fix(showcase/aimock): drop stale turnIndex:0 gate from multi-turn D6 pill fixtures

D6 drives each feature's pills as sequential turns in one chat thread.
aimock matches turnIndex against the count of assistant messages in
history, so a "turnIndex": 0 gate on a per-pill tool-call leg only
matches the FIRST pill — pills 2+ (turnIndex 1/2/3) match no fixture,
503 under strict, and the harness reports "timeout: assistant did not
respond".

Remove the turnIndex:0 gate from the multi-turn tool-call legs of
frontend-tools (sunset/forest/cosmic) and tool-rendering-reasoning-chain
(the three chained pills: Compare AAPL/MSFT, compare-to-smaller dice,
weather-there flights) so they match on their distinct userMessage
substrings + context, mirroring the already-green langgraph-python
fixtures. Each pill's substring is unambiguous and its toolCallId-keyed
follow-up fixture is ordered before the de-gated first leg (first-match
wins), so follow-up narration still wins and there is no cross-matching.

The reasoning-chain "Find flights from SFO to JFK." pill keeps its
turnIndex:0 gate to match the green langgraph-python reference exactly.

Proven locally with aimock --strict: multi-turn requests for these pills
returned 503 with the gate (negative control) and now return 200 across
all turns with the correct fixture/narration.

Author: jpr5

showcase/aimock/d6/agno/frontend-tools.json

@@ -20,7 +20,6 @@
       "_comment": "frontend-tools 'Sunset' pill — 1st leg: emit change_background tool call only. NB: do NOT include `content` here. agent_framework_openai's ChatCompletions client splits an assistant message that carries BOTH `content` and `tool_calls` into two separate history entries (one with content, one with tool_calls), so on the follow-up leg aimock sees the standalone content message and re-matches THIS fixture by `userMessage` substring → another change_background tool call → infinite loop. The toolCallId-keyed follow-up fixture immediately above provides the post-tool narration text.",
       "match": {
         "userMessage": "Make the background a sunset gradient",
-        "turnIndex": 0,
         "context": "agno"
       },
       "response": {
@@ -49,7 +48,6 @@
       "_comment": "frontend-tools 'Forest' pill — 1st leg: emit change_background tool call only. See the Sunset fixture above for why we drop `content`.",
       "match": {
         "userMessage": "deep green forest gradient",
-        "turnIndex": 0,
         "context": "agno"
       },
       "response": {
@@ -78,7 +76,6 @@
       "_comment": "frontend-tools 'Cosmic' pill — 1st leg: emit change_background tool call only. See the Sunset fixture above for why we drop `content`.",
       "match": {
         "userMessage": "navy → magenta cosmic gradient",
-        "turnIndex": 0,
         "context": "agno"
       },
       "response": {
@@ -94,4 +91,4 @@
       }
     }
   ]
-}
+}

showcase/aimock/d6/agno/tool-rendering-reasoning-chain.json

@@ -40,7 +40,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 1 (stocks) — first leg: emit get_stock_price(AAPL). The `Compare AAPL and MSFT stocks` substring is unique to this demo's pill prompt — other integrations' reasoning-chain demos still send the older `How is AAPL doing?` prompt — so we don't need a tool-name gate and the fixture stays scoped to langgraph-python without affecting fleet-wide aimock traffic. MUST appear before the bare 'AAPL' fixtures later in this file.",
       "match": {
         "userMessage": "Compare AAPL and MSFT stocks",
-        "turnIndex": 0,
         "context": "agno"
       },
       "response": {
@@ -89,7 +88,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 2 (dice) — first leg: emit roll_dice(sides=20). Unique substring 'compare it to a smaller one' keeps us scoped to this demo (other integrations' dice pills still send 'Roll a 20-sided die for me.' and fall through to the older 5x roll_d20 fixtures further down). NB: aimock's `toolName` gate is a tool-LIST gate, not a tool-CALL gate; we don't use it here because the reasoning-chain agents across the fleet all register `roll_dice`, so a `toolName: roll_dice` claim would NOT have distinguished this demo from the others.",
       "match": {
         "userMessage": "compare it to a smaller one",
-        "turnIndex": 0,
         "context": "agno"
       },
       "response": {
@@ -138,7 +136,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 3 (flights + destination weather) — first leg: emit search_flights(SFO,JFK). The 'show me the weather there' substring is unique to this demo's pill, so the basic tool-rendering demo's bare 'Find flights from SFO to JFK.' prompt (and the equivalent prompts in other integrations' reasoning-chain demos that have not yet been ported to the chained phrasing) flow through to the basic single-tool flights fixture later in the file.",
       "match": {
         "userMessage": "show me the weather there",
-        "turnIndex": 0,
         "context": "agno"
       },
       "response": {
@@ -190,4 +187,4 @@
       }
     }
   ]
-}
+}

