🪟 Windows TippsThe Gemini desktop app is now available for Windows(11.09.2026 um 17:06 Uhr)
🕵️ SicherheitslückenBurn Out, Or Fade Away(14.09.2026 um 14:25 Uhr)
🪟 Windows TippsProfi-Edelstahlpfanne von WMF jetzt zum halben Preis erhältlich(15.09.2026 um 08:05 Uhr)
🪟 Windows TippsThe Gemini desktop app is now available for Windows(11.09.2026 um 17:06 Uhr)
🕵️ SicherheitslückenBurn Out, Or Fade Away(14.09.2026 um 14:25 Uhr)
🪟 Windows TippsProfi-Edelstahlpfanne von WMF jetzt zum halben Preis erhältlich(15.09.2026 um 08:05 Uhr)

🔧 Programmierung 🕛 vor 4 Monaten 28 Min Lesezeit
0

Designing Conversational Infrastructure for AI Agents: Context Forking, Rate Limiting, and Identity Rotation

↗ Quelle (dev.to)
🗣️ Stimme:
📑 Inhaltsübersicht

AI agents are becoming a new interface for handling inbound messages.



Instead of opening an inbox, scanning dozens of conversations, deciding which ones matter, and manually typing replies, a user can now say something like:




Check my recent messages for new leads.




In



The Lead Engagement process is the passive filtering pipeline. While the Search and Contact process proactively finds people, Lead Engagement handles the messages that have already arrived.



The agent analyses all recent messages and classifies each conversation into one of four actions:




























Scenario Action
Worth following up, fewer than 10 messages Reply in the current chat
Worth following up, 10 or more messages Compact the context and create a new chat with a reply
Not suitable for follow-up yet Take no action for now
Completely irrelevant (e.g., marketing spam) Quit the space to avoid being disturbed


This classification is not arbitrary. The 10-message threshold exists because long chat threads accumulate noise. An AI agent reading a 50-message thread must parse through greetings, tangents, and outdated context before finding the signal. By forking into a new chat at the 10-message mark, the agent compresses the history into a compact summary and starts fresh — a design choice we will revisit later.









The agent-side entry points



The Lead Engagement process exposes five functions to the AI agent. They are implemented in the skill's scripts/callable_functions.py file and communicate with QuestMeet through GraphQL.






Reading functions






CODE
def ai_read_messages(access_token: str, lookback_window: int = None) -> Union[list, bool, None]:
try:
response = httpx.post(
BASE_URL,
json={
"query": """
query AiReadMessages($lookbackWindow: Int) {
aiReadMessages(lookbackWindow: $lookbackWindow)
}
""",
"variables": {"lookbackWindow": lookback_window},
},
headers={"Authorization": f"Bearer {access_token}"},
trust_env=False,
timeout=20,
)
return response.json()["data"]["aiReadMessages"]
except Exception:
return False


def ai_read_chat_messages(access_token: str, space_id: str, chat_id: str) -> Union[dict, bool, None]:
try:
response = httpx.post(
BASE_URL,
json={
"query": """
query AiReadChatMessages($spaceId: BigInt!, $chatId: BigInt!) {
aiReadChatMessages(spaceId: $spaceId, chatId: $chatId)
}
""",
"variables": {"spaceId": space_id, "chatId": chat_id},
},
headers={"Authorization": f"Bearer {access_token}"},
trust_env=False,
timeout=20,
)
return response.json()["data"]["aiReadChatMessages"]
except Exception:
return False









