mirror of
https://github.com/block/buzz.git
synced 2026-10-27 12:40:30 +00:00
feat(model-capabilities): humanize Databricks UC model families (#6955)
Chat-eligible Unity Catalog models from the Gemini, DeepSeek, GLM, Grok, Llama, Qwen, Gemma, and Inkling families were rendering as raw FQNs such as `system.ai.gemini-3-5-flash` in the agent model picker. #6918 surfaces these models, but the capability manifest carried no records for most of them and the registry-label path could not strip their Unity Catalog or `goose-` prefixes. I added a display-only `label_family_tokens` list and `databricks_v2` exact records for the sixteen previously unlabeled endpoint stems. All 26 target FQNs and their `goose-` aliases now resolve to curated labels through `databricks_registry_label`, while capability resolution continues to use only the existing `family_tokens` (`claude-`, `gpt-`, and `kimi-`). This keeps label discovery from changing capability profiles for unrelated model IDs. Each new record includes reconciliation metadata against the pinned [models.dev catalog](https://models.dev/api.json). Nine records adopt first-party effort evidence that the Databricks MLflow Chat transport can express: Gemini 3.5 Flash, Gemini 3.5 Flash Lite, Gemini 3.6 Flash, Gemini 3 Pro Image, DeepSeek V4 Flash, DeepSeek V4 Pro, GLM-5.3 Flash, Grok 4.6, and Inkling. The remaining seven deliberately retain the `databricks_v2/concrete_unknown` fallback because upstream evidence is absent, identifies a non-reasoning model, or provides only toggle/token-budget controls that `reasoning_effort` cannot represent. The normative corpus adds the sixteen exact records, four Unity Catalog alias probes, and two capability-isolation probes. Existing base vectors remain unchanged, and Rust and TypeScript consume the same strict manifest and corpus. Related: #6918 --------- Signed-off-by: Will Pfleger <pfleger.will@gmail.com> Signed-off-by: Thufir <7ebdb0b67dab08a570b9faf7bbada97535673b4ccaba2cbd546ad3ba84c87fa6@buzz.block.builderlab.xyz> Co-authored-by: Duncan <dcfd242e557282d7a1e2cf2e6877522682f1e5c6156dc92ca7d90eaedd3b0f95@buzz.block.builderlab.xyz> Co-authored-by: Thufir <7ebdb0b67dab08a570b9faf7bbada97535673b4ccaba2cbd546ad3ba84c87fa6@buzz.block.builderlab.xyz>
This commit is contained in:
Will Pfleger
@@ -11,6 +11,20 @@
|
||||
"gpt-",
|
||||
"kimi-"
|
||||
],
|
||||
"_comment_label_family_tokens": "Prefix tokens used ONLY by databricks_registry_label (and its TS mirror) to strip catalog/endpoint prefixes off Unity Catalog FQN and goose- alias ids before matching a curated display label. Deliberately SEPARATE from family_tokens: label stripping is a discovery-only display concern, while family_tokens drives capability resolution in resolve() for every provider. Adding a family marker here humanizes its UC ids without altering any model's resolved capability profile.",
|
||||
"label_family_tokens": [
|
||||
"claude-",
|
||||
"gpt-",
|
||||
"kimi-",
|
||||
"gemini-",
|
||||
"deepseek-",
|
||||
"glm-",
|
||||
"grok-",
|
||||
"llama-",
|
||||
"qwen",
|
||||
"gemma-",
|
||||
"inkling"
|
||||
],
|
||||
"family_rules": [
|
||||
{
|
||||
"id": "anthropic-manual-budget-claude3",
|
||||
@@ -880,6 +894,335 @@
|
||||
"_provenance": "all axes materialized from provider fallback (databricks_v2/concrete_unknown)",
|
||||
"_source": "registry_labels"
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-gemini-3-1-flash-image",
|
||||
"registry_label": "Gemini 3.1 Flash Image",
|
||||
"thinking_mode": "none",
|
||||
"supported_efforts": [
|
||||
"none",
|
||||
"minimal",
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
"xhigh"
|
||||
],
|
||||
"default_effort": "medium",
|
||||
"databricks_v2_wire_route": "mlflow-chat",
|
||||
"normalization_policy": "openai-clamp-max-to-xhigh",
|
||||
"_provenance": "all axes materialized from provider fallback (databricks_v2/concrete_unknown)",
|
||||
"_source": "registry_labels",
|
||||
"_reconciliation": "keep-fallback",
|
||||
"_reconciliation_note": "No model-level entry for gemini-3-1-flash-image exists under any provider in the pinned models.dev payload; there is genuinely no upstream reasoning evidence to reconcile. Retain the databricks_v2 concrete_unknown fallback profile.",
|
||||
"_reconciliation_doc": "https://models.dev/api.json (pinned SHA-256 9266003029c4ea265e923637826211f597db08e8f0f40123aad8547411029238): no providers.*.models[*] key matches gemini-3-1-flash-image."
