaded; query arguments only decide `replay.exact_match`, except that a call matching one of the view's `projected_query_keys`, or on a view with `projected_record_ordinals` asking for some fields only with a value other than `*` no checked line gave or one a replayed read gave, replays its recording. An entity the state does not hold answers the tool's latest recorded 400, 404 or 410 response with `state.view` `missing`, or is a tool error when none was recorded; one lacking a field every recording carried is a tool error, unless a read showed the application leaves that field out; a body is never invented. | | `list` | When the arguments name one of the lines the view checked exactly (its latest recordings before the first related write; every path and query value equal to the recording's, and every recorded query parameter supplied), that recorded envelope with its array rendered from the state: every entity of the collection in state order for `membership: "all"` or a line `all_record_ordinals` names, or the recorded members still held. A call with no query argument answers from such a line of the collection its path arguments name that only pages its list, with `replay.exact_match` false. On a line the view's `query` answers, and for a call whose every query argument has a role there (an argument-less call aside), the answer is the query evaluated over the state: filtered, searched, sorted and paged, with counters at the number listed and `query.totals` at the number matched, and `state.membership: "query"`; such a call answers on a query or whole line of its collection with `replay.exact_match` false. A value an `inert` parameter never recorded, a parameter without a role, a call matching one of the view's `projected_query_keys`, or a field selection the checked lines do not show (as for `item`), replays its recording. A member lacking a field every recording carried makes the call a tool error rather than a partial list. | | `document` | When the arguments name the document's checked line exactly, the state's value for it; a tool error when the state holds none. | | `recorded` | The recording, as replay answers it. | A read with repeated query values uses replay, because the state query model does not infer repeated-parameter semantics. A repeated-query write is refused before it can change state for the same reason. List counters retain their recorded number or digit-string representation. Changing a digit-string counter preserves its observed zero-padding width; query-total inference remains limited to canonical decimal counts. Path matching uses the same segment parser as extraction, preserving empty internal segments. An item or list view that always spells a clock field otherwise than the entity's stored value names that spelling in `clock_formats`, and a value it never recorded, such as a created entity's clock, is rendered in it: a list that writes `+00:00` where item reads write `Z` lists a new entity the same way. A view that names a field in `sorted_arrays` lists that string array sorted, as a read-back showed the application does, while the state keeps it in the order it was written, so a write's own answer echoes it. If a later counted read contradicts that ordering, the view stays recorded and its earlier reads no longer confirm served writes. A view that names a field in `nested_fields` always showed that field's objects with the same keys, in any order, and fewer than an entity stores, such as a list showing a parent without the parent's own nested type; a stored object it never recorded, such as a created entity's parent, is rendered with those keys. Members a view names in `per_response_members`, such as a request id each response mints, keep the value its recording carried. A list's `counters` and `query.totals` are top-level members or members one level down in a paging object (`/pageInfo/totalRows`); either is set to the number listed or matched, and members beside it such as `isLastPage` stay as recorded. A list or document call that names no checked line, including a line recorded after a write or with other query values, answers from the recording. Every answer has the replay shape plus `state`: `{"source": "state", "view": …}` naming the entity, collection or document path, or `{"source": "recording", "reason": …}` with the view's reason, `no-view`, `unrecorded-request`, `page-exceeded` (a call naming a page of a whole list that the collection has outgrown), `projection` (a call to an item or list tool with replayed reads asking for a selection of fields the checked lines do not show, or leaving out a projection parameter every checked line names) or `variant` (a call matching another `projected_query_keys` key: a parameter, or a value of one, only lines showing the entities in another representation named, or leaving out a parameter every other line named). A `projection` or `variant` answer is a recording, so it does not show served writes. A state answer carries the base record's status, content type and `replay` provenance with `truncated: false`; one whose JSON would exceed 256 KiB is refused as a `resource_constraint` tool error rather than cut. Extraction does not state-back a document whose rendered JSON exceeds 256 KiB; that read stays recorded (`rendered-oversize`) and replays