@fluentcommerce/fluent-mcp-extn 0.7.0 → 0.7.2

package/docs/RUNBOOK.md

@@ -148,18 +148,18 @@ Point to a JSON file with `FLUENT_PROFILES_FILE`:
 
 #### Runtime management
 
-- `connection.list` — see all registered profiles and their status
-- `connection.switch` — change the default at runtime
-- `connection.add` — add profiles dynamically (CLI profile name or explicit credentials)
-- `connection.remove` — remove a non-default profile
+- `connection_list` — see all registered profiles and their status
+- `connection_switch` — change the default at runtime
+- `connection_add` — add profiles dynamically (CLI profile name or explicit credentials)
+- `connection_remove` — remove a non-default profile
 
 #### Verify multi-profile setup
 
 ```
-1. connection.list                                              → all profiles listed
-2. connection.test                                              → default profile connected
-3. graphql.query { profile: "DEV/DEV_RETAILER", query: "{ me { username } }" }  → secondary connected
-4. workflow.list { profile: "STAGING/UK" }                       → third profile connected
+1. connection_list                                              → all profiles listed
+2. connection_test                                              → default profile connected
+3. graphql_query { profile: "DEV/DEV_RETAILER", query: "{ me { username } }" }  → secondary connected
+4. workflow_list { profile: "STAGING/UK" }                       → third profile connected
 ```
 
 #### Prompting the LLM for multi-profile
@@ -168,46 +168,46 @@ Example prompts that leverage multi-profile:
 
 - "Compare ORDER workflows between DEV/DEV_RETAILER and STAGING/UK"
 - "Query order ORD-123 on STAGING/US"
-- "Run environment.discover on all profiles and compare locations"
-- "Check metrics.healthCheck on DEV/DEV_RETAILER — is the failure rate normal?"
+- "Run environment_discover on all profiles and compare locations"
+- "Check metrics_healthCheck on DEV/DEV_RETAILER — is the failure rate normal?"
 - "List settings on STAGING/UK and STAGING/US — what's different?"
 
 #### Prompting the LLM for ambiguous time windows
 
 When the user asks for relative windows like `last month`, `yesterday`, `this week`, or mixes metrics-style datemath with API questions, resolve the time intent first instead of guessing:
 
-1. `time.resolveWindow { phrase: "last month", timezone: "Asia/Calcutta" }`
+1. `time_resolveWindow { phrase: "last month", timezone: "Asia/Calcutta" }`
 2. If `valid: false` and `ambiguous: true`, clarify with the user or choose `mode: "calendar"` / `mode: "rolling"` explicitly
-3. Feed the exact `from` / `to` timestamps into `graphql.query`, `graphql.queryAll`, `event.list`, or `event.flowInspect`
+3. Feed the exact `from` / `to` timestamps into `graphql_query`, `graphql_queryAll`, `event_list`, or `event_flowInspect`
 
 Example prompt pattern:
 
 - "Resolve `last month` in Asia/Calcutta, then count return orders for that exact window."
-- "Resolve `now-7d/d` in Asia/Calcutta, then use those exact timestamps for `event.list`."
+- "Resolve `now-7d/d` in Asia/Calcutta, then use those exact timestamps for `event_list`."
 
 ## 4) Startup verification checklist
 
 Run tools in this order:
 