Writing functions






CODE
def ai_create_message(access_token: str, space_id: str, chat_id: str, content: str) -> Union[bool, None]:
try:
response = httpx.post(
BASE_URL,
json={
"query": """
mutation AiCreateMessage($spaceId: BigInt!, $chatId: BigInt!, $content: String!) {
aiCreateMessage(spaceId: $spaceId, chatId: $chatId, content: $content)
}
""",
"variables": {"spaceId": space_id, "chatId": chat_id, "content": content},
},
headers={"Authorization": f"Bearer {access_token}"},
trust_env=False,
timeout=20,
)
return response.json()["data"]["aiCreateMessage"]
except Exception:
return False


def ai_create_chat_and_message(access_token: str, space_id: str, content: str) -> Union[bool, None]:
try:
response = httpx.post(
BASE_URL,
json={
"query": """
mutation AiCreateChatAndMessage($spaceId: BigInt!, $content: String!) {
aiCreateChatAndMessage(spaceId: $spaceId, content: $content)
}
""",
"variables": {"spaceId": space_id, "content": content},
},
headers={"Authorization": f"Bearer {access_token}"},
trust_env=False,
timeout=20,
)
return response.json()["data"]["aiCreateChatAndMessage"]
except Exception:
return False









Cleanup function






CODE
def ai_quit_spaces(access_token: str, space_ids: list[str]) -> Union[bool, None]:
try:
response = httpx.post(
BASE_URL,
json={
"query": """
mutation AiQuitSpaces($spaceIds: [BigInt!]!) {
aiQuitSpaces(spaceIds: $spaceIds)
}
""",
"variables": {"spaceIds": space_ids},
},
headers={"Authorization": f"Bearer {access_token}"},
trust_env=False,
timeout=20,
)
return response.json()["data"]["aiQuitSpaces"]
except Exception:
return False









Return value semantics



All five functions share the same return value contract:




























Return value Meaning

list[dict] / dict / True
The operation succeeded
[] The read succeeded, but no relevant messages were found
None The access token is missing or expired; the agent should re-authenticate
False Something failed; notify the user and stop


This contract is critical because the agent, not the server, owns the workflow. If the token is expired, the skill instructs the agent to run the sign-in process, obtain a new token, and retry. The server never attempts to redirect or refresh — it simply returns None and lets the agent decide.









The data model



The Lead Engagement functions touch five tables:




  1. users

  2. spaces


  3. members / copy_members

  4. chats

  5. messages



Here is the simplified relationship:



Vollständiger Original-Bericht
Ausführliche Details, Code-Beispiele & Hersteller-Stellungnahme auf dev.to.
↗ Original-Artikel auf dev.to lesen
Wie bewertest du diesen Beitrag?
1 Klick Feedback
Teilen mit Netzwerk & Team:

Community-Analysen & Experten-Meinungen 0

Verfasse deine eigene Analyse, teile Workarounds oder diskutiere diesen Vorfall im Blog.
Noch keine Community-Analyse verfasst. Markiere einen Textabschnitt oder klicke oben auf Eigene Analyse verfassen“!
Community Pulse: Relevanz-Einschätzung
1 Klick Experten-Votum
🔴 Akute Relevanz 0%
🟡 In Evaluierung 0%
🟢 Keine Auswirkung 0%
Spannende Innovation 0%
Verwandte Story-Cluster & Quellen (Vektor-KI)
Port 8095 Engine
1 Quelle
The Gemini desktop app is now available for Windows
1 Quelle
Burn Out, Or Fade Away
1 Quelle
Windows 11 KB5129195 is out after Microsoft confirms major issues with the September 2026 update, but it won’t fix AMD GPU errors
Ähnliche Beiträge
🔍 Verwandte News

Auch interessante Nachrichten Designing Conversational Infrastructure for AI Agents: Context Forking, Rate Limiting, and Identity Rotation

Thematisch verwandte Begriffe: Designing, Conversational, Infrastructure, Agents · 6 Treffer

Laden...

Videos werden geladen ...

Laden...

Beiträge werden geladen ...

Laden...

Videos werden geladen ...

Laden...

Beiträge werden geladen ...

Laden...

Videos werden geladen ...

Laden...

Beiträge werden geladen ...

Laden...

Videos werden geladen ...

Laden...

Beiträge werden geladen ...

Laden...

Videos werden geladen ...