the captured body. Query `POST`s, and `POST` tools the capture shows only reading (a lookup answering as a `GET` did, an RPC tunnel naming read operations, a session renewal), stay served and answer from their recordings with the reason `query-body`; they are not write tools. A line establishes whole-collection membership only from the beginning: `offset`, `start`, `_start` and `page` must be zero when present. Positive or malformed positions do not by themselves establish whole membership. A separate query model may describe supported paging; an empty later page cannot start returning earlier entities merely because it was empty in the capture. `POST`, `PUT`, `PATCH` and `DELETE` tools are served only when the state's [write plan](web-network-captures.md#environment-state) for them is served: the capture's later reads confirmed the effect the plan models. Other write tools are not served, so no call claims a change it does not make; each one's plan states why in its `reason`. A served write changes the live state, which every MCP session and `data/get` then see: | Effect | Call | | ------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `create` | Adds an entity to the collection the path names, built from the observed entity with each ruled field taken from the call or generated, at the plan's `insert` position. A plan tied to its exemplar's collection writes only there. | | `update` | Sets the sent members on the entity the path names, constants for members accepted only with their recorded value, and the clock, nested clock, increment, slug, stamp, derived, composed, reference, unique and renewed changes the plan models. | | `update` (action) | A `POST`, `PUT` or `PATCH` to an item path plus an action segment (`/{type}/{id}/archive`) sets, on the entity before the segment, each scalar the recorded calls showed the action set (`set`), with any sent members; it is served only when a recorded call found those fields already set, so a toggle never is. | | `delete` | Removes the entity the path names. | | bulk `update` or `delete` | A `DELETE`, `PUT` or `PATCH` at a collection, or a `POST` to it plus `delete`, `remove` or `destroy`, applies its effect to every entity the body names, as recorded: an array of ids or of objects carrying the id field, at the root or as the body's one array member (`{"IDs": […], "Read": true}`). | | `document` | Merges the body into the plan's document object, or replaces it for `PUT`. | An update's unsent changes follow the plan's rules. A `held-clock` is a clock the client sends back as it read it and the application stamps anew (Ghost's `updated_at`): the call must send the entity's value and the field takes the write's clock. A `nested-clock` sets the clocks inside an object the entity holds, in that object's recorded format. A `stamp` writes the acting user the entity already names under its `created…by` counterpart into a `modified…by` or `updated…by` field. A `derived` field takes a value showing the one sent member's text that the entity stores nowhere (a field Ghost derives from `html`), only with that member's recorded value. An action's `set` rule sets a scalar to the value the recorded calls left it at. Its answer has the status and content type of the plan's recorded response, with the written entity or its identity rendered in, no body, or the recorded body. A call whose body is not an object, sends a member the capture did not show stored, sends a fixed member with another value or a member of another JSON type, or lacks a required member is a tool error naming the accepted members; so is a call sending query parameters other than the exemplar's (they may change what the body does), a body not wrapped in the exemplar's envelope (Ghost's `{"posts": [{…}]}`), a bulk call naming an id the state does not hold, a `held-clock` member sent with another value than the entity holds, a call sending a `derived` rule's member to an entity that does not hold the value the recorded call found, a nested clock on an entity holding no such object, and a rendered answer missing a field the recorded response carried, and an update or delete of an entity the state does not hold answers the recorded 400, 404 or 410 of the tool or of an item view of the type, if any. A refused call leaves the state unchanged. Values a write generates are deterministic: the clock starts at `write_clock` and advances one second per served write, sequences take one past both the largest held value and the largest they generated, and UUIDs and tokens derive from the state Evidence id, tool, field and write count, skipping held values. `data/reset` and `data/add` restart the clock, counter and sequences, so the same calls after a reset give the same state. Answers carry `state: {"source": "state", "view": "create" | "update" | "delete", …}` or `"document-write"`; a bulk answer adds `ids`, every entity it wrote in body order, with `id` naming the first. The data plane serves three JSON-RPC methods: | Method | Result | | ------------ | --------------------------------------------------------------------------------------------------------- | | `data/reset` | `{}` after restoring the state the Evidence holds | | `data/add` | `{}` after replacing the whole state with one valid `rea-state/v1` document | | `data/get` | `{"parts": [{"kind": "data", "data": }]}` with `state_evidence_id` and the `types` | Calls run one at a time in arrival order across requests. Every message of a batch is queued when the batch arrives, so another request's call never lands between them and each message sees the changes of those before it; a reset sent while a download is loading applies after that load. `data/add` takes exactly one part: a `data` part whose `data` is the document, or a `file` part whose `file` carries `bytes` (base64 of UTF-8 JSON) or a `uri`, either a `file://` URL of a local regular file, whose host is empty or `localhost`, or an `https://` URL fetched without following redirects and within 30 seconds, including reading the body; `mimeType`, when given, is `application/json`. A `file://` URL naming another host, or a UNC path such as `file:////server/share/state.json`, is refused before anything is opened, so a load never reaches a network share. A loaded document is at most 32 MiB, and so is the state as `data/get` writes it back with the members a document may omit (`types`, `state_evidence_id`, record citations), so a reported state always loads again; an inline part also stays within the 4 MiB request body bound, so larger states arrive by `uri`. Anything else, including `{"parts": []}`, is `-32602 invalid params`; a download that fails or answers a non-2xx status is `-32000`. Errors never echo the uri or the content; a file or download failure names its category in `error.data.reason`: `not-found`, `permission`, `not-regular-file`, `changed` or `read-failed` for files, `timeout`, `http-status` or `network` (connection, TLS or a refused redirect) for downloads, and `cancelled` for a download the server's stop or its caller's departure ended. Served creates also bound additional collection history since the last reset or `data/add` to 1 MiB of deterministic accounting: UTF-8 bytes for each new collection spelling and its possible sequence keys, plus a 64-byte allowance per collection and potential sequence-key record. The score bounds identifier payload and a fixed record allowance; it is not a measurement or guarantee of process memory. Collections already present in the Evidence or loaded state are part of the state itself; the store indexes their unique spellings so they remain known after deletion, but they do not consume this additional-history budget. A create that would exceed the budget is refused before the state changes. `data/reset` or `data/add` clears generated history; if the same calls would hit the limit again, use fewer distinct collection paths. The 1 MiB score ceiling is 1/32 of the separate 32 MiB state-intake ceiling, reserving a small, explicit allowance for identifiers retained beyond the loaded state. A loaded-state path that is later deleted and then introduced again may consume the additional-history budget when the store must retain it beyond the source entity. Stopping the server cancels every pending call, and a caller that leaves before its reply cancels its own: a download in progress ends, and calls not yet run are answered `-32000` with `error.data.reason` `cancelled` without running. A cancelled call leaves the state unchanged, and shutdown never waits for a download. One `/agentenv` response carries at most 64 MiB of replies, twice the 32 MiB a loaded document may hold: room for a `data/get` of a loaded state, while a batch of reads cannot multiply a large state into one body. Replies are measured in order as they are produced, in bounded parts and before they are assembled, and room is kept for every later reply's budget error and the batch's brackets and commas, so one that would take the response past the budget is never built whole and is answered instead with `-32000` whose `error.data` gives `max_response_bytes` and the `reply_bytes` it would have taken. That call still ran, so repeat such a read in another request. A reply no larger than that error, such as a write's `{}`, is always kept. ```json { "rea_state": { "version": 1, "entities": [ { "type": "/api/users", "collection": "/api/users", "id": "2", "fields": { "id": 2, "login": "probe" } } ], "documents": [] } } ``` Each entity's `type` is a state type's `collection_template`, its `collection` matches that template segment by segment (a template parameter matches any one segment), its identity field's value is its `id`, and its type, collection and id are unique; `view_fields` is optional and names item or list views of its type. Views render their values over the entity's fields, so a view's values must not set the type's identity field to a value whose text differs from the entity's `id`. Spell a collection as requests spell it, as `data/get` reports it: list calls find entities under the checked line's recorded path. State collection identity preserves repeated separators inside captured paths: `/api/books` and `/api//books` are distinct. A single trailing slash continues to name the same collection. Each document names a `document` view once, at its initial document's `path`. The `version`, and the `state_evidence_id` and `types` that `data/get` reports, must match the served state, so a `data/get` result loads back unchanged. A number without an exact native value, or whose serialized spelling would not be read as exact (an integer from 2^53 below 1e21, such as `1e20`, in any spelling), is refused rather than altered. Caller data preserves all own JSON members, including `__proto__`; unknown members of the state document's structure are refused. An invalid document is `-32602` naming the first problem by JSON pointer, as in `/rea_state/entities/3/collection` (also in `error.data.path`); a problem inside caller data (`fields`, `value`, `types`) is located at that member, so the pointer never names the caller's keys. A refused document changes nothing; a valid one replaces the whole state at once. The order of `entities` is the state order lists use. Record citations stay Evidence provenance. An entity's `record_ordinals` may be omitted or empty and a document's `record_ordinal` omitted; otherwise they must be the served Evidence's citations for that entity or document, or the document is refused. After loading, an entity or document whose values equal the Evidence's cites the Evidence's records, and one whose values were edited or added cites none (`record_ordinals: []`, no `record_ordinal`), so `data/get` never presents a loaded value as recorded. The card declares the operations and what `data/add` accepts: ```json { "extensions": [ { "uri": "urn:agentenv:intake/v1", "description": "data/add replaces the whole environment state with one rea-state/v1 document; data/get returns the current state in the same format.", "params": { "add": [ { "part": "data", "format": "rea-state/v1", "load": "replace" }, { "part": "file", "format": "rea-state/v1", "mimeTypes": ["application/json"], "load": "replace" } ], "get": [{ "part": "data", "format": "rea-state/v1" }] } } ], "operations": ["data/reset", "data/add", "data/get"] } ``` The state starts as a projection of recorded reads and changes only through served write tools and the data plane. List and document calls answer from the state only for the lines their views checked, and every recorded view answers from recordings; item calls answer for any held entity but render only the envelope one recording carried. Values copied outside entity objects, derived values and counters other than those that count a list stay as recorded, and a served write changes only the one entity or document it writes: side effects on counters, relations and copies of entities in other collections, reordering after an update and referential rules on delete are not modelled. An exported bundle carries no state file: its server derives the state at startup, as the export does to predict what it serves. Known limits of served writes: - A recorded view answers from its recordings after a served write: Mailpit's `get_messages`, recorded as `list-differs`, still lists a message a served delete removed. - Served n8n workflow updates accept any `versionId`, while served Ghost post updates require `updated_at` to match the entity (a `held-clock`). - A slug derived from a title can repeat across served creates with the same title, where the application would make it unique. - A `composed` string copies sent text as sent: an application that escapes or renders it (HTML entities, Markdown) differs for text that needs it, as BookStack's `description_html` would for a description holding `&`. - A served create's sequence id is the state's next value, not the gaps an application's own sequence would leave. - Nested clocks are served in the spelling of the write's own response, which can differ from what a later read of the application shows. - A served write to an entity that a replayed (unserved) create made answers as for a missing entity, since the state never held it. ## Export a bundle `rea environment-export` writes the same pair as a bundle folder the agentenv framework runs directly, shaped like its own echo example: ```sh rea environment-export manifest.json --evidence capture.json ./grafana-example --json agent-env run ./grafana-example ``` ```text grafana-example/ README.md provenance, what it serves, run command, rights note envs/grafana-example/Dockerfile pinned image: node:24.22.1-bookworm-slim + rea-agents@ envs/grafana-example/env.toml environment_name = "grafana-example" envs/grafana-example/manifest.json byte-exact copy of manifest.json envs/grafana-example/evidence.json byte-exact copy of capture.json artifacts/check_grafana-example/verify.py the verifier tasks/smoke.json deploy_env (local sandbox), then env_outcome_verifier ``` The command reads each file once, after checking that reading and parsing the whole file, including sealing traversal, fits the process's live heap headroom (a file that does not is refused as a `resource_constraint` before it is read), then authenticates and cross-checks the pair as `environment-serve` does, so a manifest projected from another capture is refused with the same `invalid_request` before anything is written, and the bytes it copies are the bytes it authenticated. The bundle directory must be absent or empty; an occupied directory is refused and nothing in it changes. After checking the bundle name, the export prepares the state from the capture exactly as the bundle's server will at startup under that name, to predict what the bundle serves; an unavailable state, including one whose catalog exceeds the discovery reservation, does not stop the export, and the bundle