@aws/agentcore 0.21.0 → 0.22.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (77) hide show
  1. package/README.md +17 -17
  2. package/dist/assets/__tests__/__snapshots__/assets.snapshot.test.ts.snap +531 -90
  3. package/dist/assets/__tests__/googleadk-session-eviction.test.ts +87 -0
  4. package/dist/assets/__tests__/summarization-namespace.test.ts +43 -0
  5. package/dist/assets/python/a2a/strands/capabilities/memory/session.py +1 -1
  6. package/dist/assets/python/agui/strands/capabilities/memory/session.py +1 -1
  7. package/dist/assets/python/http/autogen/base/main.py +33 -10
  8. package/dist/assets/python/http/googleadk/base/main.py +45 -8
  9. package/dist/assets/python/http/langchain_langgraph/base/main.py +46 -7
  10. package/dist/assets/python/http/openaiagents/base/main.py +19 -8
  11. package/dist/assets/python/http/strands/base/main.py +36 -29
  12. package/dist/assets/python/http/strands/base/mcp_client/client.py +4 -1
  13. package/dist/assets/python/http/strands/base/model/load.py +116 -0
  14. package/dist/assets/python/http/strands/base/model/mantle_compat.py +21 -0
  15. package/dist/assets/python/http/strands/base/pyproject.toml +3 -0
  16. package/dist/assets/python/http/strands/capabilities/memory/session.py +1 -1
  17. package/dist/assets/typescript/http/strands/base/main.ts +96 -18
  18. package/dist/assets/typescript/http/strands/base/package.json +3 -2
  19. package/dist/assets/typescript/http/strands/capabilities/memory/memory.ts +52 -0
  20. package/dist/assets/typescript/http/vercelai/base/main.ts +42 -2
  21. package/dist/cli/index.mjs +574 -608
  22. package/dist/lib/errors/types.d.ts +25 -0
  23. package/dist/lib/errors/types.d.ts.map +1 -1
  24. package/dist/lib/errors/types.js +40 -1
  25. package/dist/lib/errors/types.js.map +1 -1
  26. package/dist/lib/secrets/cipher.d.ts +12 -0
  27. package/dist/lib/secrets/cipher.d.ts.map +1 -0
  28. package/dist/lib/secrets/cipher.js +54 -0
  29. package/dist/lib/secrets/cipher.js.map +1 -0
  30. package/dist/lib/secrets/index.d.ts +4 -0
  31. package/dist/lib/secrets/index.d.ts.map +1 -0
  32. package/dist/lib/secrets/index.js +15 -0
  33. package/dist/lib/secrets/index.js.map +1 -0
  34. package/dist/lib/secrets/key-provider.d.ts +16 -0
  35. package/dist/lib/secrets/key-provider.d.ts.map +1 -0
  36. package/dist/lib/secrets/key-provider.js +191 -0
  37. package/dist/lib/secrets/key-provider.js.map +1 -0
  38. package/dist/lib/secrets/sensitive-keys.d.ts +21 -0
  39. package/dist/lib/secrets/sensitive-keys.d.ts.map +1 -0
  40. package/dist/lib/secrets/sensitive-keys.js +67 -0
  41. package/dist/lib/secrets/sensitive-keys.js.map +1 -0
  42. package/dist/lib/utils/env.d.ts +4 -2
  43. package/dist/lib/utils/env.d.ts.map +1 -1
  44. package/dist/lib/utils/env.js +57 -27
  45. package/dist/lib/utils/env.js.map +1 -1
  46. package/dist/schema/constants.d.ts +29 -2
  47. package/dist/schema/constants.d.ts.map +1 -1
  48. package/dist/schema/constants.js +41 -5
  49. package/dist/schema/constants.js.map +1 -1
  50. package/dist/schema/schemas/agent-env.d.ts +47 -2
  51. package/dist/schema/schemas/agent-env.d.ts.map +1 -1
  52. package/dist/schema/schemas/agent-env.js +34 -5
  53. package/dist/schema/schemas/agent-env.js.map +1 -1
  54. package/dist/schema/schemas/agentcore-project.d.ts +46 -1
  55. package/dist/schema/schemas/agentcore-project.d.ts.map +1 -1
  56. package/dist/schema/schemas/auth.d.ts +2 -3
  57. package/dist/schema/schemas/auth.d.ts.map +1 -1
  58. package/dist/schema/schemas/auth.js +8 -7
  59. package/dist/schema/schemas/auth.js.map +1 -1
  60. package/dist/schema/schemas/connections.d.ts +185 -0
  61. package/dist/schema/schemas/connections.d.ts.map +1 -0
  62. package/dist/schema/schemas/connections.js +176 -0
  63. package/dist/schema/schemas/connections.js.map +1 -0
  64. package/dist/schema/schemas/index.d.ts +1 -0
  65. package/dist/schema/schemas/index.d.ts.map +1 -1
  66. package/dist/schema/schemas/index.js +1 -0
  67. package/dist/schema/schemas/index.js.map +1 -1
  68. package/dist/schema/schemas/primitives/config-bundle.d.ts +1 -0
  69. package/dist/schema/schemas/primitives/config-bundle.d.ts.map +1 -1
  70. package/dist/schema/schemas/primitives/config-bundle.js +3 -0
  71. package/dist/schema/schemas/primitives/config-bundle.js.map +1 -1
  72. package/dist/schema/schemas/primitives/harness.d.ts +43 -0
  73. package/dist/schema/schemas/primitives/harness.d.ts.map +1 -1
  74. package/dist/schema/schemas/primitives/harness.js +20 -0
  75. package/dist/schema/schemas/primitives/harness.js.map +1 -1
  76. package/npm-shrinkwrap.json +223 -0
  77. package/package.json +4 -1
package/README.md CHANGED
@@ -93,11 +93,26 @@ agentcore invoke
93
93
 