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-gemini-3-5-flash",
|
||||
"registry_label": "Gemini 3.5 Flash",
|
||||
"thinking_mode": "none",
|
||||
"supported_efforts": [
|
||||
"minimal",
|
||||
"low",
|
||||
"medium",
|
||||
"high"
|
||||
],
|
||||
"default_effort": null,
|
||||
"databricks_v2_wire_route": "mlflow-chat",
|
||||
"normalization_policy": "openai-standard",
|
||||
"_provenance": "supported_efforts+thinking_mode+default_effort+normalization_policy: adopted from models.dev first-party google model-level evidence (Kimi-K3 precedent); databricks_v2_wire_route+label: registry_labels",
|
||||
"source": "models.dev google reasoning_options effort: minimal|low|medium|high",
|
||||
"_reconciliation": "adopt",
|
||||
"_reconciliation_note": "The Unity Catalog endpoint uses the hyphenated stem gemini-3-5-flash, while the pinned models.dev first-party google entry uses the dotted model id gemini-3.5-flash and advertises effort [minimal, low, medium, high]. Per the Kimi-K3 precedent, adopt this model-level effort evidence despite the spelling difference and the exact endpoint being absent from the models.dev databricks catalog. Databricks serves via MLflow Chat (reasoning_effort only), so thinking_mode stays none and default_effort is null.",
|
||||
"_reconciliation_doc": "https://models.dev/api.json (pinned SHA-256 9266003029c4ea265e923637826211f597db08e8f0f40123aad8547411029238): providers.google.models[\"gemini-3.5-flash\"].reasoning_options=[{\"type\":\"effort\",\"values\":[\"minimal\",\"low\",\"medium\",\"high\"]}]"
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-gemini-3-5-flash-lite",
|
||||
"registry_label": "Gemini 3.5 Flash Lite",
|
||||
"thinking_mode": "none",
|
||||
"supported_efforts": [
|
||||
"minimal",
|
||||
"low",
|
||||
"medium",
|
||||
"high"
|
||||
],
|
||||
"default_effort": null,
|
||||
"databricks_v2_wire_route": "mlflow-chat",
|
||||
"normalization_policy": "openai-standard",
|
||||
"_provenance": "supported_efforts+thinking_mode+default_effort+normalization_policy: adopted from models.dev first-party google model-level evidence (Kimi-K3 precedent); databricks_v2_wire_route+label: registry_labels",
|
||||
"source": "models.dev google reasoning_options effort: minimal|low|medium|high",
|
||||
"_reconciliation": "adopt",
|
||||
"_reconciliation_note": "The Unity Catalog endpoint uses the hyphenated stem gemini-3-5-flash-lite, while the pinned models.dev first-party google entry uses the dotted model id gemini-3.5-flash-lite and advertises effort [minimal, low, medium, high]. Per the Kimi-K3 precedent, adopt this model-level effort evidence despite the spelling difference and the exact endpoint being absent from the models.dev databricks catalog. Databricks serves via MLflow Chat (reasoning_effort only), so thinking_mode stays none and default_effort is null.",
|
||||
"_reconciliation_doc": "https://models.dev/api.json (pinned SHA-256 9266003029c4ea265e923637826211f597db08e8f0f40123aad8547411029238): providers.google.models[\"gemini-3.5-flash-lite\"].reasoning_options=[{\"type\":\"effort\",\"values\":[\"minimal\",\"low\",\"medium\",\"high\"]}]"
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-gemini-3-6-flash",
|
||||
"registry_label": "Gemini 3.6 Flash",
|
||||
"thinking_mode": "none",
|
||||
"supported_efforts": [
|
||||
"minimal",
|
||||
"low",
|
||||
"medium",
|
||||
"high"
|
||||
],
|
||||
"default_effort": null,
|
||||
"databricks_v2_wire_route": "mlflow-chat",
|
||||
"normalization_policy": "openai-standard",
|
||||