then serves replay. The complete tool catalog the bundle serves must also fit the server's advertised catalog budget before any files are written. Privately parsed JSON is sealed once so authentication and replay share immutable response trees rather than copying the capture repeatedly. `--name` replaces the manifest's portable kebab-case name as the env folder and env id (at most 63 characters for its DNS service label; Windows device names and labels interpreted as IP addresses are refused); `--package-tarball ` copies a packed `rea-agents` tarball into the env folder and makes the Dockerfile install it instead of the registry package and remove it in the same layer, which is how a checkout rather than a release is run. The command prints the written files with their sizes, the pinned package source, the number of tools the bundle serves as `tool_count`, and in `state` whether it serves from the state, in the shape of the serve command's stopped document. Export uses the shared output-tree owner to check directory identities around exclusive creates, verify written bytes, and reject unowned entries before reporting success. It does not delete an inspectable partial folder on failure. Node's portable pathname APIs leave a syscall-boundary race, so the output's parent directories must be trusted. On POSIX output files use mode `0600`; Windows inherits ACLs and REA does not establish owner-only access there. Choose an already private Windows destination when captured content needs it. The Dockerfile sets `MCP_HOST=0.0.0.0` and `MCP_PORT=18765`, the port the framework maps for an MCP server env, and `MCP_ALLOWED_HOSTS` naming the loopback addresses and the environment name, because the container binds outside loopback and the server refuses to serve on such a bind without an operator-declared allowlist: the framework's published port is reached over loopback and its gateway proxies to the env container by the compose service name (the environment name). The framework's own deploy supplies `MCP_HOST`, `MCP_PORT` and `ENVIRONMENT_NAME`, so the served card carries the env's name. It installs Debian's `python3` because the framework's local sandbox probes a container's readiness with `python3` inside it, which the slim Node image lacks. It copies the two inputs owned by the image's non-root `node` user, so a private host umask cannot leave them unreadable, runs as that user and starts `rea environment-serve /env/manifest.json --evidence /env/evidence.json`. The `env.toml` names the environment because the framework otherwise reads the name from Python sources the image does not have. `verify.py` is the framework's `async def verify(mcp_url)` shape over its Python MCP client: it lists the tools and checks the count equals the number the bundle serves (from the state, the manifest's read tools and the write tools whose effect the capture confirmed; every manifest tool in replay), calls one tool with no arguments and checks the call did not fail and its `status` is the expected one, and returns one `serve` result whose description reports both checks. The tool is the first served `GET` tool without path parameters whose answer to no arguments is not an error, and the expected status is the status of that answer: the export calls the same answer function the server uses, from the derived state or by replay, so a state answer carries its base record's status and a replayed one its record's (an unknown recorded status stays unknown; it is not borrowed from another record). A bundle with no such tool yields a verifier that checks the count only and says so. `tasks/smoke.json` deploys the env on the local sandbox and runs that verifier against the env's MCP endpoint; the first run also builds the framework's own infrastructure, and the run tears everything down when it ends. The README written into the bundle records the capture artifact's SHA-256, the capture and manifest Evidence ids, the manifest view digest, the served tool count, the derived state's Evidence id or that no state is served, and the package source. It says what the environment serves: read tools from the state the capture observed, the `/agentenv` data plane on it and the write tools whose effect the capture's later reads confirmed, replay when the state is unavailable, and `--replay-only` for pure replay; it says which applies to this bundle, with the error code and message when the state is unavailable, and that neither is emulation and served content is untrusted data. It states that the recorded content belongs to the captured application and must not be published without the rights to it. ## Measure fidelity against the application An environment agrees with its own capture by construction. What matters to an agent is how it answers the calls the capture did not make, what it shows after a write, and how it fails. `rea environment-compare` measures that against the application itself: ```sh rea environment-compare manifest.json --evidence capture.json \ --probe probe-crud.json --probe probe-reads.json --json ``` Each `--probe` is capture Evidence (`inspect-web-network-capture` of a HAR, or `capture-browser-scenario`) of one call sequence made against the live application, seeded as it was for the capture and reset before the sequence. The command makes