docs(evm): record compatible wiring and real task costs

Record six exact SDK catalog/fact pairs, 59 real CLI/MCP cases, six cross-domain artifact workflows and six actual Codex CLI trials. Preserve failed setup attempts privately and qualify unchanged complete delivery, host-state variance and unknown final resource counters.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

experiments/analysis-efficiency/README.md

@@ -44,8 +44,9 @@ acceptance conditions for every optimization.
   experiment control; it does not itself establish reduced CPU consumption.
 
 Migrate domain by domain with focused real-artifact checks and relevant shared
-contract checks. The domain matrix is a growing roadmap; native PE and DOS, for
-example, remain unverified in this study. A passed lane does not imply all
+contract checks. The native follow-up verifies selected PE and DOS MZ entry facts;
+DOS COM and complete native application behavior remain unverified. The domain
+matrix is a growing roadmap. A passed lane does not imply all
 advertised platforms/providers have passed. Newly discovered REA bugs remain
 in the separate local handoff document for later team repair.
 

experiments/analysis-efficiency/evm-descriptor.md

@@ -21,7 +21,7 @@ real EVMole/WABT claims. Nine service and 26 provider-boundary cases also pass;
 two unsupported-host scenarios are skipped on this Linux host. The existing seven
 WASM MCP scenarios pass. Full `npm run check` passes; its approximately 3 GiB
 sampled peak and `memory.high` events are excluded from performance claims.
-Fresh candidate real-artifact/catalog and model comparisons are still pending.
+Candidate real-artifact/catalog and model observations are recorded below.
 
 ## Public inputs and independent checks
 
@@ -94,5 +94,88 @@ and `--output` selecting a new private receipt. It acquires no dependencies and
 does not overwrite an existing receipt.
 
 The [template model question](questions/evm-uniswap.txt) requires the same complete
-inferred interface facts and explicit unknowns. Real model trials and a candidate
-recommendation are pending; an ABI-count match is not used as a model grade.
+inferred interface facts and explicit unknowns. An ABI-count match is not used as
+a model grade.
+
+## Candidate compatibility and real-provider verification
+
+Candidate: `152984da771450048ee9d60db8a410994a125878`, frozen runtime file-table
+SHA-256 `725563640c27eb50ddb6f977d2dfbe1bdaddf7e05c02897318bceaa36fa602d7`.
+Two repetitions for each EVM input produce six passing paired fact/settings
+comparisons with the same driver and explicit limits. Each report preserves both
+original Evidence reference maps. The complete actual SDK catalog is byte-identical
+on every pair, including order, names, descriptions, schemas and annotations;
+catalog SHA-256 is
+`8664e42fd5225645cfd910f440f731c67ac198d3d53aa85b5c485374c74cf603`.
+Result byte counts remain unchanged. Candidate Factory/Pool selectors also match
+the independent published ABI oracle.
+
+| Question | Control seconds, repetitions 1 / 2 | Candidate seconds, repetitions 1 / 2 |
+| -------- | ---------------------------------: | -----------------------------------: |
+| Factory  |                      3.628 / 3.650 |                        3.708 / 3.605 |
+| Pool     |                     11.211 / 3.591 |                        3.749 / 3.581 |
+| WETH     |                     11.432 / 3.694 |                        3.572 / 3.677 |
+
+First controls preceded wiring; each second pair ran candidate then control.
+Every measurement starts a new MCP process; host cache/page state is not fully
+controlled. Slower initial controls do not establish a descriptor speedup.
+Second-pair latency and last-observed CPU are similar. Sampled EVM SDK family peaks
+range from 510,255,104 to 527,622,144 bytes. No scope abort occurred; final counters
+remain unknown, so these measurements are descriptive.
+
+The candidate passes all 59 existing real CLI/MCP verifier cases with solc 0.8.30
+and unchanged EVMole 0.9.3. Actual syscall traces report target execution and network
+sockets absent for those scenarios, and the verifier reports no remaining
+descendants. The scope took 177.456 seconds, sampled peak 1,237,020,672 bytes and
+last-observed CPU 144.913 seconds. Different totals from the earlier control are
+not attributed to unchanged provider algorithms.
+
+Post-descriptor public MCP regression uses the original pinned shipped corpus:
+
+| Domain / selected question                  | Actual provider / scope                            | Calls | Seconds |
+| ------------------------------------------- | -------------------------------------------------- | ----: | ------: |
+| SQLite WASM counts / exports                | WABT 1.0.42; selected summary and retained read    |     2 |   5.516 |
+| ShareX managed metadata / native boundaries | Static PE/CLI, no assembly execution               |     2 |   3.710 |
+| Obsidian manifest / inventory               | Complete inventory retained, no AST claim          |     4 |   5.376 |
+| NewPipe package / MainActivity methods      | Real headless JADX 0.7.1                           |     3 |  21.669 |
+| OpenWrt regions                             | Real firmware signature scan, no device execution  |     1 |   3.581 |
+| jq native entry                             | Ghidra 12.1.4, default analysis, ephemeral Program |     4 | 270.986 |
+
+All six workflows pass named SDK output validation and original digest checks;
+input bytes remain unchanged. Maximum sampled family peak is 1,284,648,960 bytes.
+They establish those available Linux workflows, not paired performance or
+Windows/macOS, IDA/Hopper, Android-device, DOS COM, browser or JavaScript AST
+behavior. Browser/AST were not repeated for this narrow migration.
+
+## Real model complete-output calibration
+
+Six serial Codex CLI 0.161.0 trials request `gpt-5.6-terra`, high reasoning, with
+isolated temporary profiles pointing to the frozen candidate. Resolved server-side
+model identity is not inferred. Only the EVM inspection tool is enabled, matching
+the earlier WETH calibration; this is not full-catalog tool selection verification.
+Every trial makes one successful call and no failed call.
+
+| Trial     | Total input | Uncached input | Output | Seconds |
+| --------- | ----------: | -------------: | -----: | ------: |
+| Factory 1 |      66,158 |         36,974 |  1,329 |  43.483 |
+| Pool 1    |      65,600 |         36,416 |  2,307 |  69.546 |
+| WETH 1    |      54,700 |         25,516 |  1,144 |  56.372 |
+| Factory 2 |      65,964 |         36,780 |  1,453 |  26.412 |
+| Pool 2    |      65,753 |         36,569 |  1,939 |  74.706 |
+| WETH 2    |      54,502 |         25,318 |  1,208 |  35.137 |
+
+Every trial reports 29,184 cached input tokens. Selected fact/reference/lifecycle
+grades all pass: original/decoded identities, every inferred selector, offset,
+dispatch, argument/mutability string including null, explicit unknowns, no runtime
+execution, observed Evidence references, unchanged bytes and removed profiles.
+Raw transcripts and grades remain private. Sampled peaks are
+594,853,888–776,335,360 bytes; last-observed CPU is 6.181–7.034 seconds. Strict
+overall grades remain unverified because final resource counters are unknown;
+they are not relabeled as wholly passing resource-qualified runs.
+
+This calibrates the current complete path after compatible wiring, not a paired
+model performance experiment. The next token experiment should answer the same
+interface question through an explicitly selected precise view, retain full
+bytecode/original Evidence under the existing lifetime, and preserve complete
+defaults. Discover support before sending new options to an older server. Include
+discovery, follow-up, failures and retries in the complete task cost.