"_provenance": "supported_efforts+thinking_mode+default_effort+normalization_policy: adopted from models.dev first-party google model-level evidence (Kimi-K3 precedent); databricks_v2_wire_route+label: registry_labels",
|
||||
"source": "models.dev google reasoning_options effort: minimal|low|medium|high",
|
||||
"_reconciliation": "adopt",
|
||||
"_reconciliation_note": "The Unity Catalog endpoint uses the hyphenated stem gemini-3-6-flash, while the pinned models.dev first-party google entry uses the dotted model id gemini-3.6-flash and advertises effort [minimal, low, medium, high]. Per the Kimi-K3 precedent, adopt this model-level effort evidence despite the spelling difference and the exact endpoint being absent from the models.dev databricks catalog. Databricks serves via MLflow Chat (reasoning_effort only), so thinking_mode stays none and default_effort is null.",
|
||||
"_reconciliation_doc": "https://models.dev/api.json (pinned SHA-256 9266003029c4ea265e923637826211f597db08e8f0f40123aad8547411029238): providers.google.models[\"gemini-3.6-flash\"].reasoning_options=[{\"type\":\"effort\",\"values\":[\"minimal\",\"low\",\"medium\",\"high\"]}]"
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-gemini-3-pro-image",
|
||||
"registry_label": "Gemini 3 Pro Image",
|
||||
"thinking_mode": "none",
|
||||
"supported_efforts": [
|
||||
"low",
|
||||
"high"
|
||||
],
|
||||
"default_effort": null,
|
||||
"databricks_v2_wire_route": "mlflow-chat",
|
||||
"normalization_policy": "openai-standard",
|
||||
"_provenance": "supported_efforts+thinking_mode+default_effort+normalization_policy: adopted from models.dev first-party google model-level evidence (Kimi-K3 precedent); databricks_v2_wire_route+label: registry_labels",
|
||||
"source": "models.dev google reasoning_options effort: low|high",
|
||||
"_reconciliation": "adopt",
|
||||
"_reconciliation_note": "The exact databricks endpoint is absent from the models.dev databricks catalog, but the first-party google entry advertises effort [low, high]. Per the Kimi-K3 precedent, adopt model-level effort evidence despite endpoint absence. Databricks serves via MLflow Chat (reasoning_effort only), so thinking_mode stays none and default_effort is null.",
|
||||
"_reconciliation_doc": "https://models.dev/api.json (pinned SHA-256 9266003029c4ea265e923637826211f597db08e8f0f40123aad8547411029238): providers.google.models[\"gemini-3-pro-image\"].reasoning_options=[{\"type\":\"effort\",\"values\":[\"low\",\"high\"]}]"
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-deepseek-v4-flash-0731",
|
||||
"registry_label": "DeepSeek V4 Flash",
|
||||
"thinking_mode": "none",
|
||||
"supported_efforts": [
|
||||
"low",
|
||||
"high",
|
||||
"max"
|
||||
],
|
||||
"default_effort": null,
|
||||
"databricks_v2_wire_route": "mlflow-chat",
|
||||
"normalization_policy": "openai-standard",
|
||||
"_provenance": "supported_efforts+thinking_mode+default_effort+normalization_policy: adopted from models.dev first-party deepseek model-level evidence (Kimi-K3 precedent); databricks_v2_wire_route+label: registry_labels",
|
||||
"source": "models.dev deepseek reasoning_options effort: low|high|max",
|
||||
"_reconciliation": "adopt",
|
||||
"_reconciliation_note": "The exact databricks endpoint is absent from the models.dev databricks catalog, but the first-party deepseek entry advertises a reasoning toggle plus effort [low, high, max]. Per the Kimi-K3 precedent, adopt the model-level effort list despite endpoint absence. The toggle is not representable on the MLflow Chat request schema (reasoning_effort only), so thinking_mode stays none and default_effort is null — mirroring the kimi-k3 record.",
