The Conversation Prune API from WritersLogic Verifiable AI Agent Hub — 1 operation(s) for conversation prune.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/writerslogic-com:writerslogic-com-conversation-prune-api"curl "https://apis.io/api/v1/apis?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: WritersLogic Verifiable AI Agent Hub Conversation Prune API
version: 2.0.0
description: Pay-per-call agents settled in USDC on Base via x402. Every response carries a signed provenance envelope.
contact:
name: WritersLogic
url: https://writerslogic.com/agents
email: agents@writerslogic.com
servers:
- url: https://agents.writerslogic.com
tags:
- name: Conversation Prune
paths:
/api/v1/conversation-prune:
post:
operationId: conversation_prune
summary: Choose which old messages to drop to hit a token target without touching the…
description: 'Given a conversation, the index of the last message inside the provider''s cached prefix, and a token target, returns which messages to drop: whole tool call plus tool result pairs (so no result is left without its call) and messages the caller marked droppable, oldest first or largest first, never inside the cached prefix, never the most recent keepRecent messages, never pinned ones. Everything up to the cache breakpoint stays byte-identical because it is never selected; the response carries a digest of that prefix so a later call can confirm it did not change. Does not summarize, edit or reorder messages, and does not know any provider''s minimum cacheable size or TTL.
Price: 0.005 USDC on Base (x402).'
x-x402-price-usdc: '0.005'
x-x402-amount: '5000'
x-payment-info:
protocols:
- x402
price:
mode: fixed
currency: USD
amount: '0.005'
x-audience: agent-infra
x-sample-url: https://agents.writerslogic.com/api/v1/samples/conversation-prune
security:
- x402: []
- apiKey: []
requestBody:
required: true
content:
application/json:
schema:
type: object
additionalProperties: false
required:
- messages
- cacheBreakpoint
- targetTokens
properties:
messages:
type: array
items:
type: object
additionalProperties: false
properties:
id:
type: string
maxLength: 100
role:
type: string
maxLength: 32
minLength: 1
description: user, assistant, tool, system, ...
kind:
type: string
enum:
- text
- tool_call
- tool_result
description: 'tool_call: assistant message holding a tool call; tool_result: its output. Pairs are matched by toolCallId. Default text.'
toolCallId:
type: string
maxLength: 200
description: Pairs a tool_call with its tool_result.
content:
type: string
maxLength: 100000
description: Message text, used only to count tokens when tokens is absent.
tokens:
type: integer
minimum: 0
maximum: 100000000
description: Caller-supplied token count; always accepted.
pinned:
type: boolean
description: Never dropped.
droppable:
type: boolean
description: A text message that may be dropped (tool pairs are droppable by default).
required:
- role
maxItems: 500
minItems: 1
description: Up to 500; 400000 characters of content in total.
cacheBreakpoint:
type: integer
minimum: -1
maximum: 499
description: Index of the last message inside the cached prefix; -1 when nothing is cached.
targetTokens:
type: integer
minimum: 0
maximum: 100000000
description: Total tokens to get at or under.
keepRecent:
type: integer
minimum: 0
maximum: 100
description: Most recent messages that are never dropped. Default 4.
strategy:
type: string
enum:
- oldest-first
- largest-first
description: Order in which droppable units are removed. Default oldest-first.
tokenizer:
type: string
maxLength: 64
description: o200k_base or cl100k_base. Any other name (including Claude models) returns status unsupported for items that need counting; caller token counts are always accepted.
example:
messages:
- role: system
content: You are a support agent.
tokens: 400
- role: user
content: Look up order 1042.
tokens: 20
- role: assistant
kind: tool_call
toolCallId: t1
tokens: 30
- role: user
kind: tool_result
toolCallId: t1
tokens: 6000
- role: assistant
content: Order 1042 shipped.
tokens: 15
- role: user
content: Thanks. Now order 1043.
tokens: 20
cacheBreakpoint: 1
targetTokens: 1000
keepRecent: 2
responses:
'200':
description: Paid result with provenance
content:
application/json:
schema:
type: object
properties:
data:
type: object
properties:
status:
type: string
enum:
- pass
- fail
- unknown
- unsupported
description: 'pass: every rule held. fail: a rule was violated (see witnesses). unknown: the input lacks the evidence to decide. unsupported: outside what this engine covers. Missing evidence is never a pass.'
keep:
type: array
items:
type: integer
maxItems: 500
description: Indices of messages to keep, ascending.
dropped:
type: array
items:
type: object
additionalProperties: false
properties:
index:
type: integer
id:
type: string
role:
type: string
kind:
type: string
tokens:
type: integer
reason:
type: string
enum:
- stale-tool-pair
- droppable
pairedWith:
type: integer
maxItems: 500
tokensBefore:
type: integer
tokensAfter:
type: integer
targetMet:
type: boolean
prefix:
type: object
additionalProperties: false
properties:
messages:
type: integer
tokens:
type: integer
sha256:
type: string
description: SHA-256 of the RFC 8785 canonical JSON of the prefix messages exactly as supplied.
notes:
type: array
items:
type: string
maxItems: 20
witnesses:
type: array
items:
type: object
properties:
ruleId:
type: string
detail:
type: string
path:
type: string
description: JSON pointer or dotted path into the input.
offset:
type: integer
index:
type: integer
expected:
description: What the rule required.
actual:
description: What the input had.
versions:
type: object
description: Every semantic dependency of this answer (engine, tables and their as-of dates, tokenizer, calendar, rounding profile).
limits:
type: array
items:
type: string
deterministic:
type: boolean
description: 'Always true: pure code, no model.'
_provenance:
type: object
description: C2PA-aligned manifest and W3C VC 2.0 (eddsa-jcs-2022) issued by the hub DID; verify at POST /api/v1/verify-provenance
required:
- data
- _provenance
'400':
description: Invalid request (no payment consumed)
content:
application/json:
schema:
type: object
properties:
error:
type: string
code:
type: string
'401':
description: Invalid X-API-KEY
content:
application/json:
schema:
type: object
properties:
error:
type: string
code:
type: string
'402':
description: Payment required or invalid
content:
application/json:
schema:
type: object
description: x402 v2 PaymentRequired (also base64 in the PAYMENT-REQUIRED header)
properties:
x402Version:
type: integer
error:
type: string
code:
type: string
resource:
type: object
accepts:
type: array
items:
type: object
extensions:
type: object
'502':
description: Upstream failure; the payment is released or not settled
content:
application/json:
schema:
type: object
properties:
error:
type: string
code:
type: string
tags:
- Conversation Prune
components:
securitySchemes:
x402:
type: apiKey
in: header
name: PAYMENT-SIGNATURE
description: x402 v2 payment payload (base64) sent after a 402 challenge
apiKey:
type: apiKey
in: header
name: X-API-KEY