docs: fix 30 documentation inaccuracies found by source code audit (#697)

* docs: fix 30 documentation inaccuracies found by source code audit

- configuration.md: fix networkMode PRIVATE→VPC, remove stale mcp.json
  section, add 7 missing AgentEnvSpec fields, add Node.js runtimes,
  fix gateway name max 63→100, list all 6 targetType values, fix memory
  strategies wording, fix deployed-state.json path, add missing project
  fields, fix CUSTOM_JWT field requirements, add customClaims field
- README.md: add CrewAI framework, update all 4 default model IDs,
  add missing command sections
- frameworks.md: add CrewAI with model providers, add protocol
  compatibility matrix (HTTP/MCP/A2A)
- commands.md: fix agent name max 64→48 chars, add fetch access section,
  add policy-engine/policy to status --type, remove ghost
  --tool-filter-description flag, fix model ID date
- gateway.md: add enableSemanticSearch/exceptionLevel config options,
  fix mcp.json→agentcore.json, remove api-key from MCP Server auth
- transaction_search.md: fix traces command syntax
- container-builds.md: remove nonexistent --progress flag
- evals.md: fix model date 20250929→20250514
- local-development.md: fix mcp.json→agentcore.json
- AGENTS.md: remove AutoGen, remove stale mcp.json reference
- src/assets/README.md: add CrewAI to template list
- src/assets/agents/AGENTS.md: remove AutoGen

Constraint: All fixes verified against Zod schemas and CLI runtime
Constraint: CLI --help text bugs left for separate agent
Confidence: high
Scope-risk: narrow

* style: run prettier on documentation files

* test: update asset snapshots for edited README.md and AGENTS.md

* ci: trigger build workflow

* docs: update docs for upstream schema refactor and naming unification

- Remove `type` fields from agent, memory, evaluator, online-eval-config
  examples and field tables (removed in #709)
- Remove `modelProvider` from agent spec (removed in #709)
- Rename credential `type` to `authorizerType` (renamed in #709)
- Rename `add identity` to `add credential` everywhere (#705)
- Replace `--force` with `-y/--yes` on remove commands (#705)
- Replace `--plan` with `--dry-run` on deploy command (#705)
- Update snapshot for src/assets/README.md change

* docs: fix stale agents reference in gateway example

Update `"agents": [...]` to `"runtimes": [...]` in the gateway
configuration example to match the schema rename in #706.

* docs: rename --agent flags to --runtime and remove stale type fields

Update all documentation to reflect upstream renames:
- --agent → --runtime, -a → -r across all commands
- --agent-arn → --runtime-arn, --agent-runtime-id → --runtime-id
- Remove stale "type" fields from JSON examples in evals.md,
  memory.md, and container-builds.md

Constraint: --agent-id, --agent-alias-id, --agent-client-id,
  --agent-client-secret are unchanged (different semantics)
Constraint: --type agent filter value in status/fetch stays as-is
Confidence: high
Scope-risk: narrow

* docs: add missing flags and fix --lines → --limit

- Add -H, --header flag to dev and invoke commands
- Add --bearer-token flag to invoke command
- Fix --lines → --limit in evals.md logs evals section

Confidence: high
Scope-risk: narrow

* docs: fix stale gateway flags and add missing CLI flags

- Rename --agent-client-id → --client-id, --agent-client-secret →
  --client-secret in gateway docs (naming unification #705)
- Add missing flags to add agent: --authorizer-type, --discovery-url,
  --allowed-audience, --allowed-clients, --allowed-scopes,
  --custom-claims, --client-id, --client-secret, --idle-timeout,
  --max-lifetime
- Add missing flags to create: --idle-timeout, --max-lifetime
- Add missing flags to add gateway: --runtimes, --custom-claims,
  --policy-engine, --policy-engine-mode
- Fix --exception-level values: NONE/ALL (was undocumented)

Confidence: high
Scope-risk: narrow

* docs: fix --exception-level valid values to NONE/DEBUG

The CLI help text says ALL but the schema (GatewayExceptionLevelSchema)
defines the valid values as NONE and DEBUG. Aligns commands.md with
gateway.md and the Zod schema.

* docs: fix stale fields and add flags from upstream v0.5–v0.7

- Remove stale "type": "AgentCoreMemory" from memory streaming example
- Add memory streaming flags: --delivery-type, --data-stream-arn,
  --stream-content-level, --stream-delivery-resources
- Add --exec to dev command flag table (Container agents)
- Add --skip-install to create command flag table
- Add --identity-name to fetch access flag table

Author: aidandaly24

AGENTS.md

@@ -31,10 +31,10 @@ These options are available on all commands:
 ## CLI Commands
 
 - `create` - Create new AgentCore project
-- `add` - Add resources (agent, memory, identity, evaluator, online-eval, gateway, gateway-target, policy-engine,
+- `add` - Add resources (agent, memory, credential, evaluator, online-eval, gateway, gateway-target, policy-engine,
   policy)
-- `remove` - Remove resources (agent, memory, identity, evaluator, online-eval, gateway, gateway-target, policy-engine,
-  policy, all)
+- `remove` - Remove resources (agent, memory, credential, evaluator, online-eval, gateway, gateway-target,
+  policy-engine, policy, all)
 - `deploy` - Deploy infrastructure to AWS
 - `status` - Check deployment status
 - `dev` - Local development server (CodeZip: uvicorn with hot-reload; Container: Docker build + run with volume mount)
@@ -68,10 +68,10 @@ These options are available on all commands:
 