|
||||
"_reconciliation_doc": "https://models.dev/api.json (pinned SHA-256 9266003029c4ea265e923637826211f597db08e8f0f40123aad8547411029238): providers.deepseek.models[\"deepseek-v4-flash\"].reasoning_options=[{\"type\":\"toggle\"},{\"type\":\"effort\",\"values\":[\"low\",\"high\",\"max\"]}]"
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-deepseek-v4-pro-0813",
|
||||
"registry_label": "DeepSeek V4 Pro",
|
||||
"thinking_mode": "none",
|
||||
"supported_efforts": [
|
||||
"high",
|
||||
"max"
|
||||
],
|
||||
"default_effort": null,
|
||||
"databricks_v2_wire_route": "mlflow-chat",
|
||||
"normalization_policy": "openai-standard",
|
||||
"_provenance": "supported_efforts+thinking_mode+default_effort+normalization_policy: adopted from models.dev first-party deepseek model-level evidence (Kimi-K3 precedent); databricks_v2_wire_route+label: registry_labels",
|
||||
"source": "models.dev deepseek reasoning_options effort: high|max",
|
||||
"_reconciliation": "adopt",
|
||||
"_reconciliation_note": "The exact databricks endpoint is absent from the models.dev databricks catalog, but the first-party deepseek entry advertises a reasoning toggle plus effort [high, max]. Per the Kimi-K3 precedent, adopt the model-level effort list despite endpoint absence. The toggle is not representable on the MLflow Chat request schema (reasoning_effort only), so thinking_mode stays none and default_effort is null — mirroring the kimi-k3 record.",
|
||||
"_reconciliation_doc": "https://models.dev/api.json (pinned SHA-256 9266003029c4ea265e923637826211f597db08e8f0f40123aad8547411029238): providers.deepseek.models[\"deepseek-v4-pro\"].reasoning_options=[{\"type\":\"toggle\"},{\"type\":\"effort\",\"values\":[\"high\",\"max\"]}]"
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-glm-5-3-flash",
|
||||
"registry_label": "GLM-5.3 Flash",
|
||||
"thinking_mode": "none",
|
||||
"supported_efforts": [
|
||||
"low",
|
||||
"high",
|
||||
"max"
|
||||
],
|
||||
"default_effort": null,
|
||||
"databricks_v2_wire_route": "mlflow-chat",
|
||||
"normalization_policy": "openai-standard",
|
||||
"_provenance": "supported_efforts+thinking_mode+default_effort+normalization_policy: adopted from models.dev first-party Z.AI model-level evidence (Kimi-K3 precedent); databricks_v2_wire_route+label: registry_labels",
|
||||
"source": "models.dev zai reasoning_options effort: low|high|max",
|
||||
"_reconciliation": "adopt",
|
||||
"_reconciliation_note": "The exact databricks endpoint is absent from the models.dev databricks catalog, but the first-party Z.AI entry glm-5.3-flash advertises effort [low, high, max]. Per the Kimi-K3 precedent, adopt the model-level effort list despite endpoint absence. Databricks serves via MLflow Chat (reasoning_effort only), so thinking_mode stays none and default_effort is null.",
|
||||
"_reconciliation_doc": "https://models.dev/api.json (pinned SHA-256 9266003029c4ea265e923637826211f597db08e8f0f40123aad8547411029238): providers.zai.models[\"glm-5.3-flash\"].reasoning_options=[{\"type\":\"effort\",\"values\":[\"low\",\"high\",\"max\"]}]"
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-grok-4-6",
|
||||
"registry_label": "Grok 4.6",
|
||||
"thinking_mode": "none",
|
||||
"supported_efforts": [
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
"xhigh"
|
||||
],
|
||||
"default_effort": null,
|
||||
"databricks_v2_wire_route": "mlflow-chat",
|
||||
"normalization_policy": "openai-standard",
|
||||
