01-projects/phdata

CCDV-F study sheet: API mechanics, optimization and MCP (red/yellow topics)

2026-10-20·study-sheet·status: active·source: Live docs fetched 2026-10-20 (platform.claude.com, code.claude.com, modelcontextprotocol.io); exam guide v1.0 (July 2026) for scope
phdatacertanthropicccdv-foundationscert-prepcheat-sheet

CCDV-F study sheet (red and yellow topics)

Every fact below was checked against the live official docs on 2026-10-20 and carries its source link. Where current docs differ from what an exam written in July 2026 might key, the line is marked EXAM-LAG. On those items, answer from the scenario's model: if the stem names a current model (Opus 5.5, Sonnet 5.5, Haiku 5.5, Fable 5.1), use current behavior.

Practice quiz: [[2026-10-20-ccdv-f-quiz-1]] · interactive at https://ccdv-quiz.rdco.dev

See [[2026-10-20-ccdv-f-readiness]] for the full domain-by-domain readiness read and prep-plan ROI order this sheet backs.

0. Exam logistics (from the guide PDF)

1. Current models

Source: https://platform.claude.com/docs/en/about-claude/models/overview · https://platform.claude.com/docs/en/about-claude/pricing

Model API ID (= Google Cloud ID) Bedrock ID Input / output $ per MTok Cache read Default effort Thinking
Claude Fable 5.1 claude-fable-5-1 anthropic.claude-fable-5-1 10 / 50 0.025x high adaptive, always on
Claude Opus 5.5 claude-opus-5-5 anthropic.claude-opus-5-5 4 / 20 0.05x medium adaptive, always on
Claude Sonnet 5.5 claude-sonnet-5-5 anthropic.claude-sonnet-5-5 2 / 10 0.05x high adaptive; between_tools instead of disabled
Claude Haiku 5.5 claude-haiku-5-5 anthropic.claude-haiku-5-5 0.10 / 0.50 (prompts up to 100K); 0.50 / 2.50 above 0.1x medium adaptive; disabled only at effort high or below

2. Breaking-change matrix (the EXAM-LAG hot zone)

Setting Opus 5.5 Sonnet 5.5 Haiku 5.5 Fable 5.1 Source
thinking: {type: "enabled", budget_tokens} 400 400 400 400 extended-thinking ("Claude 4.7 and later models ... reject requests that use it")
thinking: {type: "disabled"} 400 400 (use between_tools) OK at effort high or below 400 thinking-troubleshooting
tool_choice any / tool 400 400 (even on count_tokens) allowed 400 thinking
Non-default temperature / top_p / top_k 400 400 400 400 api/messages
Assistant prefill 400 400 400 400 all Claude 4.6+ models
display default omitted omitted omitted omitted thinking

3. Thinking and effort

Sources: https://platform.claude.com/docs/en/build-with-claude/thinking · https://platform.claude.com/docs/en/build-with-claude/effort · https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking

4. Prompt caching

Source: https://platform.claude.com/docs/en/build-with-claude/prompt-caching

Change Tools System Messages
Tool definitions x x x
Web search toggle, citations toggle, speed (fast vs standard) kept x x
tool_choice, images added or removed kept kept x
Thinking parameters, output_config.effort model-specific model-specific x

5. Token counting

Source: https://platform.claude.com/docs/en/build-with-claude/token-counting

6. Streaming

Source: https://platform.claude.com/docs/en/build-with-claude/streaming

  1. message_start: a Message with empty content, stop_reason: null.
  2. Per block: content_block_start then one or more content_block_delta then content_block_stop. The block index matches its position in the final content array.
  3. One or more message_delta: carries stop_reason and cumulative usage.
  4. message_stop: always last.

7. Message Batches

Source: https://platform.claude.com/docs/en/build-with-claude/batch-processing

8. Vision and PDF

Sources: https://platform.claude.com/docs/en/build-with-claude/vision · https://platform.claude.com/docs/en/build-with-claude/pdf-support

9. Tool use, tool_choice, stop_reason

Sources: https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools · https://platform.claude.com/docs/en/agents-and-tools/tool-use/handle-tool-calls · https://platform.claude.com/docs/en/agents-and-tools/tool-use/parallel-tool-use · https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons

stop_reason Meaning Action
end_turn finished naturally use it
max_tokens hit your cap raise or continue; output truncated
stop_sequence hit one of your stop_sequences read stop_sequence
tool_use calling a tool run it, return tool_result
pause_turn server-tool loop limit send back to continue
refusal declined (HTTP 200) read stop_details.category; fallback model
model_context_window_exceeded filled the context window treat as truncated

stop_details is null except on refusal (category: cyber, bio, frontier_llm, reasoning_extraction, general_harms, or null).