showcase/aimock/d6/built-in-agent/tool-rendering-reasoning-chain.json

@@ -40,7 +40,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 1 (stocks) — first leg: emit get_stock_price(AAPL). The `Compare AAPL and MSFT stocks` substring is unique to this demo's pill prompt — other integrations' reasoning-chain demos still send the older `How is AAPL doing?` prompt — so we don't need a tool-name gate and the fixture stays scoped to langgraph-python without affecting fleet-wide aimock traffic. MUST appear before the bare 'AAPL' fixtures later in this file.",
       "match": {
         "userMessage": "Compare AAPL and MSFT stocks",
-        "turnIndex": 0,
         "context": "built-in-agent"
       },
       "response": {
@@ -89,7 +88,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 2 (dice) — first leg: emit roll_dice(sides=20). Unique substring 'compare it to a smaller one' keeps us scoped to this demo (other integrations' dice pills still send 'Roll a 20-sided die for me.' and fall through to the older 5x roll_d20 fixtures further down). NB: aimock's `toolName` gate is a tool-LIST gate, not a tool-CALL gate; we don't use it here because the reasoning-chain agents across the fleet all register `roll_dice`, so a `toolName: roll_dice` claim would NOT have distinguished this demo from the others.",
       "match": {
         "userMessage": "compare it to a smaller one",
-        "turnIndex": 0,
         "context": "built-in-agent"
       },
       "response": {
@@ -138,7 +136,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 3 (flights + destination weather) — first leg: emit search_flights(SFO,JFK). The 'show me the weather there' substring is unique to this demo's pill, so the basic tool-rendering demo's bare 'Find flights from SFO to JFK.' prompt (and the equivalent prompts in other integrations' reasoning-chain demos that have not yet been ported to the chained phrasing) flow through to the basic single-tool flights fixture later in the file.",
       "match": {
         "userMessage": "show me the weather there",
-        "turnIndex": 0,
         "context": "built-in-agent"
       },
       "response": {
@@ -190,4 +187,4 @@
       }
     }
   ]
-}
+}

