jerry/buzz
1
0
Fork 0
mirror of https://github.com/block/buzz.git synced 2026-11-12 04:12:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/main' into jtennant/collections-prototype

Browse Source 
* origin/main:
  feat(desktop): implement 30178 team catalog backend (#5112)
  feat(model-capabilities): humanize Databricks UC model families (#6955)
  feat(agent): discover Databricks Unity Catalog models (#6918)
  test(db): use canonical channel roster fixtures (#6819)
  preserve channel description paragraph breaks (#6946)
  fix(cli): enrich template cardinality error with per-candidate presence and profile hints (#4825)
  Fix Codex security review authorization (#6913)
  fix(db): disable heartbeat vacuum truncation (#6898)
  chore(deps): update rui314/setup-mold digest to 7e4f20a (#6663)
  chore(deps): update dependency vitest to v4.1.11 (#6667)
  chore(deps): update dependency @tanstack/react-virtual to v3.14.10 (#6666)
  chore(deps): update ubuntu:24.04 docker digest to 33ceb71 (#6664)
  fix(projects): allow owners to delete agent projects (#6533)
  Fade expanded video controls on hover (#6926)
  fix(db): exclude kind:30179 ciphertext from brownfield FTS (#6822)

Signed-off-by: John Tennant <jtennant@squareup.com>
This commit is contained in:
John Tennant
2026-08-27 17:47:49 -04:00
parent 241d4cc651 a7c7414a7f
commit 569b4f001d
183 changed files with 18376 additions and 1822 deletions
Download Patch File Download Diff File Expand all files Collapse all files

