fix(office-hours): skip a last-session greeting clause whose value is empty

A profile backfilled from the timeline can carry a welcome_back or regular
tier with empty LAST_ASSIGNMENT and LAST_PROJECT. The welcome_back and
regular greetings now drop the "last time" clause and its question when the
value it names is empty, and say only "Welcome back."

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

CHANGELOG.md

@@ -13,7 +13,7 @@ Run `/gstack-upgrade`, then start `/office-hours` on a new idea. Before the doc
 ### Itemized changes
 
 #### Fixed
-- /office-hours reads your builder profile before it logs the session and carries the earlier tier, count and last assignment to the closing. This session is counted as the prior count plus one. If the profile can't be read, it treats the session as your first and tells you so. (#2801)
+- /office-hours reads your builder profile before it logs the session and carries the earlier tier, count and last assignment to the closing. This session is counted as the prior count plus one. If the profile can't be read, it treats the session as your first and tells you so. A returning greeting skips "last time" when the profile has no last assignment or project, and just says "Welcome back." (#2801)
 - /office-hours prints the complete design doc in the conversation before asking you to approve it. (#879)
 - /office-hours logs `success` only when this run's own design doc exists and isn't empty. It checks the doc's exact path under your gstack state root. A session that ends without a doc is logged as `abort` or `error` with failed step `design_doc`. (#1049)
 - `/plan-ceo-review`, `/plan-eng-review`, `/plan-devex-review` and `/autoplan` skip the "run /office-hours first?" offer in spawned and headless sessions, where nobody can answer it, and continue with the standard review. (#1958)

office-hours/sections/design-and-handoff.md

@@ -446,6 +446,9 @@ If CROSS_PROJECT is false (same project as last time):
 If CROSS_PROJECT is true (different project):
 "Welcome back. Last time we talked about [LAST_PROJECT]. Still on that, or onto something new?"
 
+If the value a greeting names (LAST_ASSIGNMENT or LAST_PROJECT) is empty, skip that clause and
+its question and say only "Welcome back." Backfilled profiles can have a tier without them.
+
 Then: "No pitch this time. You already know about YC. Let's talk about your work."
 
 **Tone examples (prevent generic AI voice):**
@@ -468,6 +471,7 @@ Then proceed to Founder Resources below.
 Lead with recognition and session count.
 
 "Welcome back. This is session [PRIOR_SESSION_COUNT + 1]. Last time: [LAST_ASSIGNMENT]. How'd it go?"
+If LAST_ASSIGNMENT is empty, skip the "Last time" clause and its question.
 
 **Tone examples:**
 - GOOD: "You've been at this for 5 sessions now. Your designs keep getting sharper. Let me show you what I've noticed."

office-hours/sections/design-and-handoff.md.tmpl

@@ -292,6 +292,9 @@ If CROSS_PROJECT is false (same project as last time):
 If CROSS_PROJECT is true (different project):
 "Welcome back. Last time we talked about [LAST_PROJECT]. Still on that, or onto something new?"
 
+If the value a greeting names (LAST_ASSIGNMENT or LAST_PROJECT) is empty, skip that clause and
+its question and say only "Welcome back." Backfilled profiles can have a tier without them.
+
 Then: "No pitch this time. You already know about YC. Let's talk about your work."
 
 **Tone examples (prevent generic AI voice):**
@@ -314,6 +317,7 @@ Then proceed to Founder Resources below.
 Lead with recognition and session count.
 
 "Welcome back. This is session [PRIOR_SESSION_COUNT + 1]. Last time: [LAST_ASSIGNMENT]. How'd it go?"
+If LAST_ASSIGNMENT is empty, skip the "Last time" clause and its question.
 
 **Tone examples:**
 - GOOD: "You've been at this for 5 sessions now. Your designs keep getting sharper. Let me show you what I've noticed."

test/gen-skill-docs.test.ts

@@ -1999,6 +1999,16 @@ describe('office-hours closing reads the builder profile before logging the sess
     expectAbsent(tiers, ['[SESSION_COUNT]', 'from profile]'], 'tier paths');
   });
 
+  test('welcome_back and regular greetings drop a last-session clause whose value is empty', () => {
+    const welcomeBack = between(handoff, '### If TIER = welcome_back', '### If TIER = regular');
+    const regular = between(handoff, '### If TIER = regular', '### If TIER = inner_circle');
+    expectTokens(welcomeBack, ['[LAST_ASSIGNMENT]', '[LAST_PROJECT]', '"Welcome back."'], 'welcome_back');
+    expectMentions(welcomeBack, [['last_assignment', 'last_project', 'empty', 'skip']], 'welcome_back');
+    expectOrdered(welcomeBack, ['Last time we talked about [LAST_PROJECT]', 'empty'], 'welcome_back');
+    expectTokens(regular, ['Last time: [LAST_ASSIGNMENT]'], 'regular');
+    expectMentions(regular, [['last_assignment', 'empty', 'skip']], 'regular');
+  });
+
   test('executing the rendered blocks in order: a first session reads introduction, a failed read is marked', () => {
     const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'oh-tier-'));
     try {

test/helpers/carve-guards.ts

@@ -353,7 +353,7 @@ do not launch the downstream skill or open a browser.`,
     maxSkeletonBytes: 94_900, // Office-hours + sketch outside voices include host guards and completion checks. + v1.91.19.0 wave: Q<N> open-question prose form (#2729, approved Q3), DESIGN_READY --version probe (B4), Aside ~/.local/bin fallback (E7), verdict-form outside voice (INV-1), plus v1.91.17.0's round accounting (#3022) merged in; measured 89,684 (2026-10-03). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); skeleton measured 92,590 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; skeleton measured 92,869 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; skeleton measured 92,930 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; skeleton measured 92,756 (2026-10-07). Merged with the guard area: measured skeleton 93,099 (2026-10-07). + fix wave PR D: the Phase 4.5 builder-profile read before the session log (#2801) and the pre-telemetry design-doc check (#1049); measured skeleton 94,877 (2026-10-07).
     minUnionBytes: 115_800, // Phase 4 wave 4; measured union 118,175
     mustContain: ['design doc', 'problem statement'],
-    maxSizeRatio: 1.1690, // + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); measured 149,758 / 131,110 = 1.1422 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; measured 150,037 / 131,110 = 1.1444 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; measured 150,098 / 131,110 = 1.1448 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; measured 150,011 / 131,110 = 1.1442 (2026-10-07). Merged with the guard area: measured 150,354 / 131,110 = 1.1468 (2026-10-07). + fix wave PR D: builder-profile read before the session log with Phase 6 using the carried values (#2801), the inline design doc before approval (#879) and the pre-telemetry design-doc check (#1049); measured 153,206 / 131,110 = 1.1685 (2026-10-07).
+    maxSizeRatio: 1.1710, // + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); measured 149,758 / 131,110 = 1.1422 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; measured 150,037 / 131,110 = 1.1444 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; measured 150,098 / 131,110 = 1.1448 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; measured 150,011 / 131,110 = 1.1442 (2026-10-07). Merged with the guard area: measured 150,354 / 131,110 = 1.1468 (2026-10-07). + fix wave PR D: builder-profile read before the session log with Phase 6 using the carried values (#2801), the inline design doc before approval (#879) and the pre-telemetry design-doc check (#1049); measured 153,206 / 131,110 = 1.1685 (2026-10-07). + empty LAST_ASSIGNMENT/LAST_PROJECT guards in the welcome_back and regular greetings (backfilled profiles); measured 153,469 / 131,110 = 1.1705 (2026-10-08).
   },
   'document-release': {
     skill: 'document-release',