diff --git a/docs/basic_info/getting_started.md b/docs/basic_info/getting_started.md index 7bf966d5e..aa70f05cf 100644 --- a/docs/basic_info/getting_started.md +++ b/docs/basic_info/getting_started.md @@ -132,7 +132,7 @@ llama_stack: use_as_library_client: true # Unified mode (recommended): the run.yaml created above is consumed as # the synthesis profile. The legacy library_client_config_path setup is - # deprecated and removed in 0.7 — see the migration guide: + # deprecated and removed in 0.8 — see the migration guide: # ../user_doc/deployment_guide.md#migrating-from-the-legacy-two-file-configuration config: profile: run.yaml diff --git a/docs/design/llama-stack-config-merge/llama-stack-config-merge.md b/docs/design/llama-stack-config-merge/llama-stack-config-merge.md index 30d0288d0..0d6d641d4 100644 --- a/docs/design/llama-stack-config-merge/llama-stack-config-merge.md +++ b/docs/design/llama-stack-config-merge/llama-stack-config-merge.md @@ -68,8 +68,9 @@ detail that LCORE owns, not an operator-facing artifact. server modes and serves `/v1/query` successfully. - **R2:** Legacy mode (`llama_stack.library_client_config_path` + external `run.yaml`) works unchanged through the deprecation window: - fully functional with a startup deprecation WARN in 0.6, removed in - 0.7 (Decision S2, confirmed 2026-05-20). + fully functional with a startup deprecation WARN in 0.6 and 0.7, + removed in 0.8 (Decision S2, confirmed 2026-05-20, schedule revised + 2026-08-24). - **R3:** Setting both `llama_stack.config` and `llama_stack.library_client_config_path` in the same file fails at configuration load time with a clear error message pointing to the @@ -427,8 +428,14 @@ Three operator-facing migration paths (choose per deployment): Deprecation schedule (Decision S2, confirmed by @sbunciak 2026-05-20): unified mode ships in 0.6 with legacy mode fully functional plus a startup deprecation WARN (no breaking change); the legacy two-file path -is removed in 0.7. Tentative releases: 0.6 end of June 2026, 0.7 end of -September 2026. +is removed in 0.8. + +Schedule revised 2026-08-24 (confirmed by @sbunciak): removal moves from +0.7 to 0.8. Removing in 0.7 would satisfy the Engineering Support +Agreement's one-minor-release deprecation phase only formally -- the +unified replacement is itself only completed in 0.7, so operators would +not have had a full release with a working migration path. Releases: +0.6 June 2026, 0.7 September 2026, 0.8 December 2026. ## Implementation Suggestions @@ -553,6 +560,7 @@ reference. |---|---|---| | 2026-04-23 | Initial version | Spike completion | | 2026-08-20 | Default baseline openai provider is conditional on `OPENAI_API_KEY` | LCORE-3607: `baseline: default` must load when the key is unset | +| 2026-08-24 | Legacy two-file removal moves from 0.7 to 0.8 | Unified replacement only completed in 0.7; operators need a full release with a working migration path (confirmed by @sbunciak) | ## Appendix A — Worked example: legacy → unified migration diff --git a/docs/devel_doc/openapi.json b/docs/devel_doc/openapi.json index 73dd0ba50..51812091c 100644 --- a/docs/devel_doc/openapi.json +++ b/docs/devel_doc/openapi.json @@ -15198,7 +15198,7 @@ } ], "title": "Llama Stack configuration path (legacy, deprecated)", - "description": "Path to configuration file used when Llama Stack is run in library mode. DEPRECATED legacy two-file setup: logs a startup warning since 0.6 and is removed in 0.7 \u2014 use unified mode instead (the config block below, and/or the root-level inference.providers section); migrate with lightspeed-stack --migrate-config." + "description": "Path to configuration file used when Llama Stack is run in library mode. DEPRECATED legacy two-file setup: logs a startup warning since 0.6 and is removed in 0.8 \u2014 use unified mode instead (the config block below, and/or the root-level inference.providers section); migrate with lightspeed-stack --migrate-config." }, "timeout": { "type": "integer", diff --git a/docs/models/successful_responses.json b/docs/models/successful_responses.json index 0d164cb19..7605af4f8 100644 --- a/docs/models/successful_responses.json +++ b/docs/models/successful_responses.json @@ -2052,7 +2052,7 @@ "type": "string", "nullable": true, "default": null, - "description": "Path to configuration file used when Llama Stack is run in library mode. DEPRECATED legacy two-file setup: logs a startup warning since 0.6 and is removed in 0.7 \u2014 use unified mode instead (the config block below, and/or the root-level inference.providers section); migrate with lightspeed-stack --migrate-config.", + "description": "Path to configuration file used when Llama Stack is run in library mode. DEPRECATED legacy two-file setup: logs a startup warning since 0.6 and is removed in 0.8 \u2014 use unified mode instead (the config block below, and/or the root-level inference.providers section); migrate with lightspeed-stack --migrate-config.", "title": "Llama Stack configuration path (legacy, deprecated)" }, "timeout": { @@ -4466,7 +4466,7 @@ "type": "string" }, "model_prompt": { - "default": "\nInstructions:\n- You are a question classifying tool\n- You are an expert in kubernetes and openshift\n- Your job is to determine where or a user's question is related to kubernetes and/or openshift technologies and to provide a one-word response.