@sellable/install 0.1.279 → 0.1.280
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/package.json
CHANGED
|
@@ -1232,7 +1232,7 @@ Message, and verify current-revision sample messages before final completion.
|
|
|
1232
1232
|
Short form: Do not pass the warm template into Shared Signal Discovery or Shared Cold Fallback.
|
|
1233
1233
|
Short form: Shared lanes must reject generic product-summary samples.
|
|
1234
1234
|
Short form: Shared lanes must reject three nearly identical samples.
|
|
1235
|
-
Short form: Shared lanes must reject intent-assumptive hedges
|
|
1235
|
+
Short form: Shared lanes must reject unsupported intent-assumptive hedges; Shared Signal Discovery may use Dotwork-style topic bridges like "saw you might be interested in [topic], so hope this is relevant", "saw you in a few conversations about [topic], so hope this is relevant", or "hope this is relevant if [topic] is part of the plan" when the source evidence supports the topic and the line does not claim engagement or expose source mechanics.
|
|
1236
1236
|
Short form: Shared lanes must reject internal workflow vocabulary.
|
|
1237
1237
|
Short form: revise or rerun the packaged create-campaign/generate-messages path.
|
|
1238
1238
|
- **Post Engagers** first-message style: short, casual, references the
|
|
@@ -1298,7 +1298,7 @@ Message, and verify current-revision sample messages before final completion.
|
|
|
1298
1298
|
Short form: Shared Signal Discovery uses no self-intro such as "I'm building Sellable".
|
|
1299
1299
|
Short form: Shared Signal Discovery uses no self-intro such as "We're building Sellable".
|
|
1300
1300
|
Short form: Shared Signal Discovery uses no "I've put together".
|
|
1301
|
-
Short form: topic-level bridges, including "saw you in a few conversations about/around [topic], so hope this is relevant" and "hope this is relevant if [topic] is part of the plan", are allowed for Shared Signal Discovery when evidence-backed and not engagement-claiming; "might be interested"
|
|
1301
|
+
Short form: topic-level bridges, including "saw you might be interested in [topic], so hope this is relevant", "saw you in a few conversations about/around [topic], so hope this is relevant", and "hope this is relevant if [topic] is part of the plan", are allowed for Shared Signal Discovery when evidence-backed and not engagement-claiming; do not use bare "might be interested" as a generic intent claim.
|
|
1302
1302
|
Short form: no internal workflow vocabulary such as "Codex-style workflow", "MCP", "agent workflows", "Claude Code", or "Claude-style agent workflows".
|
|
1303
1303
|
- **Shared Cold Fallback** first-message style: cold, direct, and cohesive.
|
|
1304
1304
|
It must not pretend there was engagement, must not say "saw you pop up",
|
|
@@ -157,6 +157,19 @@ return concrete continuation options with campaign names, exact ids, which optio
|
|
|
157
157
|
is already covered by the current packet, and which option needs a new approval
|
|
158
158
|
packet.
|
|
159
159
|
|
|
160
|
+
For `--yolo` fill/schedule requests, completion means scheduler-proven horizon
|
|
161
|
+
saturation, not merely prepared/approved/ready rows. Maintain a horizon
|
|
162
|
+
saturation ledger per selected sender: selected send days, gross capacity,
|
|
163
|
+
future scheduler-owned scheduled cells with non-null `scheduledFor`,
|
|
164
|
+
ready-to-schedule buffer, remaining scheduled gap, remaining ready-or-scheduled
|
|
165
|
+
gap, and the next MCP primitive that can reduce the gap. After every
|
|
166
|
+
apply/prep/start result, wait for processing, reread refill state, recompute the
|
|
167
|
+
ledger, then keep applying safe bounded actions until the scheduled count fills
|
|
168
|
+
the horizon or a concrete blocker/timeout is proven. If ready rows cover the
|
|
169
|
+
horizon but the scheduler has not picked them up yet, run a bounded scheduler
|
|
170
|
+
settle loop and report `awaiting_scheduler_after_ready_buffer` as not complete
|
|
171
|
+
when the timeout is reached.
|
|
172
|
+
|
|
160
173
|
In `--yolo`, the default two-day fill horizon is two send days unless
|
|
161
174
|
`--until`/`untilDate` is provided. If an until date is provided, compute bounded
|
|
162
175
|
gaps through that sender-local date inclusive, skipping no-send days and never
|