showcase/aimock/d6/claude-sdk-typescript/tool-rendering-reasoning-chain.json

@@ -40,7 +40,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 1 (stocks) — first leg: emit get_stock_price(AAPL). The `Compare AAPL and MSFT stocks` substring is unique to this demo's pill prompt — other integrations' reasoning-chain demos still send the older `How is AAPL doing?` prompt — so we don't need a tool-name gate and the fixture stays scoped to langgraph-python without affecting fleet-wide aimock traffic. MUST appear before the bare 'AAPL' fixtures later in this file.",
       "match": {
         "userMessage": "Compare AAPL and MSFT stocks",
-        "turnIndex": 0,
         "context": "claude-sdk-typescript"
       },
       "response": {
@@ -89,7 +88,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 2 (dice) — first leg: emit roll_dice(sides=20). Unique substring 'compare it to a smaller one' keeps us scoped to this demo (other integrations' dice pills still send 'Roll a 20-sided die for me.' and fall through to the older 5x roll_d20 fixtures further down). NB: aimock's `toolName` gate is a tool-LIST gate, not a tool-CALL gate; we don't use it here because the reasoning-chain agents across the fleet all register `roll_dice`, so a `toolName: roll_dice` claim would NOT have distinguished this demo from the others.",
       "match": {
         "userMessage": "compare it to a smaller one",
-        "turnIndex": 0,
         "context": "claude-sdk-typescript"
       },
       "response": {
@@ -138,7 +136,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 3 (flights + destination weather) — first leg: emit search_flights(SFO,JFK). The 'show me the weather there' substring is unique to this demo's pill, so the basic tool-rendering demo's bare 'Find flights from SFO to JFK.' prompt (and the equivalent prompts in other integrations' reasoning-chain demos that have not yet been ported to the chained phrasing) flow through to the basic single-tool flights fixture later in the file.",
       "match": {
         "userMessage": "show me the weather there",
-        "turnIndex": 0,
         "context": "claude-sdk-typescript"
       },
       "response": {
@@ -190,4 +187,4 @@
       }
     }
   ]
-}
+}

showcase/aimock/d6/crewai-crews/frontend-tools.json

@@ -20,7 +20,6 @@
       "_comment": "frontend-tools 'Sunset' pill — 1st leg: emit change_background tool call only. NB: do NOT include `content` here. agent_framework_openai's ChatCompletions client splits an assistant message that carries BOTH `content` and `tool_calls` into two separate history entries (one with content, one with tool_calls), so on the follow-up leg aimock sees the standalone content message and re-matches THIS fixture by `userMessage` substring → another change_background tool call → infinite loop. The toolCallId-keyed follow-up fixture immediately above provides the post-tool narration text.",
       "match": {
         "userMessage": "Make the background a sunset gradient",
-        "turnIndex": 0,
         "context": "crewai-crews"
       },
       "response": {
@@ -49,7 +48,6 @@
       "_comment": "frontend-tools 'Forest' pill — 1st leg: emit change_background tool call only. See the Sunset fixture above for why we drop `content`.",
       "match": {
         "userMessage": "deep green forest gradient",
-        "turnIndex": 0,
         "context": "crewai-crews"
       },
       "response": {
@@ -78,7 +76,6 @@
       "_comment": "frontend-tools 'Cosmic' pill — 1st leg: emit change_background tool call only. See the Sunset fixture above for why we drop `content`.",
       "match": {
         "userMessage": "navy → magenta cosmic gradient",
-        "turnIndex": 0,
         "context": "crewai-crews"
       },
       "response": {
@@ -94,4 +91,4 @@
       }
     }
   ]
-}
+}

showcase/aimock/d6/crewai-crews/tool-rendering-reasoning-chain.json

@@ -40,7 +40,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 1 (stocks) — first leg: emit get_stock_price(AAPL). The `Compare AAPL and MSFT stocks` substring is unique to this demo's pill prompt — other integrations' reasoning-chain demos still send the older `How is AAPL doing?` prompt — so we don't need a tool-name gate and the fixture stays scoped to langgraph-python without affecting fleet-wide aimock traffic. MUST appear before the bare 'AAPL' fixtures later in this file.",
       "match": {
         "userMessage": "Compare AAPL and MSFT stocks",
-        "turnIndex": 0,
         "context": "crewai-crews"
       },
       "response": {
@@ -89,7 +88,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 2 (dice) — first leg: emit roll_dice(sides=20). Unique substring 'compare it to a smaller one' keeps us scoped to this demo (other integrations' dice pills still send 'Roll a 20-sided die for me.' and fall through to the older 5x roll_d20 fixtures further down). NB: aimock's `toolName` gate is a tool-LIST gate, not a tool-CALL gate; we don't use it here because the reasoning-chain agents across the fleet all register `roll_dice`, so a `toolName: roll_dice` claim would NOT have distinguished this demo from the others.",
       "match": {
         "userMessage": "compare it to a smaller one",
-        "turnIndex": 0,
         "context": "crewai-crews"
       },
       "response": {
@@ -138,7 +136,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 3 (flights + destination weather) — first leg: emit search_flights(SFO,JFK). The 'show me the weather there' substring is unique to this demo's pill, so the basic tool-rendering demo's bare 'Find flights from SFO to JFK.' prompt (and the equivalent prompts in other integrations' reasoning-chain demos that have not yet been ported to the chained phrasing) flow through to the basic single-tool flights fixture later in the file.",
       "match": {
         "userMessage": "show me the weather there",
-        "turnIndex": 0,
         "context": "crewai-crews"
       },
       "response": {
@@ -190,4 +187,4 @@
       }
     }
   ]
-}
+}

