@sellable/install 0.1.294 → 0.1.296

package/bin/sellable-install.mjs

@@ -1973,7 +1973,8 @@ ${allowedToolsYaml(REFILL_SENDS_ALLOWED_TOOLS)}
 
 Use this as the customer-facing entrypoint for the Sellable \`refill-sends\`
 workflow. It supports \`--yolo\` and optional repeated \`--sender <name-or-id>\`
-selectors. It also supports \`--until YYYY-MM-DD\` to fill through a specific
+selectors. It also supports \`--target-date YYYY-MM-DD\` to fill one exact
+sender-local date and \`--until YYYY-MM-DD\` to fill through a specific
 sender-local date instead of the default scheduler-forward 48-hour target window.
 
 Goal-mode continuation: a skill cannot create or invoke \`/goal\` by itself. If
@@ -1998,8 +1999,8 @@ Desktop, then start a new thread.
 ## Execute Workflow
 
 1. Call \`mcp__sellable__get_auth_status({})\`.
-2. Normalize invocation arguments with \`mcp__sellable__refill_sends({ yolo, senders, senderIds, senderNames, untilDate })\` when the host exposes typed MCP tools.
-3. Call \`mcp__sellable__get_refill_target_plan({ senders, senderIds, senderNames, untilDate })\` before any mutation. If the returned target is already complete, stop with the no-op receipt. If ready rows cover the target but scheduled rows do not, keep the run open in the read-only scheduler wait/re-read loop until projected coverage fills, a concrete non-scheduler blocker appears, or Christian explicitly stops/statuses the run.
+2. Normalize invocation arguments with \`mcp__sellable__refill_sends({ yolo, senders, senderIds, senderNames, targetDate, untilDate })\` when the host exposes typed MCP tools.
+3. Call \`mcp__sellable__get_refill_target_plan({ senders, senderIds, senderNames, targetDate, untilDate })\` before any mutation. Render \`target.eligibleSenderLedger\`, \`target.senderRefillPlans[]\`, and \`target.globalActionQueue\` as the structured packet. Preserve the labels \`Need to prepare\`, \`Goal\`, \`Already sent\`, \`Scheduled\`, \`Ready and waiting to be scheduled\`, and \`Still need\`. In \`--yolo\`, execute only one globally ranked primitive from \`target.globalActionQueue[0]\`, then rerun \`get_refill_target_plan\`. Maintain a run-local \`refreshedPaidInmailSenderIds\` set and refresh each selected paid-InMail sender at most once before falling back to an existing connection lane or manual continuation. For exact-date proof, \`mcp__sellable__get_scheduler_fill_capacity\` is read-only and tells how many cells the scheduler will try to place for a sender/action/date. If the returned target is already complete, stop with the no-op receipt. If ready rows cover the target but scheduled rows do not, keep the run open in the read-only scheduler wait/re-read loop until projected coverage fills, a concrete non-scheduler blocker appears, or Christian explicitly stops/statuses the run.
 4. Load the canonical prompt via
    \`mcp__sellable__get_subskill_prompt({ subskillName: "refill-sends" })\`,
    then load \`mcp__sellable__get_subskill_prompt({ subskillName: "refill-sends-workflow" })\`.

package/lib/runtime-verify.mjs

@@ -31,6 +31,7 @@ export const REQUIRED_SELLABLE_MCP_TOOLS = [
   "resolve_campaign_fill_route",
   "get_campaign_refill_state",
   "get_refill_target_plan",
+  "get_scheduler_fill_capacity",
   "refill_sends",
   "setup_evergreen_campaigns",
   "start_campaign_message_preparation",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/install",
-  "version": "0.1.294",
+  "version": "0.1.296",
   "type": "module",
   "description": "One-command installer for Sellable MCP in Claude Code and Codex",
   "bin": {

package/skill-templates/refill-sends.md

@@ -5,6 +5,7 @@ visibility: public
 allowed-tools:
   - mcp__sellable__refill_sends
   - mcp__sellable__get_refill_target_plan
+  - mcp__sellable__get_scheduler_fill_capacity
   - mcp__sellable__refresh_paid_inmail_credits
   - mcp__sellable__get_auth_status
   - mcp__sellable__start_cli_login
@@ -71,16 +72,21 @@ Accepted invocation flags in the same user request:
   senders.
 - `--until <YYYY-MM-DD>`: fill through that sender-local date, inclusive,
   instead of the default scheduler-forward 48-hour target window.
+- `--target-date <YYYY-MM-DD>`: fill only that sender-local date. This means
+  prepare rows for scheduler-fillable slots on that date, not every remaining
+  daily-limit slot and not an inclusive through-date.
 - `senderIds: <id>, <id>` or `senderNames: <name>, <name>`: explicit selector
   alternatives when the host preserves natural-language arguments better than
   shell-style flags.
 - `untilDate: YYYY-MM-DD`: explicit date selector alternative when the host
   preserves natural-language arguments better than shell-style flags.
+- `targetDate: YYYY-MM-DD`: exact-date selector alternative when the host
+  preserves natural-language arguments better than shell-style flags.
 