 ## Primitives Architecture
 
-All resource types (agent, memory, identity, evaluator, online-eval, gateway, gateway-target, policy-engine, policy) are
-modeled as **primitives** -- self-contained classes in `src/cli/primitives/` that own the full add/remove lifecycle for
-their resource type. Resources support config-driven tagging via `agentcore.json` and `mcp.json`, with tags flowing
-through to deployed CloudFormation resources.
+All resource types (agent, memory, credential, evaluator, online-eval, gateway, gateway-target, policy-engine, policy)
+are modeled as **primitives** -- self-contained classes in `src/cli/primitives/` that own the full add/remove lifecycle
+for their resource type. Resources support config-driven tagging via `agentcore.json`, with tags flowing through to
+deployed CloudFormation resources.
 
 Each primitive extends `BasePrimitive` and implements: `add()`, `remove()`, `previewRemove()`, `getRemovable()`,
 `registerCommands()`, and `addScreen()`.
@@ -80,7 +80,7 @@ Current primitives:
 
 - `AgentPrimitive` — agent creation (template + BYO), removal, credential resolution
 - `MemoryPrimitive` — memory creation with strategies, removal
-- `CredentialPrimitive` — credential/identity creation, .env management, removal
+- `CredentialPrimitive` — credential creation, .env management, removal
 - `EvaluatorPrimitive` — custom evaluator creation/removal with cross-reference validation
 - `OnlineEvalConfigPrimitive` — online eval config creation/removal
 - `GatewayPrimitive` — gateway creation/removal

README.md

@@ -60,17 +60,18 @@ agentcore invoke
 | ------------------- | ----------------------------- |
 | Strands Agents      | AWS-native, streaming support |
 | LangChain/LangGraph | Graph-based workflows         |
+| CrewAI              | Multi-agent orchestration     |
 | Google ADK          | Gemini models only            |
 | OpenAI Agents       | OpenAI models only            |
 
 ## Supported Model Providers
 
-| Provider       | API Key Required          | Default Model                 |
-| -------------- | ------------------------- | ----------------------------- |
-| Amazon Bedrock | No (uses AWS credentials) | claude-sonnet-4-5-20250929-v1 |
-| Anthropic      | Yes                       | claude-sonnet-4-5-20250929    |
-| Google Gemini  | Yes                       | gemini-2.5-flash              |
-| OpenAI         | Yes                       | gpt-4o                        |
+| Provider       | API Key Required          | Default Model                                |
+| -------------- | ------------------------- | -------------------------------------------- |
+| Amazon Bedrock | No (uses AWS credentials) | us.anthropic.claude-sonnet-4-5-20250514-v1:0 |
+| Anthropic      | Yes                       | claude-sonnet-4-5-20250514                   |
+| Google Gemini  | Yes                       | gemini-2.5-flash                             |
+| OpenAI         | Yes                       | gpt-4.1                                      |
 
 ## Commands
 
@@ -85,13 +86,22 @@ agentcore invoke
 
 ### Resource Management
 
-| Command  | Description                                       |
-| -------- | ------------------------------------------------- |
-| `add`    | Add agents, memory, identity, evaluators, targets |
-| `remove` | Remove resources from project                     |
+| Command  | Description                                          |
+| -------- | ---------------------------------------------------- |
+| `add`    | Add agents, memory, credentials, evaluators, targets |
+| `remove` | Remove resources from project                        |
 
 > **Note**: Run `agentcore deploy` after `add` or `remove` to update resources in AWS.
 
+### Observability
+
+| Command       | Description                             |
+| ------------- | --------------------------------------- |
+| `logs`        | Stream or search agent runtime logs     |
+| `traces list` | List recent traces for a deployed agent |
+| `traces get`  | Download a trace to a JSON file         |
+| `status`      | Show deployed resource details          |
+
 ### Evaluations
 
 | Command              | Description                                   |
@@ -102,6 +112,16 @@ agentcore invoke
 | `evals history`      | View past eval run results                    |
 | `pause online-eval`  | Pause a deployed online eval config           |
 | `resume online-eval` | Resume a paused online eval config            |
+| `logs evals`         | Stream or search online eval logs             |
+
+### Utilities
+
+| Command        | Description                               |
+| -------------- | ----------------------------------------- |
+| `validate`     | Validate configuration files              |
+| `package`      | Package agent artifacts without deploying |
+| `fetch access` | Fetch access info for deployed resources  |
+| `update`       | Check for and install CLI updates         |
 
 ## Project Structure
 
@@ -129,15 +149,15 @@ my-project/
 
 Projects use JSON schema files in the `agentcore/` directory:
 
-- `agentcore.json` - Agent specifications, memory, identity, evaluators, online evals
+- `agentcore.json` - Agent specifications, memory, credentials, evaluators, online evals
 - `deployed-state.json` - Runtime state in agentcore/.cli/ (auto-managed)
 - `aws-targets.json` - Deployment targets (account, region)
 
 ## Capabilities
 
 - **Runtime** - Managed execution environment for deployed agents
 - **Memory** - Semantic, summarization, and user preference strategies
-- **Identity** - Secure API key management via Secrets Manager
+- **Credentials** - Secure API key management via Secrets Manager
 - **Evaluations** - LLM-as-a-Judge for on-demand and continuous agent quality monitoring
 
 ## Documentation