-1. `config.validate`
-2. `health.ping`
-3. `time.resolveWindow` with `phrase: "last month"` — verify local ambiguity handling and exact timestamp output
-4. `connection.test`
-5. `event.build`
-6. `event.send` with `dryRun: true`
-7. `event.send` with `dryRun: false`
-8. `event.get` using ID returned by send
-9. `graphql.query` simple read
-10. `entity.get` — verify entity lookup works (e.g., look up a known order by ref)
-11. `setting.get` with `name: "fc.mystique.manifest.%"` — verify settings read access and wildcard support
-12. `workflow.list` — verify REST workflow API access (list all workflows for a retailer)
-13. `workflow.get` with `entityType: "ORDER", entitySubtype: "HD"` — verify specific workflow fetch
-14. `workflow.transitions` (optional) — verify User Action API access for a known trigger
-15. `graphql.queryAll` — verify auto-pagination and run-level timeout
-16. `graphql.introspect` with `listMutations: true` — verify schema access
-17. `environment.discover` with `include: ["retailer", "locations"]` — verify environment snapshot
-18. `environment.validate` with `checks: ["auth", "retailer", "locations"]` — verify pre-flight checks
-19. (optional) `graphql.query` synchronous fulfilment options call
+1. `config_validate`
+2. `health_ping`
+3. `time_resolveWindow` with `phrase: "last month"` — verify local ambiguity handling and exact timestamp output
+4. `connection_test`
+5. `event_build`
+6. `event_send` with `dryRun: true`
+7. `event_send` with `dryRun: false`
+8. `event_get` using ID returned by send
+9. `graphql_query` simple read
+10. `entity_get` — verify entity lookup works (e.g., look up a known order by ref)
+11. `setting_get` with `name: "fc.mystique.manifest.%"` — verify settings read access and wildcard support
+12. `workflow_list` — verify REST workflow API access (list all workflows for a retailer)
+13. `workflow_get` with `entityType: "ORDER", entitySubtype: "HD"` — verify specific workflow fetch
+14. `workflow_transitions` (optional) — verify User Action API access for a known trigger
+15. `graphql_queryAll` — verify auto-pagination and run-level timeout
+16. `graphql_introspect` with `listMutations: true` — verify schema access
+17. `environment_discover` with `include: ["retailer", "locations"]` — verify environment snapshot
+18. `environment_validate` with `checks: ["auth", "retailer", "locations"]` — verify pre-flight checks
+19. (optional) `graphql_query` synchronous fulfilment options call
     (`createFulfilmentOption` with `executionMode: AWAIT_ORCHESTRATION`)
     for live checkout readiness checks
 
@@ -292,7 +292,7 @@ Likely causes:
 
 Actions:
 
-1. call `config.validate`
+1. call `config_validate`
 2. inspect `errors` and `warnings`
 3. verify env vars in `.mcp.json`
 4. reload your IDE's MCP process
@@ -341,7 +341,7 @@ Actions:
 1. increase `FLUENT_REQUEST_TIMEOUT_MS`
 2. increase `FLUENT_RETRY_ATTEMPTS`
 3. verify base URL and outbound connectivity
-4. for `graphql.queryAll`, increase tool-level `timeoutMs` (controls whole pagination run)
+4. for `graphql_queryAll`, increase tool-level `timeoutMs` (controls whole pagination run)
 
 ### `VALIDATION_ERROR`
 
@@ -364,11 +364,11 @@ Likely causes:
 
 Actions:
 
-1. pass exact raw HTTP body via `rawBody` in `webhook.validate`
+1. pass exact raw HTTP body via `rawBody` in `webhook_validate`
 2. verify signature header value is unchanged
 3. confirm algorithm (`SHA512withRSA` default)
 
-### `SDK_ERROR` with `Request failed: 400` on `event.send`
+### `SDK_ERROR` with `Request failed: 400` on `event_send`
 
 Likely causes:
 
@@ -377,7 +377,7 @@ Likely causes:
 
 Actions:
 
-1. query the target entity via `graphql.query` and capture `id`, `ref`, and retailer
+1. query the target entity via `graphql_query` and capture `id`, `ref`, and retailer
 2. send event with matching `retailerId`
 3. include `entityId` and `rootEntityId` when available
 
@@ -411,7 +411,7 @@ Actions:
 2. increase `FLUENT_RESPONSE_BUDGET_CHARS` (e.g., `80000` or `100000`)
 3. increase `FLUENT_RESPONSE_MAX_ARRAY` if specific arrays are being summarized
 4. set `FLUENT_RESPONSE_BUDGET_CHARS=0` to disable shaping entirely
-5. for `event.flowInspect`, use `compact: true` (default) to get a pre-analyzed
+5. for `event_flowInspect`, use `compact: true` (default) to get a pre-analyzed
    summary instead of raw arrays
 
 ## 7) Reliability tuning guidance