 When the host can call typed MCP tools, start with:
 
 ```text
-refill_sends({ yolo?: boolean, senders?: string[], senderIds?: string[], senderNames?: string[], horizonSendDays?: number, untilDate?: "YYYY-MM-DD" })
+refill_sends({ yolo?: boolean, senders?: string[], senderIds?: string[], senderNames?: string[], horizonSendDays?: number, untilDate?: "YYYY-MM-DD", targetDate?: "YYYY-MM-DD" })
 ```
 
 That command helper only normalizes arguments and returns the execution
@@ -137,6 +143,44 @@ two lanes to fill. If a stale target plan selects `send_dm` or
 `send_inmail_open`, stop and re-plan with the current planner before mutation.
 Short form: trust the target plan's inferred lane only when it is a
 connection-invite or paid-InMail refill lane.
+
+Structured planner packet:
+
+- `target.eligibleSenderLedger` is the public sender eligibility ledger.
+- `target.senderRefillPlans[]` is the canonical sender-level packet; read and
+  display it before mutation.
+- Each sender packet includes `campaignRanking.options`, `sourcePlan`,
+  `nextActions`, and `manualAlternates`.
+- Preserve these coverage labels exactly: `Need to prepare`, `Goal`,
+  `Already sent`, `Scheduled`, `Ready and waiting to be scheduled`, and
+  `Still need`.
+- `target.globalActionQueue` is the only cross-sender yolo execution queue.
+  Execute exactly one globally ranked primitive from
+  `target.globalActionQueue[0]`, then rerun `get_refill_target_plan` before
+  choosing another action.
+- `manualAlternates` are not yolo actions. Threshold lowering and campaign
+  creation are manual continuations only.
+
+Run-local paid-credit guard: maintain a `refreshedPaidInmailSenderIds` set for
+the current command call. Refresh each selected sender at most once per refill
+command call, then rerun `get_refill_target_plan`. If fresh facts are still
+below threshold, below-threshold paid-InMail facts fall back to an existing
+connection lane or a manual continuation.
+
+Compact refill lessons: sender-level target plan is final truth; trust
+`schedulerGate.sendable` and scheduler gate blockers, not raw
+`unipileAccountStatus` labels alone; use compact prep status checks for
+long-running jobs; reread target plans after prep or cancel; treat ready rows as
+intermediate; avoid huge parallel target-plan reads when output is large. If a
+campaign produces prepared/ready rows but sender-level projected coverage does
+not move after one bounded settle loop, pivot to compact prep status or a
+scheduler-proven lane. Do not keep waiting on campaign-level ready counts.
+
+For exact-date requests, pass `targetDate` to `get_refill_target_plan`. If you
+need raw proof, call the read-only `get_scheduler_fill_capacity` query for the
+same sender/action/date; it tells the MCP how many cells the product scheduler
+will try to place and does not import, approve, schedule, refresh credits, or
+mutate.
 If the target plan is complete by projected coverage, report that the selected
 target is already filled and no-op without asking for approval. If the ready
 buffer covers the projected gap but scheduled coverage is still short, keep the
@@ -149,10 +193,11 @@ state, not a close-out condition.
 If paid InMail credit facts are stale or missing and the target plan returns a
 `refresh_paid_inmail_credits` action candidate, include the exact sender id,
 campaign/table/column proof, expected sender-credit-cache writes, and rerun plan
-step in the bounded packet. After `refresh_paid_inmail_credits`, rerun
-`get_refill_target_plan` before any prep/import/approval/start action. If paid
-InMail is below threshold after a fresh credit read, report the exact
-campaign/table/column threshold action or connection fallback; `--yolo` does not lower paid-InMail thresholds or create campaigns.
+step in the bounded packet. In `--yolo`, refresh each exact selected sender at
+most once for the current refill run, then rerun `get_refill_target_plan` before
+any prep/import/approval/start action. If paid InMail is below threshold after a
+fresh credit read, report the exact campaign/table/column threshold action or
+connection fallback; `--yolo` does not lower paid-InMail thresholds or create campaigns.
 
 If the plain route's managed waterfall targets are stale, for example skipped
 targets show archived/completed shared slots or the returned targets do not cover
@@ -208,7 +253,7 @@ apply/prep/start result, reread state, settle processing when needed, and move t
 the next selected sender or start-eligible same-packet campaign instead of
 stopping after the first partial result. If no in-packet safe action remains,
 return concrete continuation options with campaign names, exact ids, which option
-is already covered by the current packet, and which option needs a new approval
+is still covered by the current packet, and which option needs a new approval
 packet.
 
 For `--yolo` fill/schedule requests, completion means projected saturation
@@ -229,8 +274,10 @@ blocked only because it is still `awaiting_scheduler_after_ready_buffer`; keep
 waiting unless Christian stops the run or the host cannot continue.
 
 In `--yolo`, the default fill target is the scheduler-forward 48-hour window
-unless `--until`/`untilDate` or an explicit compatibility `horizonSendDays` is
-provided. If an until date is provided, compute bounded gaps through that
+unless `--target-date`/`targetDate`, `--until`/`untilDate`, or an explicit
+compatibility `horizonSendDays` is provided. If a target date is provided,
+compute bounded gaps for only that sender-local date using scheduler-fillable
+slots. If an until date is provided, compute bounded gaps through that
 sender-local date inclusive, skipping no-send days and never extending beyond
 that date without a new packet. For each target sender, compute the bounded gap
 from that sender's healthy daily capacity, existing future scheduler-owned