# harness-sdk - Doramagic AI Context Pack

> Purpose: pre-work context for the user's host AI. This pack does not prove that the project has been installed, run, or validated.

## Project

- canonical_name: `strands-agents/harness-sdk`
- capability: A model-driven approach to building AI agents in just a few lines of code.
- expected_user_outcome: A model-driven approach to building AI agents in just a few lines of code.

## Operating Boundaries

- Do not claim that the project has been installed, run, called through an API, or used on local files unless separate evidence proves it.
- Project facts must come from repo evidence, Claim Graph, or explicit source references.
- When a capability is not verified, mark it as unverified instead of completing it as fact.
- publish_status: `publishable`
- blocking_gaps: none

---

## Doramagic Context Augmentation

The following sections strengthen the repository context for a host AI. Human Manual data is a reading route, and pitfall notes become operating constraints.

## Human Manual Outline

Usage rule: this is only a reading route and salience signal, not factual authority. Concrete claims must still return to repo evidence or Claim Graph.

Host AI hard rules:
- Do not treat page titles, section order, summaries, or importance values as factual project evidence.
- When explaining the Human Manual outline, state that it is only a reading route or salience signal.
- Capability, installation, compatibility, runtime state, and risk claims must cite repo evidence, source paths, or Claim Graph.

- **Monorepo Architecture & SDKs Overview**: importance `high`
  - source_paths: README.md, strands-py/src/strands/__init__.py, strands-ts/src/index.ts, strands-py/pyproject.toml, strands-ts/package.json
- **Agent Loop, Tools & Hooks**: importance `high`
  - source_paths: strands-py/src/strands/agent/agent.py, strands-py/src/strands/event_loop/event_loop.py, strands-py/src/strands/tools/decorator.py, strands-py/src/strands/tools/registry.py, strands-py/src/strands/tools/mcp/mcp_client.py
- **Model Providers & Multi-Agent Patterns**: importance `high`
  - source_paths: strands-py/src/strands/models/bedrock.py, strands-py/src/strands/models/anthropic.py, strands-py/src/strands/models/gemini.py, strands-py/src/strands/models/openai.py, strands-py/src/strands/models/openai_responses.py
- **Plugins, Bidirectional Streaming & WASM Interop**: importance `high`
  - source_paths: strands-py/src/strands/vended_plugins/skills/agent_skills.py, strands-py/src/strands/vended_plugins/skills/skill.py, strands-py/src/strands/vended_plugins/context_offloader/plugin.py, strands-py/src/strands/vended_plugins/context_offloader/storage.py, strands-py/src/strands/vended_plugins/steering/core/handler.py

## Repo Inspection Evidence

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `9c4fe1e110a408223719cb66eb814aa8f6007021`
- inspected_files: `README.md`, `package.json`, `pyproject.toml`

Host AI hard rules:
- Without repo_clone_verified=true, do not claim that the source code has been read.
- Without repo_inspection_verified=true, do not write README, docs, or package-file conclusions as facts.
- Without quick_start_verified=true, do not claim that the Quick Start path has run successfully.

## Doramagic Pitfall Constraints

These rules come from Doramagic discovery, validation, or compilation findings. The host AI must treat them as operating constraints, not background notes.

### Constraint 1: Installation risk requires verification

- Trigger: Project evidence flags a installation risk. Review the linked source before relying on this workflow.
- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.
- Why it matters: May increase setup, validation, or first-run risk for the user.
- Evidence: community_evidence:github | https://github.com/strands-agents/harness-sdk/issues/2748
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 2: Security or permission risk requires verification

- Trigger: Developers should check this security_permissions risk before relying on the project: [BUG] CacheConfig(strategy="auto") does not detect Claude models when using ARN-based inference profiles
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: [BUG] CacheConfig(strategy="auto") does not detect Claude models when using ARN-based inference profiles. Context: Observed when using python
- Why it matters: Developers may expose sensitive permissions or credentials: [BUG] CacheConfig(strategy="auto") does not detect Claude models when using ARN-based inference profiles
- Evidence: failure_mode_cluster:github_issue | https://github.com/strands-agents/harness-sdk/issues/2601
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 3: Security or permission risk requires verification

- Trigger: Project evidence flags a security or permission risk. Review the linked source before relying on this workflow.
- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.
- Why it matters: May increase setup, validation, or first-run risk for the user.
- Evidence: community_evidence:github | https://github.com/strands-agents/harness-sdk/issues/482
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 4: Identity risk requires verification

- Trigger: Project evidence flags a identity risk. Review the linked source before relying on this workflow.
- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.
- Why it matters: May increase setup, validation, or first-run risk for the user.
- Evidence: identity.distribution | https://github.com/strands-agents/harness-sdk
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 5: Installation risk requires verification

- Trigger: Developers should check this installation risk before relying on the project: [BUG] Gemini rejects tool results with multiple same-format images: duplicate displayName in function_response.parts (400 INVALID_ARGUMENT)
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: [BUG] Gemini rejects tool results with multiple same-format images: duplicate displayName in function_response.parts (400 INVALID_ARGUMENT). Context: Observed when using node, docker, macos, linux
- Why it matters: Developers may fail before the first successful local run: [BUG] Gemini rejects tool results with multiple same-format images: duplicate displayName in function_response.parts (400 INVALID_ARGUMENT)
- Evidence: failure_mode_cluster:github_issue | https://github.com/strands-agents/harness-sdk/issues/2748
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 6: Installation risk requires verification

- Trigger: Developers should check this installation risk before relying on the project: [BUG] OpenAIModel tool message content sent as array instead of string breaks OpenAI-compatible endpoints (e.g., Kimi K2.5)
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: [BUG] OpenAIModel tool message content sent as array instead of string breaks OpenAI-compatible endpoints (e.g., Kimi K2.5). Context: Observed when using python, macos
- Why it matters: Developers may fail before the first successful local run: [BUG] OpenAIModel tool message content sent as array instead of string breaks OpenAI-compatible endpoints (e.g., Kimi K2.5)
- Evidence: failure_mode_cluster:github_issue | https://github.com/strands-agents/harness-sdk/issues/1696
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 7: Installation risk requires verification

- Trigger: Developers should check this installation risk before relying on the project: python/v1.41.0
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: python/v1.41.0. Context: Observed when using python
- Why it matters: Upgrade or migration may change expected behavior: python/v1.41.0
- Evidence: failure_mode_cluster:github_release | https://github.com/strands-agents/harness-sdk/releases/tag/python/v1.41.0
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 8: Installation risk requires verification

- Trigger: Developers should check this installation risk before relying on the project: v1.41.0
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v1.41.0. Context: Observed when using python
- Why it matters: Upgrade or migration may change expected behavior: v1.41.0
- Evidence: failure_mode_cluster:github_release | https://github.com/strands-agents/harness-sdk/releases/tag/v1.41.0
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 9: Installation risk requires verification

- Trigger: Project evidence flags a installation risk. Review the linked source before relying on this workflow.
- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.
- Why it matters: May increase setup, validation, or first-run risk for the user.
- Evidence: community_evidence:github | https://github.com/strands-agents/harness-sdk/issues/1696
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 10: Installation risk requires verification

- Trigger: Project evidence flags a installation risk. Review the linked source before relying on this workflow.
- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.
- Why it matters: May increase setup, validation, or first-run risk for the user.
- Evidence: community_evidence:github | https://github.com/strands-agents/harness-sdk/issues/2614
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.