343
scripts/model-capabilities.json
View File

@@ -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",

437
scripts/normative-corpus.json
View File

@@ -2266,5 +2266,442 @@
"normalization_policy": "openai-standard",
"registry_label": null
}
},
{
"_group": "Databricks UC model-family humanization probes (#6918 follow-up)",
"_note": "Exact-record and UC-FQN strip probes for the Gemini/DeepSeek/GLM/Grok/Llama/Qwen/Gemma/Inkling families surfaced by UC discovery."
},
{
"id": "dbv2-gemini-3-1-flash-image-exact-record-probe",
"provider": "databricks_v2",
"raw_model_id": "databricks-gemini-3-1-flash-image",
"_note": "Probes the Gemini 3.1 Flash Image endpoint record and label.",
"expect": {
"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",
"registry_label": "Gemini 3.1 Flash Image"
}
},
{
"id": "dbv2-gemini-3-5-flash-exact-record-probe",
"provider": "databricks_v2",
"raw_model_id": "databricks-gemini-3-5-flash",
"_note": "Probes the Gemini 3.5 Flash endpoint record and label.",
"expect": {
"thinking_mode": "none",
"supported_efforts": [
"minimal",
"low",
"medium",
"high"
],
"default_effort": null,
"databricks_v2_wire_route": "mlflow-chat",
"normalization_policy": "openai-standard",
"registry_label": "Gemini 3.5 Flash"
}
},
{
"id": "dbv2-gemini-3-5-flash-lite-exact-record-probe",
"provider": "databricks_v2",
"raw_model_id": "databricks-gemini-3-5-flash-lite",
"_note": "Probes the Gemini 3.5 Flash Lite endpoint record and label.",
"expect": {
"thinking_mode": "none",
"supported_efforts": [
"minimal",
"low",
"medium",
"high"
],
"default_effort": null,
"databricks_v2_wire_route": "mlflow-chat",
"normalization_policy": "openai-standard",
"registry_label": "Gemini 3.5 Flash Lite"
}
},
{
"id": "dbv2-gemini-3-6-flash-exact-record-probe",
"provider": "databricks_v2",
"raw_model_id": "databricks-gemini-3-6-flash",
"_note": "Probes the Gemini 3.6 Flash endpoint record and label.",
"expect": {
"thinking_mode": "none",
"supported_efforts": [
"minimal",
"low",
"medium",
"high"
],
"default_effort": null,
"databricks_v2_wire_route": "mlflow-chat",
"normalization_policy": "openai-standard",
"registry_label": "Gemini 3.6 Flash"
}
},
{
"id": "dbv2-gemini-3-pro-image-exact-record-probe",
"provider": "databricks_v2",
"raw_model_id": "databricks-gemini-3-pro-image",
"_note": "Probes the Gemini 3 Pro Image endpoint record and label.",
"expect": {
"thinking_mode": "none",
"supported_efforts": [
"low",
"high"
],
"default_effort": null,
"databricks_v2_wire_route": "mlflow-chat",
"normalization_policy": "openai-standard",
"registry_label": "Gemini 3 Pro Image"
}
},
{
"id": "dbv2-deepseek-v4-flash-exact-record-probe",
"provider": "databricks_v2",
"raw_model_id": "databricks-deepseek-v4-flash-0731",
"_note": "Probes the DeepSeek V4 Flash endpoint record and label.",
"expect": {
"thinking_mode": "none",
"supported_efforts": [
"low",
"high",
"max"
],
"default_effort": null,
"databricks_v2_wire_route": "mlflow-chat",
"normalization_policy": "openai-standard",
"registry_label": "DeepSeek V4 Flash"
}
},
{
"id": "dbv2-deepseek-v4-pro-exact-record-probe",
"provider": "databricks_v2",
"raw_model_id": "databricks-deepseek-v4-pro-0813",
"_note": "Probes the DeepSeek V4 Pro endpoint record and label.",
"expect": {
"thinking_mode": "none",
"supported_efforts": [
"high",
"max"
],
"default_effort": null,
"databricks_v2_wire_route": "mlflow-chat",
"normalization_policy": "openai-standard",
"registry_label": "DeepSeek V4 Pro"
}
},
{
"id": "dbv2-glm-5-3-flash-exact-record-probe",
"provider": "databricks_v2",
"raw_model_id": "databricks-glm-5-3-flash",
"_note": "Probes the GLM-5.3 Flash endpoint record and label.",
"expect": {
"thinking_mode": "none",
"supported_efforts": [
"low",
"high",
"max"
],
"default_effort": null,
"databricks_v2_wire_route": "mlflow-chat",
"normalization_policy": "openai-standard",
"registry_label": "GLM-5.3 Flash"
}
},
{
"id": "dbv2-grok-4-6-exact-record-probe",
"provider": "databricks_v2",
"raw_model_id": "databricks-grok-4-6",
"_note": "Probes the Grok 4.6 endpoint record and label.",
"expect": {
"thinking_mode": "none",
"supported_efforts": [
"low",
"medium",
"high",
"xhigh"
],
"default_effort": null,
"databricks_v2_wire_route": "mlflow-chat",
"normalization_policy": "openai-standard",
"registry_label": "Grok 4.6"
}
},
{
"id": "dbv2-llama-4-maverick-exact-record-probe",
"provider": "databricks_v2",
"raw_model_id": "databricks-llama-4-maverick",
"_note": "Probes the Llama 4 Maverick endpoint record and label.",
"expect": {
"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",
"registry_label": "Llama 4 Maverick"
}
},
{