"_provenance": "supported_efforts+thinking_mode+default_effort+normalization_policy: adopted from models.dev first-party xAI model-level evidence (Kimi-K3 precedent); databricks_v2_wire_route+label: registry_labels",
|
||||
"source": "models.dev xai reasoning_options effort: low|medium|high|xhigh",
|
||||
"_reconciliation": "adopt",
|
||||
"_reconciliation_note": "The exact databricks endpoint is absent from the models.dev databricks catalog, but the first-party xAI entry grok-4.6 advertises effort [low, medium, high, xhigh]. Per the Kimi-K3 precedent, adopt the model-level effort list despite endpoint absence. Databricks serves via MLflow Chat (reasoning_effort only), so thinking_mode stays none and default_effort is null.",
|
||||
"_reconciliation_doc": "https://models.dev/api.json (pinned SHA-256 9266003029c4ea265e923637826211f597db08e8f0f40123aad8547411029238): providers.xai.models[\"grok-4.6\"].reasoning_options=[{\"type\":\"effort\",\"values\":[\"low\",\"medium\",\"high\",\"xhigh\"]}]"
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-llama-4-maverick",
|
||||
"registry_label": "Llama 4 Maverick",
|
||||
"thinking_mode": "none",
|
||||
"supported_efforts": [
|
||||
"none",
|
||||
"minimal",
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
"xhigh"
|
||||
],
|
||||
"default_effort": "medium",
|
||||
"databricks_v2_wire_route": "mlflow-chat",
|
||||
"normalization_policy": "openai-clamp-max-to-xhigh",
|
||||
"_provenance": "all axes materialized from provider fallback (databricks_v2/concrete_unknown)",
|
||||
"_source": "registry_labels",
|
||||
"_reconciliation": "keep-fallback",
|
||||
"_reconciliation_note": "Llama 4 Maverick is a non-reasoning model: all 26 model-level records across providers in the pinned payload report reasoning=false with no reasoning_options. There is no effort evidence to adopt. Retain the databricks_v2 concrete_unknown fallback profile.",
|
||||
"_reconciliation_doc": "https://models.dev/api.json (pinned SHA-256 9266003029c4ea265e923637826211f597db08e8f0f40123aad8547411029238): every providers.*.models[*] whose id contains \"llama-4-maverick\" (e.g. meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8) has reasoning=false, reasoning_options=null."
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-meta-llama-3-1-8b-instruct",
|
||||
"registry_label": "Llama 3.1 8B Instruct",
|
||||
"thinking_mode": "none",
|
||||
"supported_efforts": [
|
||||
"none",
|
||||
"minimal",
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
"xhigh"
|
||||
],
|
||||
"default_effort": "medium",
|
||||
"databricks_v2_wire_route": "mlflow-chat",
|
||||
"normalization_policy": "openai-clamp-max-to-xhigh",
|
||||
"_provenance": "all axes materialized from provider fallback (databricks_v2/concrete_unknown)",
|
||||
"_source": "registry_labels",
|
||||
"_reconciliation": "keep-fallback",
|
||||
"_reconciliation_note": "Llama 3.1 8B Instruct is a non-reasoning model: the consensus across model-level records in the pinned payload is reasoning=false with no reasoning_options (a single reseller, pioneer, is an outlier advertising effort [low, medium, high]). There is no first-party or consensus effort evidence to adopt. Retain the databricks_v2 concrete_unknown fallback profile.",
|
||||
"_reconciliation_doc": "https://models.dev/api.json (pinned SHA-256 9266003029c4ea265e923637826211f597db08e8f0f40123aad8547411029238): providers.*.models[*] ids containing \"llama-3.1-8b\" report reasoning=false with reasoning_options=null across essentially all providers (huggingface, nvidia, groq, openrouter, kilo, ...); only pioneer/meta-llama/Llama-3.1-8B-Instruct is reasoning=true."