94
94
  | Command | Description |
95
95
  | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
96
- | `add` | Add agents, memory, credentials, gateways and gateway-targets, evaluators, online evals, online insights, knowledge bases, config bundles, datasets, harnesses, policy engines and policies, payment managers and payment connectors, runtime endpoints |
96
+ | `add` | Add harnesses, agents, memory, credentials, gateways and gateway-targets, evaluators, online evals, online insights, knowledge bases, config bundles, datasets, policy engines and policies, payment managers and payment connectors, runtime endpoints |
97
97
  | `remove` | Remove any of the above resources from the project |
98
98
 
99
99
  > **Note**: Run `agentcore deploy` after `add` or `remove` to update resources in AWS.
100
100
 
101
+ ### Harness
102
+
103
+ A harness bundles a runtime, model, tools, skills, memory, and observability into one declarative config. Use it when
104
+ you want infra without writing agent code.
105
+
106
+ | Command | Description |
107
+ | ---------------- | --------------------------------------------------------------------------- |
108
+ | `add harness` | Add a harness resource (runtime + model + memory) |
109
+ | `add tool` | Add a tool to a harness (`--harness <name> --type <type> --name <name>`) |
110
+ | `add skill` | Add a skill to a harness (`--harness <name>` + `--path` / `--s3` / `--git`) |
111
+ | `export harness` | Export a harness config to a deployable Strands Python agent under `app/` |
112
+
113
+ > After `export harness`, **read `app/<agentName>/EXPORT_NOTES.md`** before running `deploy` — it lists any manual
114
+ > follow-up the exporter could not automate.
115
+
101
116
  ### Observability
102
117
 
103
118
  | Command | Description |
@@ -167,21 +182,6 @@ clusters of bad outcomes.
167
182
  | `resume online-insights` | Resume a paused online insights config |
168
183
  | `archive insights` | Delete an insights job on the service + clear local history |
169
184
 
170
- ### Harness
171
-
172
- A harness bundles a runtime, model, tools, skills, memory, and observability into one declarative config. Use it when
173
- you want infra without writing agent code.
174
-
175
- | Command | Description |
176
- | ---------------- | --------------------------------------------------------------------------- |
177
- | `add harness` | Add a harness resource (runtime + model + memory) |
178
- | `add tool` | Add a tool to a harness (`--harness <name> --type <type> --name <name>`) |
179
- | `add skill` | Add a skill to a harness (`--harness <name>` + `--path` / `--s3` / `--git`) |
180
- | `export harness` | Export a harness config to a deployable Strands Python agent under `app/` |
181
-
182
- > After `export harness`, **read `app/<agentName>/EXPORT_NOTES.md`** before running `deploy` — it lists any manual
183
- > follow-up the exporter could not automate.
184
-
185
185
  ### Policies & Guardrails
186
186
 
187
187
  Policy engines apply Cedar-based pre/post-call policies to agent invocations — including Bedrock content filters
@@ -271,6 +271,7 @@ Projects use JSON schema files in the `agentcore/` directory:
271
271
 
272
272
  ## Capabilities
273
273
 
274
+ - **Harness** - Declarative agent: bundle runtime + tools + skills + memory + observability without writing agent code
274
275
  - **Runtime** - Managed execution environment for deployed agents
275
276
  - **Memory** - Semantic, summarization, user-preference, and episodic strategies
276
277
  - **Credentials** - Secure API key + OAuth credential management via Secrets Manager
@@ -281,7 +282,6 @@ Projects use JSON schema files in the `agentcore/` directory:
281
282
  - **A/B Tests** - Traffic-split between config-bundle or target-based variants and promote the winner
282
283
  - **Insights** _[preview]_ - Failure-pattern analysis and clustering across agent sessions
283
284
  - **Knowledge Bases** - Managed Bedrock Knowledge Bases auto-wired to gateways
284
- - **Harness** - Declarative agent: bundle runtime + tools + skills + memory + observability without writing agent code
285
285
  - **Policies & Guardrails** - Cedar pre/post-call policies including Bedrock content filters, prompt-attack detection,
286
286
  and sensitive-information redaction
287
287
  - **Payments** - x402-protocol microtransactions for pay-per-call tools and APIs