feat: static system prompt with DynamicContextMiddleware for prefix-cache optimization (#2801)

* feat(middleware): inject dynamic context via DynamicContextMiddleware

Move memory and current date out of the system prompt and into a
dedicated <system-reminder> HumanMessage injected once per session
(frozen-snapshot pattern) via a new DynamicContextMiddleware.

This keeps the system prompt byte-exact across all users and sessions,
enabling maximum Anthropic/Bedrock prefix-cache reuse.

Key design decisions:
- ID-swap technique: reminder takes the first HumanMessage's ID
  (replacing it in-place via add_messages), original content gets a
  derived `{id}__user` ID (appended after). Preserves correct ordering.
- hide_from_ui: True on reminder messages so frontend filters them out.
- Midnight crossing: date-update reminder injected before the current
  turn's HumanMessage when the conversation spans midnight.
- INFO-level logging for production diagnostics.

Also adds prompt-caching breakpoint budget enforcement tests and
updates ClaudeChatModel docs to reference the new pattern.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(token-usage): log input/output token detail breakdown in middleware

Extend the LLM token usage log line to include input_token_details and
output_token_details (cache_creation, cache_read, reasoning, audio, etc.)
when present. Adds tests covering Anthropic cache detail logging from
both usage_metadata and response_metadata.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: fix nginx

* fix(middleware): always inject date; gate memory on injection_enabled

Date injection is now unconditional — it is part of the static system
prompt replacement and should always be present. Memory injection
remains gated by `memory.injection_enabled` in the app config.

Previously the entire DynamicContextMiddleware was skipped when
injection_enabled was False, which also suppressed the date.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix(lint): format files and correct test assertions for token usage middleware

- ruff format dynamic_context_middleware.py and test_claude_provider_prompt_caching.py
- Remove unused pytest import from test_dynamic_context_middleware.py
- Fix two tests that asserted response_metadata fallback logic that
  doesn't exist: replace with tests that match actual middleware behavior

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix(middleware): address Copilot review comments on DynamicContextMiddleware

- Use additional_kwargs flag for reminder detection instead of content
  substring matching, so user messages containing '<system-reminder>'
  are not mistakenly treated as injected reminders
- Generate stable UUID when original HumanMessage.id is None to prevent
  ambiguous 'None__user' derived IDs and message collisions
- Downgrade per-turn no-op log to DEBUG; keep actual injection events at INFO
- Add two new tests: missing-id UUID fallback and user-text false-positive

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
DanielWalnut
2026-05-09 09:27:02 +08:00
committed by GitHub
parent 109490da25
commit c1b7f1d189
8 changed files with 623 additions and 12 deletions
@@ -3,7 +3,6 @@ from __future__ import annotations
import asyncio
import logging
import threading
from datetime import datetime
from functools import lru_cache
from typing import TYPE_CHECKING
@@ -368,8 +367,6 @@ You are {agent_name}, an open-source super agent.
{soul}
{self_update_section}
{memory_context}
<thinking_style>
- Think concisely and strategically about the user's request BEFORE taking action
- Break down the task: What is clear? What is ambiguous? What is missing?
@@ -776,9 +773,6 @@ def apply_prompt_template(
available_skills: set[str] | None = None,
app_config: AppConfig | None = None,
) -> str:
# Get memory context
memory_context = _get_memory_context(agent_name, app_config=app_config)
# Include subagent section only if enabled (from runtime parameter)
n = max_concurrent_subagents
subagent_section = _build_subagent_section(n, app_config=app_config) if subagent_enabled else ""
@@ -812,18 +806,18 @@ def apply_prompt_template(
custom_mounts_section = _build_custom_mounts_section(app_config=app_config)
acp_and_mounts_section = "\n".join(section for section in (acp_section, custom_mounts_section) if section)
# Format the prompt with dynamic skills and memory
prompt = SYSTEM_PROMPT_TEMPLATE.format(
# Build and return the fully static system prompt.
# Memory and current date are injected per-turn via DynamicContextMiddleware
# as a <system-reminder> in the first HumanMessage, keeping this prompt
# identical across users and sessions for maximum prefix-cache reuse.
return SYSTEM_PROMPT_TEMPLATE.format(
agent_name=agent_name or "DeerFlow 2.0",
soul=get_agent_soul(agent_name),
self_update_section=_build_self_update_section(agent_name),
skills_section=skills_section,
deferred_tools_section=deferred_tools_section,
memory_context=memory_context,
subagent_section=subagent_section,
subagent_reminder=subagent_reminder,
subagent_thinking=subagent_thinking,
acp_section=acp_and_mounts_section,
)
return prompt + f"\n<current_date>{datetime.now().strftime('%Y-%m-%d, %A')}</current_date>"