metheus-governance-mcp-cli 0.2.260 → 0.2.261
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +44 -0
- package/cli.mjs +1564 -1468
- package/lib/local-ai-adapters.mjs +1 -1
- package/lib/runner-delivery.mjs +225 -147
- package/lib/runner-orchestration.mjs +1558 -164
- package/lib/runner-recovery.mjs +640 -0
- package/lib/runner-runtime.mjs +487 -170
- package/lib/runner-trigger.mjs +160 -333
- package/lib/selftest-bot-commands.mjs +4 -4
- package/lib/selftest-runner-scenarios.mjs +2664 -240
- package/lib/selftest-telegram-e2e.mjs +239 -19
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -247,6 +247,50 @@ See the separate guide:
|
|
|
247
247
|
|
|
248
248
|
- [`docs/telegram-group-privacy-guide.md`](docs/telegram-group-privacy-guide.md)
|
|
249
249
|
|
|
250
|
+
## Runner Input Pipeline
|
|
251
|
+
|
|
252
|
+
The runner input path currently has an architecture note for separating context records from execution ownership.
|
|
253
|
+
|
|
254
|
+
- [`docs/runner-input-pipeline-architecture.md`](docs/runner-input-pipeline-architecture.md)
|
|
255
|
+
|
|
256
|
+
Use that note when working on receipt evidence, local visibility, responder selection, and accept ordering. The short version is:
|
|
257
|
+
|
|
258
|
+
- `archive = context only`
|
|
259
|
+
- `receipt evidence = execution ownership only`
|
|
260
|
+
|
|
261
|
+
Current fixed module order:
|
|
262
|
+
|
|
263
|
+
1. input reception
|
|
264
|
+
- [runner-runtime.mjs](/C:/Metheus/METHEUS_V1/tools/governance-mcp-cli/lib/runner-runtime.mjs)
|
|
265
|
+
2. raw trigger evaluation
|
|
266
|
+
- [runner-trigger.mjs](/C:/Metheus/METHEUS_V1/tools/governance-mcp-cli/lib/runner-trigger.mjs)
|
|
267
|
+
3. continuation link recovery
|
|
268
|
+
- [runner-recovery.mjs](/C:/Metheus/METHEUS_V1/tools/governance-mcp-cli/lib/runner-recovery.mjs)
|
|
269
|
+
4. final execution decision and execution preparation
|
|
270
|
+
- [runner-orchestration.mjs](/C:/Metheus/METHEUS_V1/tools/governance-mcp-cli/lib/runner-orchestration.mjs)
|
|
271
|
+
5. request recording, state, lifecycle, and operator output
|
|
272
|
+
- [cli.mjs](/C:/Metheus/METHEUS_V1/tools/governance-mcp-cli/cli.mjs)
|
|
273
|
+
6. delivery orchestration
|
|
274
|
+
- [runner-delivery.mjs](/C:/Metheus/METHEUS_V1/tools/governance-mcp-cli/lib/runner-delivery.mjs)
|
|
275
|
+
7. provider transport
|
|
276
|
+
- [provider-local-transport.mjs](/C:/Metheus/METHEUS_V1/tools/governance-mcp-cli/lib/provider-local-transport.mjs)
|
|
277
|
+
|
|
278
|
+
Execution order depends on message type, but module numbering does not:
|
|
279
|
+
|
|
280
|
+
- normal human message: `1 -> 2 -> 4 -> 5 -> 6 -> 7`
|
|
281
|
+
- continuation bot reply: `1 -> 2 -> 3 -> 4 -> 5 -> 6 -> 7`
|
|
282
|
+
|
|
283
|
+
Maintenance guardrail:
|
|
284
|
+
|
|
285
|
+
- do not renumber these modules during cleanup
|
|
286
|
+
- do not solve a local edge case by moving behavior into the wrong module
|
|
287
|
+
- interpret old selftest names and old progress notes using the current module order only
|
|
288
|
+
|
|
289
|
+
Current validation guardrail:
|
|
290
|
+
|
|
291
|
+
- `npm run check` must stay green
|
|
292
|
+
- runner selftest baseline is `282 pass / 0 fail`
|
|
293
|
+
|
|
250
294
|
Built-in helper command for legacy fallback/testing:
|
|
251
295
|
|
|
252
296
|
```bash
|