no network call: whoever records the probes drives the application with its own credentials. For each probe it resets the environment's state, takes the requests in the order they were made (record order when any lacks a start time), matches each to the manifest tool of the same method whose path template fits with the most literal segments (a format-rule parameter must fit its format once percent-decoded). A path argument is the raw segment, which the environment decodes once. It answers the call as the served environment would, and compares that answer with the application's. A re-seeded application holds the same entities under other ids, so the comparison maps them. Objects in the two answers to one call pair by a natural key, a string field unique on each side that both share, such as a name or a slug; their identifier fields (`id`, `uuid`, `guid`, and names ending in `_id`, `Id`, `ID`, `_uuid` or `Uuid`), and those of two single answers such as a create's, map the live value to the environment's, including a create that returns only the new id. Ids are learned only from an answer the environment gave that call itself, from its state or a recording of that very call, request line and body, never from another call's recording replayed in its place and never from a recording whose body the probe omitted. The answer's own `id`, `uuid` or `guid` also maps within the collection the call names, since two collections can reuse a live id, and an equal pair stays in that collection. A live id in a later request's path, query or body is translated before the environment answers, a path parameter by the collection the live path names (a nested collection keeps its parent values, each decoded once, and a literal route segment stays), except a query value that pages a list, such as `limit` or `page`. Each call is checked against the served tool's input schema first, as the MCP server checks it. After mapping, two clock values compare by format only (ISO-8601 strings, and epoch numbers under `at`, `time`, `date`, `timestamp`, `created`, `updated` or `modified` field names, including snake-case and camel-case forms). Numeric arrays retain that containing field's clock context through nested arrays; an object's own fields establish their own context. Numeric values at the body root, in root arrays, or under measurement fields remain literal. Generated values normalize only where this confirmed, served write's entity response rules identify generation. A UUID identity rule must still compare two UUIDs, and a `unique` rule two UUIDs or two generated integers (10 to 20 digits) of one JSON kind and length; a `renewed` rule applies only at its recorded pointers, with `*` matching actual array items. Token/sequence strings retain the existing format check: equal length of at least eight, the same character classes, and a digit. Numeric sequences continue to compare literally unless an ID mapping applies. String shape and names such as `token` or `sku` alone do not establish generation. Read and replay responses without these facts stay literal except for supported clocks and learned IDs. A missing write target replays an absence response and does not inherit the successful entity response's generation rules. Admitted generated values must also preserve aliases and distinct identities within that response. UUID identity uses the generator's case-insensitive matching; token and sequence strings retain their literal identity. This correspondence ends with the answer and is not inferred across calls. A `composed` response field must spell the value its parts build from that response's own fields. Its parts then compare by their rendered text or their source fields' clock and ID rules. A coherent archive URL can therefore differ only in normalized clock digits without reporting a value difference; an incoherent URL still differs even when both sides repeat the same stale text. Normalized compositions count under `generated`; source fields are counted once. The report counts each kind of normalised value; the generation rules remain model-derived facts, rather than new observations of the application. ISO clock offsets are accepted only within RFC 3339's `00`–`23` hour and `00`–`59` minute ranges. Probe ordering retains every recorded fractional-second digit in ISO timestamps with a four-digit year, `T`, and a `Z` or `±HH:MM` suffix. Equal instants use ordinal order. Other native-Date spellings keep their existing millisecond interpretation; an absent or unreadable start time makes the whole probe use record order. Original capture timestamps remain unchanged. Clock-format comparison and respelling recognize four-digit ISO years `0000`–`0099` as well as later years, with normal calendar validation. Respelling preserves the original value when the target zone would require a year outside `0000`–`9999`; generated writes refuse a clock outside that format. Capture-state start ordering uses the same exact recorded timestamp facts, including minute-only times and fractions longer than nine digits. Recorded spellings may use `T` or a space, `Z` or an extended/compact offset, or no zone (interpreted as UTC). Equal starts use ordinal order; a missing or unreadable start makes the capture use record order. Request interval and overlap checks