10. Errors, retries, rate limits

Sources: https://platform.claude.com/docs/en/api/errors · https://platform.claude.com/docs/en/api/rate-limits · https://platform.claude.com/docs/en/cli-sdks-libraries/sdks/python

Code Type Retry?
400 invalid_request_error (also a spend limit you set) no, fix the request
401 authentication_error no
402 billing_error no
403 permission_error no
404 not_found_error no
409 conflict_error SDK retries
413 request_too_large no; shrink (Messages 32 MB, Batches 256 MB, Files 500 MB)
429 rate_limit_error yes, honor retry-after (a tier spend-cap 429 has no retry-after and keeps failing)
500 api_error yes, backoff
504 timeout_error yes; use streaming or Batches for long requests
529 overloaded_error yes, backoff; not your limits

11. Bedrock and Google Cloud

Sources: https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock · https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy · https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai

Bedrock (Opus 4.7+) Google Cloud (Vertex)
Client AnthropicBedrockMantle(aws_region=...) AnthropicVertex(project_id=..., region="global")
Endpoint bedrock-mantle.{region}.api.aws/anthropic/v1/messages ...:rawPredict, model in the URL
Model ID anthropic.claude-opus-5-5 claude-opus-5-5 (older: claude-haiku-4-5@20251001)
Auth AWS SigV4 credential chain, or bearer token GCP Application Default Credentials
Body version none on Mantle (legacy InvokeModel: bedrock-2023-05-31) anthropic_version: "vertex-2023-10-16"
Pricing note regional endpoints +10%; global no premium regional and multi-region +10%
Not supported URL/Files sources; code execution, web search, web fetch, advisor; Skills, MCP connector, programmatic tool calling; Message Batches, Models, Admin, Usage/Cost endpoints; Managed Agents; server-side fallbacks URL/Files sources; code execution, web fetch, advisor; Skills, MCP connector, programmatic tool calling; Message Batches, Models, Admin, Usage/Cost; Managed Agents; server-side fallbacks

12. MCP server authoring

Sources: https://modelcontextprotocol.io/specification/latest · https://modelcontextprotocol.io/specification/latest/basic/transports · https://modelcontextprotocol.io/docs/develop/build-server · https://modelcontextprotocol.io/specification/latest/changelog

Minimal Python server (official tutorial, current SDK):

# uv add "mcp[cli]"
from mcp.server import MCPServer

mcp = MCPServer("weather")

@mcp.tool()
async def get_alerts(state: str) -> str:
    """Get active weather alerts for a two-letter US state code."""
    return f"No alerts for {state}"

if __name__ == "__main__":
    mcp.run(transport="stdio")

EXAM-LAG: older tutorials import from mcp.server.fastmcp import FastMCP. TypeScript now uses @modelcontextprotocol/server with new McpServer({name, version}), server.registerTool(name, {description, inputSchema: z.object(...)}, handler) and serveStdio(...); hand-wiring server.connect(new StdioServerTransport()) "only serves 2025-era clients."

Using MCP from Claude:

13. Agent SDK, Managed Agents, Claude Code

Sources: https://code.claude.com/docs/en/agent-sdk/overview · https://code.claude.com/docs/en/agent-sdk/python · https://code.claude.com/docs/en/agent-sdk/migration-guide · https://platform.claude.com/docs/en/managed-agents/overview

14. Evals and debugging (Module 3 theme, D4)

Source: https://platform.claude.com/docs/en/test-and-evaluate/develop-tests

15. Docs-vs-exam watchlist (one line each)

  1. Opus 5.5 effort default is medium, not high.
  2. budget_tokens and thinking: disabled are 400s on current flagship models; budget_tokens is "legacy".
  3. Forced tool_choice (any/tool) is a 400 on Opus 5.5, Sonnet 5.5, Fable 5.1.
  4. Non-default temperature/top_p/top_k and assistant prefill are 400s on current models.
  5. Thinking display defaults to omitted.
  6. Cache: 512-token minimum on 5.x; reads 0.05x (Opus/Sonnet 5.5) and 0.025x (Fable 5.1); 1-hour TTL needs no header; workspace-level isolation.
  7. Vision 10 MB on the API; 28-px patch token formula. PDFs 600 pages on 1M-context requests.
  8. Errors list now includes 402, 409, 504.
  9. Bedrock: Mantle client and anthropic. IDs for 4.7+; Vertex IDs dateless for new models.
  10. MCP 2026-07-28: no initialize handshake, server/discover, sampling/roots/logging deprecated, Python MCPServer not FastMCP, no "sockets" transport.
  11. Course says start with Sonnet; docs say start with Opus 5.5.
  12. Reschedule notice: guide says 24h; reported FAQ says 48h (unverified); use 48h.
  13. Few-shot count: course says 1-2 examples; docs say 3-5 for best results.