"id": "dbv2-meta-llama-3-1-8b-exact-record-probe",
"provider": "databricks_v2",
"raw_model_id": "databricks-meta-llama-3-1-8b-instruct",
"_note": "Probes the meta-llama record; the llama- token strips the meta- prefix identically for record and query.",
"expect": {
"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",
"registry_label": "Llama 3.1 8B Instruct"
}
},
{
"id": "dbv2-meta-llama-3-3-70b-exact-record-probe",
"provider": "databricks_v2",
"raw_model_id": "databricks-meta-llama-3-3-70b-instruct",
"_note": "Probes the meta-llama 3.3 70B record and label.",
"expect": {
"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",
"registry_label": "Llama 3.3 70B Instruct"
}
},
{
"id": "dbv2-qwen3-next-80b-exact-record-probe",
"provider": "databricks_v2",
"raw_model_id": "databricks-qwen3-next-80b-a3b-instruct",
"_note": "Probes the Qwen3 Next 80B record; the bare qwen token strips on a hyphen boundary.",
"expect": {
"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",
"registry_label": "Qwen3 Next 80B A3B Instruct"
}
},
{
"id": "dbv2-qwen35-122b-exact-record-probe",
"provider": "databricks_v2",
"raw_model_id": "databricks-qwen35-122b-a10b",
"_note": "Probes the Qwen3.5 122B record; the bare qwen token strips a qwen35 stem with no separator.",
"expect": {
"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",
"registry_label": "Qwen3.5 122B A10B"
}
},
{
"id": "dbv2-gemma-3-12b-exact-record-probe",
"provider": "databricks_v2",
"raw_model_id": "databricks-gemma-3-12b",
"_note": "Probes the Gemma 3 12B endpoint record and label.",
"expect": {
"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",
"registry_label": "Gemma 3 12B"
}
},
{
"id": "dbv2-inkling-exact-record-probe",
"provider": "databricks_v2",
"raw_model_id": "databricks-inkling",
"_note": "Probes the Inkling endpoint record and label.",
"expect": {
"thinking_mode": "none",
"supported_efforts": [
"low",
"medium",
"high",
"xhigh",
"max"
],
"default_effort": null,
"databricks_v2_wire_route": "mlflow-chat",
"normalization_policy": "openai-standard",
"registry_label": "Inkling"
}
},
{
"id": "dbv2-uc-fqn-gemini-3-5-flash-strip-probe",
"provider": "databricks_v2",
"raw_model_id": "system.ai.gemini-3-5-flash",
"_note": "Probes strip parity on a system.ai. UC FQN carrying the gemini- token (resolve carries no label; the alias label path is unit-tested).",
"expect": {
"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",
"registry_label": null
}
},
{
"id": "dbv2-uc-fqn-meta-llama-strip-probe",
"provider": "databricks_v2",
"raw_model_id": "system.ai.meta-llama-3-3-70b-instruct",
"_note": "Probes strip parity on a UC FQN where the llama- token strips through meta-.",
"expect": {
"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",
"registry_label": null
}
},
{
"id": "dbv2-uc-goose-deepseek-strip-probe",
"provider": "databricks_v2",
"raw_model_id": "data_workflow_tools.goose.goose-deepseek-v4-pro-0813",
"_note": "Probes strip parity on a goose- prefixed UC FQN carrying the deepseek- token.",
"expect": {
"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",
"registry_label": null
}
},
{
"id": "dbv2-uc-fqn-inkling-strip-probe",
"provider": "databricks_v2",
"raw_model_id": "system.ai.inkling",
"_note": "Probes strip parity on a UC FQN carrying the bare inkling token.",
"expect": {
"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",
"registry_label": null
}
},
{
"_group": "Label/capability token isolation probes (#6955 review pass 1)",
"_note": "Pins that label_family_tokens (the UC-humanization superset) never leaks into capability resolve(): capability stripping still uses only claude-/gpt-/kimi-, so a label token appearing before a gpt- marker must NOT displace the gpt-5-pro exact profile."
},
{
"id": "isolation-openai-gemini-gpt-5-pro-probe",
"provider": "openai",
"raw_model_id": "tenant-gemini-gpt-5-pro",
"_note": "The gemini- label token must not strip here; capability resolve keeps the gpt-5-pro high-only profile.",
"expect": {
"thinking_mode": "none",
"supported_efforts": [
"high"
],
"default_effort": "high",
"databricks_v2_wire_route": "not-applicable",
"normalization_policy": "openai-standard",
"registry_label": null
}
},
{
"id": "isolation-openai-qwenchanted-gpt-5-pro-probe",
"provider": "openai",
"raw_model_id": "tenant-qwenchanted-gpt-5-pro",
"_note": "The bare qwen label token must not fire mid-segment; capability resolve keeps the gpt-5-pro high-only profile.",
"expect": {
"thinking_mode": "none",
"supported_efforts": [
"high"
],
"default_effort": "high",
"databricks_v2_wire_route": "not-applicable",
"normalization_policy": "openai-standard",
"registry_label": null
}
}
]