still use millisecond coordinates, and generated-clock progression compares milliseconds. Derived ISO clock formats still require seconds and at most nine fractional digits. Comparison keeps response representations distinct: JSON values compare structurally, text compares as text, and a retained base64 body compares by bytes (including with UTF-8 text carrying those same bytes), never by its base64 spelling. ID mappings apply at identifier fields, `ids`/`uuids`/`guids` lists, an entity's own identity within its collection, and a string field learning confirmed as a state-held ID. ID mappings leave other numeric and string values unchanged. A global conflict involving an equal pair is not used to normalize either pair; the report counts it as an ID conflict. A step agrees when the statuses and the normalised bodies are equal. The report gives agreement overall, per probe and per tool, `agreement_ignoring_order` for steps that differ only in item order, and each step's differences, at most 20, with a JSON pointer and both values cut short: | Category | Meaning | | --------------- | ------------------------------------------------------------------------------------------------------------ | | `status` | The statuses differ | | `missing-field` | The application's object has a member the environment's lacks | | `extra-field` | The environment's object has a member the application's lacks | | `value` | Values differ, or one is an object or array and the other is not | | `length` | Arrays differ in length, or not every item pairs | | `order` | Paired items come in a different order | | `clock-format` | Both are clocks, in different formats | | `refused` | The environment refused the call | | `not-served` | The request's tool is one the environment does not offer, such as a withheld write | | `no-tool` | No manifest tool matches the request | | `unmapped-id` | The application answered with success and the environment did not, for a path id the comparison never mapped | What a probe did not observe is not counted as the application's behaviour. A record without a usable request line, such as a redacted URL or a transaction the capture cannot attribute, is not replayed, nor is a request to an origin different from the application's (`other-origin`: the probe's origin with the most JSON-like records, as the manifest chooses its own), and a request with no recorded answer is made, since it may have changed the application, but not compared: each probe lists them under `unobserved` with the reason, and the summary counts them. A live body the probe did not record compares by status only and is counted as `unobserved_bodies`, unless the answer never carries one (204, 205, 304, `HEAD`). A browser probe captured without `capture.network.response_body` is refused, as is one that makes POST, PUT or PATCH calls without `capture.network.request_body`. Agreement covers only the calls the probes make, after the mapping the answers allow. Clocks compared by format and fields normalized under explicit generation rules can still differ in content, and an equal answer after a write shows the state matched for that read, not that the write had no other effect. ## Compatibility verification `npm run verify:agentenv:environment` is the hosted `real-agentenv` lane described in [testing](testing.md#exported-environment-bundles). It projects the Grafana-shaped source-owned capture through the built CLI, packs the checkout, exports a bundle with `--package-tarball`, runs it with the pinned `agentenv-framework` release on the runner's Docker and requires the smoke task to pass with no container left behind other than the framework's own image-registry helper, which the receipt reports. It proves that one exported bundle runs on one framework release; it does not claim any hosted platform or other framework versions. ## Resource and lifecycle boundaries The Evidence files are read once at startup through the bounded JSON input reader and authenticated as Evidence before the listener binds; a file that is not Evidence, a manifest of another view kind, a capture of another format, or a manifest projected from a different capture is refused before any port is opened. The state is derived once, in-process and before binding, from the already authenticated capture: it is projected as retained Evidence, so the capture's strings are not charged again as inline view input, and the view's 96 MiB budget bounds the derivation. Because authentication covers the capture's records, a manifest whose parent check passes cites only records the capture retains. The server keeps only the cited records' request lines and response text in memory, plus the live state when it serves from one: the derived initial state, or one validated document whose JSON was at most 32 MiB. Data-plane calls run one at a time, so at most one loaded document is being read and parsed at once; `data/get` serializes the held state whole. No process is launched and nothing is written to disk. No outbound network request is made unless a `data/add` call names an `https://` uri, which is fetched once within the limits above; a `file://` uri is read once. A listener that fails after binding is logged and ends the command with a `resource_constraint` error and exit `1` instead of serving nothing.