\n- If a question appears to be related to kubernetes or openshift technologies, answer with the word ${allowed}, otherwise answer with the word ${rejected}.\n- Do not explain your answer, just provide the one-word response. Do not give any other response.\n- If the given question is an empty string, answer with the word ${rejected}\n\n\nExample Question:\nWhy is the sky blue?\nExample Response:\n${rejected}\n\nExample Question:\nWhy is the grass green?\nExample Response:\n${rejected}\n\nExample Question:\nWhy is sand yellow?\nExample Response:\n${rejected}\n\nExample Question:\nCan you help configure my cluster to automatically scale?\nExample Response:\n${allowed}\n\nQuestion:\n${message}\nResponse:\n", + "default": "\nInstructions:\n- You are a question classifying tool\n- You are an expert in Kubernetes and OpenShift\n- Your job is to determine where or a user's question is related to Kubernetes and/or OpenShift technologies and to provide a one-word response.\n- If a question appears to be related to Kubernetes or OpenShift technologies, answer with the word ${allowed}, otherwise answer with the word ${rejected}.\n- Do not explain your answer, just provide the one-word response. Do not give any other response.\n- If the given question is an empty string, answer with the word ${rejected}\n\n\nExample Question:\nWhy is the sky blue?\nExample Response:\n${rejected}\n\nExample Question:\nWhy is the grass green?\nExample Response:\n${rejected}\n\nExample Question:\nWhy is sand yellow?\nExample Response:\n${rejected}\n\nExample Question:\nCan you help configure my cluster to automatically scale?\nExample Response:\n${allowed}\n\nQuestion:\n${message}\nResponse:\n", "description": "The default prompt sent to the LLM used to validate the Users' question.", "title": "Model prompt", "type": "string" diff --git a/docs/models/successful_responses.md b/docs/models/successful_responses.md index 1363bad97..a9e785d79 100644 --- a/docs/models/successful_responses.md +++ b/docs/models/successful_responses.md @@ -864,7 +864,7 @@ Useful resources: | url | string | URL to Llama Stack service; used when library mode is disabled. Must be a valid HTTP or HTTPS URL. | | api_key | string | API key to access Llama Stack service | | use_as_library_client | boolean | When set to true Llama Stack will be used in library mode, not in server mode (default) | -| library_client_config_path | string | Path to configuration file used when Llama Stack is run in library mode. DEPRECATED legacy two-file setup: logs a startup warning since 0.6 and is removed in 0.7 — use unified mode instead (the config block below, and/or the root-level inference.providers section); migrate with lightspeed-stack --migrate-config. | +| library_client_config_path | string | Path to configuration file used when Llama Stack is run in library mode. DEPRECATED legacy two-file setup: logs a startup warning since 0.6 and is removed in 0.8 — use unified mode instead (the config block below, and/or the root-level inference.providers section); migrate with lightspeed-stack --migrate-config. | | timeout | integer | Timeout in seconds for requests to Llama Stack service. Default is 180 seconds (3 minutes) to accommodate long-running RAG queries. | | max_retries | integer | Maximum number of connection attempts before giving up. Used on startup to connect to Llama Stack and retrieve its version. Connection attempts are retried with a fixed delay to handle the case where Llama Stack is still starting up (e.g., when running as a sidecar in the same pod). | | retry_delay | integer | Delay in seconds between retry attempts. Used on startup to connect to Llama Stack and retrieve its version. Connection attempts are retried with a fixed delay to handle the case where Llama Stack is still starting up (e.g., when running as a sidecar in the same pod). | diff --git a/docs/user_doc/config.html b/docs/user_doc/config.html index fdd3f64ac..750b0375c 100644 --- a/docs/user_doc/config.html +++ b/docs/user_doc/config.html @@ -1277,7 +1277,7 @@