feat(model-capabilities): humanize Databricks UC model families - #6955
Merged
Conversation
Unity Catalog chat-eligible models from the Gemini, DeepSeek, GLM, Grok, Llama, Qwen, Gemma, and Inkling families rendered as raw FQNs in the agent picker because the manifest carried no records for them and its family tokens could not strip the system.ai. / data_workflow_tools.goose.goose- prefixes off UC FQNs. Add the eight missing family tokens and databricks_v2 exact records for the sixteen previously unlabeled stems, so every chat-eligible UC FQN and its goose- alias resolves to a curated label via the existing alias path. Axes are materialized from the databricks_v2/concrete_unknown fallback per the #6360 precedent, since models.dev advertises no Databricks-served capability schema for these endpoints. Co-authored-by: Will Pfleger <pfleger.will@gmail.com> Signed-off-by: Will Pfleger <pfleger.will@gmail.com>
wpfleger96
had a problem deploying
to
codex-review
August 27, 2026 19:43 — with 
GitHub Actions
Error
GitHub Actions
Error
… evidence Review pass 1 on #6955 found two blockers. First, adding the eight UC family markers to family_tokens changed capability resolution globally: strip_catalog_prefix picks the earliest boundary token, so a label marker before a gpt-/claude- marker displaced the capability family match for every provider (e.g. openai tenant-gemini-gpt-5-pro lost its gpt-5-pro high-only profile). Split the label-only superset into a new label_family_tokens array consumed solely by databricks_registry_label and its TS mirror; capability family_tokens stays claude-/gpt-/kimi-. Both interpreters' structs, zod schema, and validate_manifest are updated in lockstep, and two negative capability vectors pin the isolation. Second, the sixteen new records defaulted all axes to the concrete_unknown fallback despite model-level upstream evidence, contrary to the Kimi-K3 precedent. Reconcile each against the pinned models.dev api.json: adopt first-party effort evidence for DeepSeek V4 Flash/Pro, GLM-5.3 Flash, Grok 4.6, Gemini 3 Pro Image, and Inkling (thinking_mode none, default_effort null, openai-standard, per MLflow-chat transport limits); document deliberate fallback for the non-reasoning and conflicting/unrepresentable records. Co-authored-by: Will Pfleger <pfleger.will@gmail.com> Signed-off-by: Will Pfleger <pfleger.will@gmail.com>
wpfleger96
had a problem deploying
to
codex-review
August 27, 2026 20:21 — with
GitHub Actions
Error
GitHub Actions
Error
Unity Catalog spells the Gemini 3.5 and 3.6 endpoint stems with hyphens, while the pinned first-party Google catalog uses dotted model IDs. Reconcile those equivalent names so the three records expose Google's documented effort levels instead of the generic fallback. Co-authored-by: Will Pfleger <pfleger.will@gmail.com> Signed-off-by: Thufir <7ebdb0b67dab08a570b9faf7bbada97535673b4ccaba2cbd546ad3ba84c87fa6@buzz.block.builderlab.xyz>
wpfleger96
had a problem deploying
to
codex-review
August 27, 2026 20:34 — with
GitHub Actions
Error
GitHub Actions
Error
wpfleger96
pushed a commit
that referenced
this pull request
Aug 27, 2026
…-history * 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) Signed-off-by: Duncan <dcfd242e557282d7a1e2cf2e6877522682f1e5c6156dc92ca7d90eaedd3b0f95@buzz.block.builderlab.xyz>
wpfleger96
pushed a commit
that referenced
this pull request
Aug 27, 2026
…arer-auth * origin/main: fix(ci): bump Codex CLI to 0.150.1 to unhang security review jobs (#6962) 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) Signed-off-by: Duncan <dcfd242e557282d7a1e2cf2e6877522682f1e5c6156dc92ca7d90eaedd3b0f95@buzz.block.builderlab.xyz>
jrobotham-square
added a commit
that referenced
this pull request
Aug 28, 2026
…age-rw * origin/main: (21 commits) fix(desktop): resolve exact typed mentions on space (#6862) perf(desktop): restore project context during startup (#6939) fix(desktop): lift right auxiliary pane above shared header backdrop (#6966) fix(ci): bump Codex CLI to 0.150.1 to unhang security review jobs (#6962) 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) fix(client): resurface hidden DMs from live activity (#6885) ... Signed-off-by: Joel Robotham <jrobotham@squareup.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
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-flashin 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 orgoose-prefixes.I added a display-only
label_family_tokenslist anddatabricks_v2exact records for the sixteen previously unlabeled endpoint stems. All 26 target FQNs and theirgoose-aliases now resolve to curated labels throughdatabricks_registry_label, while capability resolution continues to use only the existingfamily_tokens(claude-,gpt-, andkimi-). This keeps label discovery from changing capability profiles for unrelated model IDs.Each new record includes reconciliation metadata against the pinned models.dev catalog. 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_unknownfallback because upstream evidence is absent, identifies a non-reasoning model, or provides only toggle/token-budget controls thatreasoning_effortcannot 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