showcase/aimock/d6/langgraph-fastapi/frontend-tools.json

@@ -20,7 +20,6 @@
       "_comment": "frontend-tools 'Sunset' pill — 1st leg: emit change_background tool call only. NB: do NOT include `content` here. agent_framework_openai's ChatCompletions client splits an assistant message that carries BOTH `content` and `tool_calls` into two separate history entries (one with content, one with tool_calls), so on the follow-up leg aimock sees the standalone content message and re-matches THIS fixture by `userMessage` substring → another change_background tool call → infinite loop. The toolCallId-keyed follow-up fixture immediately above provides the post-tool narration text.",
       "match": {
         "userMessage": "Make the background a sunset gradient",
-        "turnIndex": 0,
         "context": "langgraph-fastapi"
       },
       "response": {
@@ -49,7 +48,6 @@
       "_comment": "frontend-tools 'Forest' pill — 1st leg: emit change_background tool call only. See the Sunset fixture above for why we drop `content`.",
       "match": {
         "userMessage": "deep green forest gradient",
-        "turnIndex": 0,
         "context": "langgraph-fastapi"
       },
       "response": {
@@ -78,7 +76,6 @@
       "_comment": "frontend-tools 'Cosmic' pill — 1st leg: emit change_background tool call only. See the Sunset fixture above for why we drop `content`.",
       "match": {
         "userMessage": "navy → magenta cosmic gradient",
-        "turnIndex": 0,
         "context": "langgraph-fastapi"
       },
       "response": {
@@ -94,4 +91,4 @@
       }
     }
   ]
-}
+}

showcase/aimock/d6/langgraph-fastapi/tool-rendering-reasoning-chain.json

@@ -40,7 +40,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 1 (stocks) — first leg: emit get_stock_price(AAPL). The `Compare AAPL and MSFT stocks` substring is unique to this demo's pill prompt — other integrations' reasoning-chain demos still send the older `How is AAPL doing?` prompt — so we don't need a tool-name gate and the fixture stays scoped to langgraph-python without affecting fleet-wide aimock traffic. MUST appear before the bare 'AAPL' fixtures later in this file.",
       "match": {
         "userMessage": "Compare AAPL and MSFT stocks",
-        "turnIndex": 0,
         "context": "langgraph-fastapi"
       },
       "response": {
@@ -89,7 +88,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 2 (dice) — first leg: emit roll_dice(sides=20). Unique substring 'compare it to a smaller one' keeps us scoped to this demo (other integrations' dice pills still send 'Roll a 20-sided die for me.' and fall through to the older 5x roll_d20 fixtures further down). NB: aimock's `toolName` gate is a tool-LIST gate, not a tool-CALL gate; we don't use it here because the reasoning-chain agents across the fleet all register `roll_dice`, so a `toolName: roll_dice` claim would NOT have distinguished this demo from the others.",
       "match": {
         "userMessage": "compare it to a smaller one",
-        "turnIndex": 0,
         "context": "langgraph-fastapi"
       },
       "response": {
@@ -138,7 +136,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 3 (flights + destination weather) — first leg: emit search_flights(SFO,JFK). The 'show me the weather there' substring is unique to this demo's pill, so the basic tool-rendering demo's bare 'Find flights from SFO to JFK.' prompt (and the equivalent prompts in other integrations' reasoning-chain demos that have not yet been ported to the chained phrasing) flow through to the basic single-tool flights fixture later in the file.",
       "match": {
         "userMessage": "show me the weather there",
-        "turnIndex": 0,
         "context": "langgraph-fastapi"
       },
       "response": {
@@ -190,4 +187,4 @@
       }
     }
   ]
-}
+}