42
scripts/attach-schema-partitions.sql → scripts/reconcile-schema-after-pgschema.sql
View File

@@ -1,11 +1,10 @@
-- Attach partition child tables after pgschema apply.
-- Reconcile schema details that pgschema does not preserve.
--
-- pgschema currently emits existing partition children as standalone CREATE TABLE
-- statements when applying schema/schema.sql in CI. The tables exist, but they
-- are not attached to their partitioned parents, so inserts into events or
-- delivery_log fail with "no partition of relation ... found for row". Keep this
-- idempotent: raw psql/schema.sql already attaches these partitions, while
-- pgschema-created schemas need this repair step.
-- pgschema reconciles DDL, but it does not execute seed DML or preserve every
-- table storage parameter from schema/schema.sql. It also currently emits
-- partition children as standalone CREATE TABLE statements. Every pgschema
-- apply caller must run this idempotent script so fresh bootstraps converge on
-- the same live database contract as migration-managed databases.
DO $$
BEGIN
@@ -197,3 +196,32 @@ BEGIN
FOR VALUES FROM ('2026-07-01') TO (MAXVALUE);
END IF;
END $$;
-- pgschema reconciles DDL but does not apply seed DML or table storage
-- parameters from schema/schema.sql. Restore those parts of the desired-state
-- contract explicitly and fail the bootstrap if the live catalog disagrees.
ALTER TABLE replica_heartbeat SET (vacuum_truncate = false);
INSERT INTO replica_heartbeat (id) VALUES (1)
ON CONFLICT (id) DO NOTHING;
DO $$
BEGIN
IF NOT EXISTS (
SELECT 1
FROM pg_class AS relation
JOIN pg_namespace AS namespace ON namespace.oid = relation.relnamespace
WHERE namespace.nspname = current_schema()
AND relation.relname = 'replica_heartbeat'
AND COALESCE(
relation.reloptions @> ARRAY['vacuum_truncate=false']::text[],
false
)
) THEN
RAISE EXCEPTION 'replica_heartbeat must disable vacuum truncation after pgschema apply';
END IF;
IF (SELECT count(*) FROM replica_heartbeat WHERE id = 1) <> 1 THEN
RAISE EXCEPTION 'replica_heartbeat must contain its singleton row after pgschema apply';
END IF;
END $$;

2
scripts/run-desktop-release-smoke.sh
View File

@@ -89,7 +89,7 @@ export PGSCHEMA_PLAN_HOST=localhost PGSCHEMA_PLAN_PORT=5432 PGSCHEMA_PLAN_DB="${
export PGSCHEMA_PLAN_USER=buzz PGSCHEMA_PLAN_PASSWORD=buzz_dev
./bin/pgschema apply --file schema/schema.sql --auto-approve
docker exec -i -e PGPASSWORD=buzz_dev buzz-postgres \
psql -U buzz -d "${DB_NAME}" -v ON_ERROR_STOP=1 < scripts/attach-schema-partitions.sql
psql -U buzz -d "${DB_NAME}" -v ON_ERROR_STOP=1 < scripts/reconcile-schema-after-pgschema.sql
BUZZ_DB_NAME="${DB_NAME}" BUZZ_COMMUNITY_HOST="${COMMUNITY_HOST}" ./scripts/setup-desktop-test-data.sh
docker exec buzz-redis redis-cli -n "${REDIS_DB}" FLUSHDB >/dev/null
phase database "${phase_start}"

2
scripts/start-isolated-test-relay.sh
View File

@@ -98,7 +98,7 @@ export PGSCHEMA_PLAN_HOST=localhost PGSCHEMA_PLAN_PORT=${PG_PORT}
export PGSCHEMA_PLAN_DB=buzz PGSCHEMA_PLAN_USER=buzz PGSCHEMA_PLAN_PASSWORD=buzz_dev
export PGHOST=localhost PGPORT=${PG_PORT} PGUSER=buzz PGDATABASE=buzz
./bin/pgschema apply --file schema/schema.sql --auto-approve
psql_h < scripts/attach-schema-partitions.sql
psql_h < scripts/reconcile-schema-after-pgschema.sql
ok "Schema applied"
# ── Deployment community + channels + members ────────────────────────────────

2
scripts/start-relay-for-tests.sh
View File

@@ -105,7 +105,7 @@ export PGSCHEMA_PLAN_PASSWORD=buzz_dev
./bin/pgschema apply --file schema/schema.sql --auto-approve
docker exec -i -e PGPASSWORD="${PGPASSWORD}" buzz-postgres \
psql -U "${PGUSER}" -d "${PGDATABASE}" -v ON_ERROR_STOP=1 < scripts/attach-schema-partitions.sql
psql -U "${PGUSER}" -d "${PGDATABASE}" -v ON_ERROR_STOP=1 < scripts/reconcile-schema-after-pgschema.sql
ok "Schema applied"
# ── Seed the deployment community ────────────────────────────────────────────