c5cefd622b
Record genuine Code Mode use and full model usage rather than response-only estimates. Describe return shapes, permit byte-budgeted internal C reads, separate guest CPU from analysis deadlines, and move subsequent model profiles outside the source tree. Verify lease, admission, cleanup-retry and cancellation semantics. Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com> Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com>
71 lines
4.1 KiB
Markdown
71 lines
4.1 KiB
Markdown
# Atomic RE through Code Mode
|
|
|
|
This is an **in-progress experiment**, not an integrated provider release. Branch
|
|
`experiment/atomic-codemode-20261016` starts at main
|
|
`42fc6c53ae188978deb3bedfe88287b6b316ba22` and carries the previous atomic-facts
|
|
prototype. Historical measurements in `../atomic-re-tools/` retain their original
|
|
baselines. No PR or merge is intended.
|
|
|
|
The goal is a real model completing reverse-engineering questions through
|
|
composable facts, with Code Mode as the calling adapter. A configured feature flag,
|
|
a scripted verifier or a small response does not prove that goal.
|
|
|
|
The reference is [Hex-Rays IDA MCP](https://github.com/HexRaysSA/ida-mcp/blob/df6de7985b534a964c125d5a86e41b26b17b14f6/ida_mcp/mcp.py):
|
|
an on-demand `reference` lookup and an execution entrypoint over a richer analysis
|
|
API. This experiment uses JavaScript and a QuickJS WASM environment rather than
|
|
Python in the host process. It exposes only declared static analysis capabilities.
|
|
It does not add target execution, patching or GUI control.
|
|
|
|
Three boundaries own the implementation:
|
|
|
|
- `provider.mjs`: existing REA native target/process owners and parsed Kuna
|
|
string/reference/SSA facts, retained sources, freshness and cleanup.
|
|
- `api.mjs`: named, validated fact/relationship contracts and session admission.
|
|
SDK callers, CLI scripts and both MCP adapters use these same methods.
|
|
- `executor.mjs`, `server.mjs`, `cli.mjs`: bounded JavaScript composition and
|
|
presentation. No analysis is reimplemented in the execution environment.
|
|
|
|
The complete Code Mode MCP catalog is `open_binary`, `reference`,
|
|
`execute_javascript`, `close_binary`. Setting `REA_ATOMIC_ADAPTER=direct` exposes
|
|
the same fact API as `facts_*` MCP operations for comparison. This is a distinct
|
|
experimental server; the production REA catalog is not filtered or replaced.
|
|
|
|
Use the pinned Node, an existing REA build and a caller-supplied Kuna 1.833:
|
|
|
|
```sh
|
|
npm ci --prefix experiments/atomic-codemode --ignore-scripts
|
|
node --test experiments/atomic-codemode/*.test.mjs
|
|
REA_KUNA_COMMAND=/absolute/path/to/kuna node experiments/atomic-codemode/server.mjs
|
|
```
|
|
|
|
The local MCP registration for real model trials is named `rea-codemode`.
|
|
`agent-trial.py --mcp-entrypoint /absolute/path/to/server.mjs
|
|
--server-name rea-codemode --protocol-profile atomic --profile-parent /tmp` creates an isolated
|
|
configuration, home and empty working directory for the model. Shell/file tools,
|
|
web search and delegation are disabled. No repository or oracle is placed in that
|
|
workspace. The copied authentication file is removed with the isolated profile.
|
|
Model output, actual MCP calls, original errors and usage remain in the trial
|
|
directory. `REA_ATOMIC_TRACE` and `REA_ATOMIC_EVIDENCE_DIR` retain actual API calls
|
|
and complete sources outside the model workspace when explicitly selected by the
|
|
evaluator. The ambient environment and credentials are not logged.
|
|
|
|
Current bounds: 64 MiB guest heap, 32 KiB code/output, 64 host calls per execution,
|
|
120 seconds wall deadline and 2 seconds of guest synchronous execution; native requests have existing supervision, an 8 MiB
|
|
capture budget and 1 GiB function-memory limit. Retained source storage is 64 MiB
|
|
per target, with two resident SSA indexes of at most 2 MiB each. Sources are
|
|
content-digested and retained until close; explicit evaluator copies survive
|
|
close. Capacity failures are explicit, not clipped facts. Leases and snapshot
|
|
handles prevent cross-session joins.
|
|
|
|
The diagnostic SSA format still has incomplete CFG, phi predecessor and
|
|
memory-alias coverage. These are active capability gaps to investigate with real
|
|
model traces, not success criteria waived by the prototype. Other providers are
|
|
not yet wired to this experimental service.
|
|
|
|
Completion requires actual model Code Mode use, independently checked task
|
|
answers, shared atomic/direct/Code Mode semantics, needed relation coverage,
|
|
failure/cancellation/identity tests, and equivalent completed-task measurements
|
|
including discovery/retries, actual model usage, cold/warm analysis, CPU and
|
|
process-family peak memory. Negative cases such as the small SQLite function
|
|
must remain in the comparison.
|