showcase/aimock/d6/langroid/frontend-tools.json

@@ -20,7 +20,6 @@
       "_comment": "frontend-tools 'Sunset' pill — 1st leg: emit change_background tool call only. NB: do NOT include `content` here. agent_framework_openai's ChatCompletions client splits an assistant message that carries BOTH `content` and `tool_calls` into two separate history entries (one with content, one with tool_calls), so on the follow-up leg aimock sees the standalone content message and re-matches THIS fixture by `userMessage` substring → another change_background tool call → infinite loop. The toolCallId-keyed follow-up fixture immediately above provides the post-tool narration text.",
       "match": {
         "userMessage": "Make the background a sunset gradient",
-        "turnIndex": 0,
         "context": "langroid"
       },
       "response": {
@@ -49,7 +48,6 @@
       "_comment": "frontend-tools 'Forest' pill — 1st leg: emit change_background tool call only. See the Sunset fixture above for why we drop `content`.",
       "match": {
         "userMessage": "deep green forest gradient",
-        "turnIndex": 0,
         "context": "langroid"
       },
       "response": {
@@ -78,7 +76,6 @@
       "_comment": "frontend-tools 'Cosmic' pill — 1st leg: emit change_background tool call only. See the Sunset fixture above for why we drop `content`.",
       "match": {
         "userMessage": "navy → magenta cosmic gradient",
-        "turnIndex": 0,
         "context": "langroid"
       },
       "response": {
@@ -94,4 +91,4 @@
       }
     }
   ]
-}
+}

showcase/aimock/d6/langroid/tool-rendering-reasoning-chain.json

@@ -40,7 +40,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 1 (stocks) — first leg: emit get_stock_price(AAPL). The `Compare AAPL and MSFT stocks` substring is unique to this demo's pill prompt — other integrations' reasoning-chain demos still send the older `How is AAPL doing?` prompt — so we don't need a tool-name gate and the fixture stays scoped to langgraph-python without affecting fleet-wide aimock traffic. MUST appear before the bare 'AAPL' fixtures later in this file.",
       "match": {
         "userMessage": "Compare AAPL and MSFT stocks",
-        "turnIndex": 0,
         "context": "langroid"
       },
       "response": {
@@ -89,7 +88,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 2 (dice) — first leg: emit roll_dice(sides=20). Unique substring 'compare it to a smaller one' keeps us scoped to this demo (other integrations' dice pills still send 'Roll a 20-sided die for me.' and fall through to the older 5x roll_d20 fixtures further down). NB: aimock's `toolName` gate is a tool-LIST gate, not a tool-CALL gate; we don't use it here because the reasoning-chain agents across the fleet all register `roll_dice`, so a `toolName: roll_dice` claim would NOT have distinguished this demo from the others.",
       "match": {
         "userMessage": "compare it to a smaller one",
-        "turnIndex": 0,
         "context": "langroid"
       },
       "response": {
@@ -138,7 +136,6 @@
       "_comment": "tool-rendering-reasoning-chain pill 3 (flights + destination weather) — first leg: emit search_flights(SFO,JFK). The 'show me the weather there' substring is unique to this demo's pill, so the basic tool-rendering demo's bare 'Find flights from SFO to JFK.' prompt (and the equivalent prompts in other integrations' reasoning-chain demos that have not yet been ported to the chained phrasing) flow through to the basic single-tool flights fixture later in the file.",
       "match": {
         "userMessage": "show me the weather there",
-        "turnIndex": 0,
         "context": "langroid"
       },
       "response": {
@@ -190,4 +187,4 @@
       }
     }
   ]
-}
+}