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-meta-llama-3-3-70b-instruct",
|
||||
"registry_label": "Llama 3.3 70B Instruct",
|
||||
"thinking_mode": "none",
|
||||
"supported_efforts": [
|
||||
"none",
|
||||
"minimal",
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
"xhigh"
|
||||
],
|
||||
"default_effort": "medium",
|
||||
"databricks_v2_wire_route": "mlflow-chat",
|
||||
"normalization_policy": "openai-clamp-max-to-xhigh",
|
||||
"_provenance": "all axes materialized from provider fallback (databricks_v2/concrete_unknown)",
|
||||
"_source": "registry_labels",
|
||||
"_reconciliation": "keep-fallback",
|
||||
"_reconciliation_note": "Llama 3.3 70B Instruct is a non-reasoning model: every model-level record across ~50 providers in the pinned payload reports reasoning=false with no effort values (one reseller, berget, sets reasoning=true but with an empty reasoning_options set, i.e. no effort list). There is no effort evidence to adopt. Retain the databricks_v2 concrete_unknown fallback profile.",
|
||||
"_reconciliation_doc": "https://models.dev/api.json (pinned SHA-256 9266003029c4ea265e923637826211f597db08e8f0f40123aad8547411029238): providers.*.models[*] ids containing \"llama-3.3-70b\" report reasoning=false, reasoning_options=null across all providers; providers.berget.models[\"meta-llama/Llama-3.3-70B-Instruct\"] is reasoning=true with reasoning_options=[]."
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-qwen3-next-80b-a3b-instruct",
|
||||
"registry_label": "Qwen3 Next 80B A3B Instruct",
|
||||
"thinking_mode": "none",
|
||||
"supported_efforts": [
|
||||
"none",
|
||||
"minimal",
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
"xhigh"
|
||||
],
|
||||
"default_effort": "medium",
|
||||
"databricks_v2_wire_route": "mlflow-chat",
|
||||
"normalization_policy": "openai-clamp-max-to-xhigh",
|
||||
"_provenance": "all axes materialized from provider fallback (databricks_v2/concrete_unknown)",
|
||||
"_source": "registry_labels",
|
||||
"_reconciliation": "keep-fallback",
|
||||
"_reconciliation_note": "The first-party alibaba entry qwen3-next-80b-a3b-instruct reports reasoning=false with no reasoning_options — the -instruct variant is the non-reasoning sibling of qwen3-next-80b-a3b-thinking. There is no effort evidence to adopt for the instruct model. Retain the databricks_v2 concrete_unknown fallback profile.",
|
||||
"_reconciliation_doc": "https://models.dev/api.json (pinned SHA-256 9266003029c4ea265e923637826211f597db08e8f0f40123aad8547411029238): providers.alibaba.models[\"qwen3-next-80b-a3b-instruct\"].reasoning=false, reasoning_options=null (contrast qwen3-next-80b-a3b-thinking which is reasoning=true with budget_tokens)."
