chore: sync branch with latest main

This commit is contained in:
morluto committed 2026-10-08 23:52:20 +08:00
commit e7946c3ad4
43 files changed
+1314 -186

No files matched your search

+12 -7
View File
@@ -100,17 +100,22 @@ a temporary output file larger than the running engine's string limit, verifies
its bytes and digest, and removes it. Use `-- jsonl` for the compact JSONL check.
Each check needs space for one output file plus a 1 GiB free-space reserve.
Other CLI formats, `--token-count`, and MCP transport serialization still
assemble whole strings. Field selection remains useful when the caller needs a
Other CLI formats and `--token-count` still assemble whole strings.
Field selection remains useful when the caller needs a
smaller view, for example `--format json --filter-output
evidence_id,normalized_result.statistics`. Streaming output does not bound the
memory needed to construct the analysis graph itself.
The separate large-response transport work is tracked in
[#1053](https://github.com/morluto/rea/issues/1053) and
MCP prepares the complete repeated response incrementally against the pinned
SDK's 10 MiB stdio receive-buffer budget. Oversized results return an actionable
transport constraint and the exact same-session Evidence reference. Use
`trace_application_feature` to inspect a selected module's relationships, or
`export_evidence_bundle` to write the complete canonical bundle without a
document-sized allocation. Same-session analysis reads reuse authenticated
immutable snapshots; foreign inline Evidence is still parsed and authenticated.
See [MCP tool results](mcp-contracts.md#tool-results) for larger client buffers
and `REA_MCP_MAX_RESPONSE_BYTES`. Follow-up results remain complete and can also
exceed the transport budget. Compact result views are tracked separately in
[#1050](https://github.com/morluto/rea/issues/1050).
Client framing limits also apply: the pinned Node MCP SDK's stdio transport
defaults to a 10 MiB buffer. Its caller-selected `maxBufferSize` must accommodate
the complete response, including text and structured Evidence projections.
## What is reconstructed
+20
View File
@@ -164,6 +164,26 @@ directly to `compare_functions`, and `inspect_artifact` Evidence to
`compare_artifacts`. Use `get_evidence_bundle` when the task needs broader
retained session history or an explicit bundle for transfer.
REA prepares complete MCP results within the pinned stdio client's 10 MiB
receive-buffer budget, including both text and structured representations and
room for the JSON-RPC envelope. If a result cannot fit, REA returns
`resource_constraint` with `details.resource: "transport"` before constructing
a document-sized string. Analysis Evidence remains complete in the current
session. Its exact reference is reported in
`details.reported_limits.evidence_reference`; use it with a focused application
workflow, or call `export_evidence_bundle` with a destination path. Complete
bundle exports stream canonical JSON into an atomically published file. A broad
follow-up or `get_evidence_bundle` can also exceed the response budget; exporting
preserves the complete session without sending it through a single MCP frame.
Clients that explicitly configure a larger receive buffer can set the REA
server's `REA_MCP_MAX_RESPONSE_BYTES` environment variable to the same byte
count. This setting must be a safe decimal integer at least 10485760; REA
reserves 1024 bytes for the envelope. Raising it restores complete inline
delivery for responses that fit that buffer and Node's single-string limit.
It does not change the client's buffer, analysis coverage, or retained content.
Ordinary responses keep their existing complete result contract.
## Retained application Evidence inputs
`trace_application_feature`, `trace_javascript_semantics`,