@sellable/install 0.1.259 → 0.1.261
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/bin/sellable-install.mjs
CHANGED
|
@@ -1944,7 +1944,8 @@ ${allowedToolsYaml(REFILL_SENDS_ALLOWED_TOOLS)}
|
|
|
1944
1944
|
|
|
1945
1945
|
Use this as the customer-facing entrypoint for the Sellable \`refill-sends\`
|
|
1946
1946
|
workflow. It supports \`--yolo\` and optional repeated \`--sender <name-or-id>\`
|
|
1947
|
-
selectors.
|
|
1947
|
+
selectors. It also supports \`--until YYYY-MM-DD\` to fill through a specific
|
|
1948
|
+
sender-local date instead of the default two send-day horizon.
|
|
1948
1949
|
|
|
1949
1950
|
## Bootstrap
|
|
1950
1951
|
|
|
@@ -1960,7 +1961,7 @@ Desktop, then start a new thread.
|
|
|
1960
1961
|
## Execute Workflow
|
|
1961
1962
|
|
|
1962
1963
|
1. Call \`mcp__sellable__get_auth_status({})\`.
|
|
1963
|
-
2. Normalize invocation arguments with \`mcp__sellable__refill_sends({ yolo, senders, senderIds, senderNames })\` when the host exposes typed MCP tools.
|
|
1964
|
+
2. Normalize invocation arguments with \`mcp__sellable__refill_sends({ yolo, senders, senderIds, senderNames, untilDate })\` when the host exposes typed MCP tools.
|
|
1964
1965
|
3. Load the canonical prompt via
|
|
1965
1966
|
\`mcp__sellable__get_subskill_prompt({ subskillName: "refill-sends" })\`,
|
|
1966
1967
|
then load \`mcp__sellable__get_subskill_prompt({ subskillName: "refill-sends-workflow" })\`.
|
package/package.json
CHANGED
|
@@ -66,14 +66,18 @@ Accepted invocation flags in the same user request:
|
|
|
66
66
|
fresh state reread.
|
|
67
67
|
- `--sender <name-or-id>`: scope to a specific sender; repeat for multiple
|
|
68
68
|
senders.
|
|
69
|
+
- `--until <YYYY-MM-DD>`: fill through that sender-local date, inclusive,
|
|
70
|
+
instead of the default two send-day horizon.
|
|
69
71
|
- `senderIds: <id>, <id>` or `senderNames: <name>, <name>`: explicit selector
|
|
70
72
|
alternatives when the host preserves natural-language arguments better than
|
|
71
73
|
shell-style flags.
|
|
74
|
+
- `untilDate: YYYY-MM-DD`: explicit date selector alternative when the host
|
|
75
|
+
preserves natural-language arguments better than shell-style flags.
|
|
72
76
|
|
|
73
77
|
When the host can call typed MCP tools, start with:
|
|
74
78
|
|
|
75
79
|
```text
|
|
76
|
-
refill_sends({ yolo?: boolean, senders?: string[], senderIds?: string[], senderNames?: string[], horizonSendDays?: number })
|
|
80
|
+
refill_sends({ yolo?: boolean, senders?: string[], senderIds?: string[], senderNames?: string[], horizonSendDays?: number, untilDate?: "YYYY-MM-DD" })
|
|
77
81
|
```
|
|
78
82
|
|
|
79
83
|
That command helper only normalizes arguments and returns the execution
|
|
@@ -132,13 +136,16 @@ reassignment, or campaigns outside those selected for the eligible sender set.
|
|
|
132
136
|
Stop and re-plan if the route, sender set, ids, caps, blockers, or side-effect
|
|
133
137
|
class drift before mutation.
|
|
134
138
|
|
|
135
|
-
In `--yolo`, the default two-day fill horizon is two send days
|
|
136
|
-
|
|
137
|
-
|
|
138
|
-
|
|
139
|
-
|
|
140
|
-
|
|
141
|
-
|
|
139
|
+
In `--yolo`, the default two-day fill horizon is two send days unless
|
|
140
|
+
`--until`/`untilDate` is provided. If an until date is provided, compute bounded
|
|
141
|
+
gaps through that sender-local date inclusive, skipping no-send days and never
|
|
142
|
+
extending beyond that date without a new packet. For each target sender, compute
|
|
143
|
+
the bounded gap from that sender's healthy daily capacity, existing future
|
|
144
|
+
scheduler-owned scheduled sends, and rows already ready to schedule across
|
|
145
|
+
active campaigns enrolled with that sender. Then pick the best same-sender
|
|
146
|
+
campaign to fill the gap: prefer recent/future scheduler-owned sends for that
|
|
147
|
+
sender, then strongest recent result evidence, then source health. Do not stop
|
|
148
|
+
after filling only one sender when the request was sender-scoped. If a
|
|
142
149
|
same-source copy hits the campaign-table row cap, split the current source into
|
|
143
150
|
a bounded LinkedIn profile source list, confirm only that smaller list into the
|
|
144
151
|
same campaign, and operate on the copied review batch. Do not fall back to
|