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-qwen35-122b-a10b",
|
||||
"registry_label": "Qwen3.5 122B A10B",
|
||||
"thinking_mode": "none",
|
||||
"supported_efforts": [
|
||||
"none",
|
||||
"minimal",
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
"xhigh"
|
||||
],
|
||||
"default_effort": "medium",
|
||||
"databricks_v2_wire_route": "mlflow-chat",
|
||||
"normalization_policy": "openai-clamp-max-to-xhigh",
|
||||
"_provenance": "all axes materialized from provider fallback (databricks_v2/concrete_unknown)",
|
||||
"_source": "registry_labels",
|
||||
"_reconciliation": "keep-fallback",
|
||||
"_reconciliation_note": "The first-party alibaba entry qwen3.5-122b-a10b expresses reasoning only as a toggle plus budget_tokens — NOT an effort-level selector. Neither axis is representable on the Databricks MLflow Chat transport (reasoning_effort only), mirroring the claude-opus-4-7 budget_tokens precedent where no effort divergence is reconciled. Resellers that do advertise effort sets conflict sharply (kilo [none, high]; tensorx [none..max]; neon [none, low, medium, high]), so there is no consistent effort list to adopt. Retain the databricks_v2 concrete_unknown fallback profile.",
|
||||
"_reconciliation_doc": "https://models.dev/api.json (pinned SHA-256 9266003029c4ea265e923637826211f597db08e8f0f40123aad8547411029238): providers.alibaba.models[\"qwen3.5-122b-a10b\"].reasoning_options=[{\"type\":\"toggle\"},{\"type\":\"budget_tokens\"}]; reseller effort sets diverge (kilo=[none,high], tensorx=[none,minimal,low,medium,high,xhigh,max], neon=[none,low,medium,high])."
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-gemma-3-12b",
|
||||
"registry_label": "Gemma 3 12B",
|
||||
"thinking_mode": "none",
|
||||
"supported_efforts": [
|
||||
"none",
|
||||
"minimal",
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
"xhigh"
|
||||
],
|
||||
"default_effort": "medium",
|
||||
"databricks_v2_wire_route": "mlflow-chat",
|
||||
"normalization_policy": "openai-clamp-max-to-xhigh",
|
||||
"_provenance": "all axes materialized from provider fallback (databricks_v2/concrete_unknown)",
|
||||
"_source": "registry_labels",
|
||||
"_reconciliation": "keep-fallback",
|
||||
"_reconciliation_note": "Gemma 3 12B is a non-reasoning model: every model-level record across providers in the pinned payload reports reasoning=false with no reasoning_options. There is no effort evidence to adopt. Retain the databricks_v2 concrete_unknown fallback profile.",
|
||||
"_reconciliation_doc": "https://models.dev/api.json (pinned SHA-256 9266003029c4ea265e923637826211f597db08e8f0f40123aad8547411029238): providers.*.models[*] ids containing \"gemma-3-12b\" (e.g. google/gemma-3-12b-it) all report reasoning=false, reasoning_options=null."
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-inkling",
|
||||
"registry_label": "Inkling",
|
||||
"thinking_mode": "none",
|
||||
"supported_efforts": [
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
"xhigh",
|
||||
"max"
|
||||
],
|
||||
"default_effort": null,
|
||||
"databricks_v2_wire_route": "mlflow-chat",
|
||||
"normalization_policy": "openai-standard",
|
||||
"_provenance": "supported_efforts+thinking_mode+default_effort+normalization_policy: adopted from models.dev first-party Thinking Machines model-level evidence (Kimi-K3 precedent); databricks_v2_wire_route+label: registry_labels",
|
||||
"source": "models.dev thinkingmachines reasoning_options effort: low|medium|high|xhigh|max",
|
||||
"_reconciliation": "adopt",
|
||||
"_reconciliation_note": "The exact databricks endpoint is absent from the models.dev databricks catalog, but the first-party Thinking Machines entry Inkling advertises a reasoning toggle plus effort [low, medium, high, xhigh, max]. Per the Kimi-K3 precedent, adopt the model-level effort list despite endpoint absence. The toggle is not representable on the MLflow Chat request schema (reasoning_effort only), so thinking_mode stays none and default_effort is null — mirroring the kimi-k3 record.",
|
||||
"_reconciliation_doc": "https://models.dev/api.json (pinned SHA-256 9266003029c4ea265e923637826211f597db08e8f0f40123aad8547411029238): providers.thinkingmachines.models[\"thinkingmachines/Inkling\"].reasoning_options=[{\"type\":\"toggle\"},{\"type\":\"effort\",\"values\":[\"low\",\"medium\",\"high\",\"xhigh\",\"max\"]}]"
|
||||
},
|
||||
{
|
||||
"provider": "databricks_v2",
|
||||
"raw_model_id": "databricks-gpt-5",
|
||||
|
||||
Reference in New Issue
Block a user