[WH-2099]

Summary

Closes #3916.

Adds claude-opus-5-5 with a 1M-token context, 128K-token output limit, always-on adaptive thinking, and a medium effort default, following the official specifications.
The model uses the existing adaptive-thinking, structured-output, task-budget, and automatic tool-choice paths.
Standard input/output pricing is $4/$20 per million tokens, with cache reads charged at 5% of the input rate.

Signed-state replay and Agent tool-loop fixes are tracked in #4032 and draft PR #4034.
This model registration uses published dependencies and can be reviewed independently of that work.

Release Notes

• Add Claude Opus 5.5 with a 1M-token context window and 128K-token output limit.
• Support always-on adaptive thinking, medium reasoning effort by default, and summarized thinking display.
• Apply the model's prompt-cache read pricing.

Change Type

• LLM plugin

LLM Plugin Checklist

• Other LLM functionality (adaptive thinking and prompt-cache pricing)
• New models / model parameter fixes

Version

• Bumped the top-level manifest.yaml version to 0.3.34.
• Declared dify_plugin>=0.10.2,<0.11.0 and locked the published 0.10.2 release.
• Anthropic remains locked to 1.4.0.

Testing

• Clean Python 3.12.13 environment matching the manifest: uv run --frozen --python 3.12 pytest --ignore=tests/test_llm_live.py -q — 128 passed.
• Validated 23 model schemas, 16 ordered model IDs, plugin registration, and model discovery.
• Real Anthropic SDK requests through an HTTP mock verified adaptive thinking, effort, task-budget headers, structured output, and mixed cache usage pricing.
• uv lock --check and git diff --check passed.
• Dify CLI 0.6.10 packaged the committed plugin source successfully.
• Live API requests and a deployed Dify environment were not tested.

[Copilot]

Copilot review overview

🟡 Changes recommended

Empty truncated tool arguments can still be replayed, and opaque replay bypasses configured assistant prompt caching.

Get a fresh assessment by requesting another Copilot review.

Review effort: Balanced
Findings: 2

Open (2)

• Preserve truncated empty-buffer tool calls as incomplete · New
• Apply prompt-caching transformations to replayed stored blocks · New

What changed in this PR

Adds Claude Opus 5.5 support and replaces shared thinking state with per-message content replay.

Changes:

• Registers Opus 5.5 with updated capabilities, pricing, and adaptive-thinking defaults.
• Preserves ordered Anthropic content blocks across tool rounds.
• Refreshes dependencies, tests, documentation, and plugin metadata.

File	Description
models/​anthropic/​models/​llm/​llm.py	Implements model handling and content replay.
models/​anthropic/​models/​llm/​claude-opus-5-5.yaml	Defines Opus 5.5 capabilities and pricing.
models/​anthropic/​models/​llm/​_position.yaml	Adds the model to display ordering.
models/​anthropic/​tests/​test_thinking_replay.py	Tests ordered multi-turn replay and truncation.
models/​anthropic/​tests/​test_opus5_parameters.py	Tests Opus 5.5 schema and request parameters.
models/​anthropic/​tests/​test_llm.py	Tests classification and cache pricing.
models/​anthropic/​README.md	Documents Opus 5.5 behavior.
models/​anthropic/​pyproject.toml	Updates direct dependencies.
models/​anthropic/​uv.lock	Refreshes resolved dependencies.
models/​anthropic/​manifest.yaml	Bumps the plugin version.

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

[Copilot]

Copilot review overview

🔵 Needs a closer look

Empty truncated tool inputs can be executed, and opaque replay bypasses configured assistant caching.

Review effort: Balanced
Findings: 2

Open (2)

• Apply prompt-caching transformations to replayed stored blocks
• Preserve truncated empty-buffer tool calls as incomplete

[Copilot]

Copilot review overview

🟡 Changes recommended

Image retention is applied to every vision provider, regressing providers that only support images on the initial tool-loop request.

Get a fresh assessment by requesting another Copilot review.

Review effort: Balanced
Findings: 2

Open (2)

• Retain later-round images only for signed Anthropic prefix replays · New
• Preserve truncated empty-buffer tool calls as incomplete

Resolved since last review (1)

• Apply prompt-caching transformations to replayed stored blocks

[Copilot]

🟢 Approval recommended

The model registration, runtime handling, pricing adjustment, dependency metadata, and regression coverage are consistent and complete.

2 open findings

• Retain later-round images only for signed Anthropic prefix replays
• Preserve truncated empty-buffer tool calls as incomplete

🧠 Review effort: Balanced