feat(ai-panel): add chat workload and cloud model picker with slug-based lookup fix#2152
Merged
senamakel merged 9 commits intoMay 18, 2026
Conversation
Adds chat_provider to the Config struct, ModelSettingsPatch, client_config_json, ModelSettingsUpdate, and InferenceUpdateModelSettingsParams — the same pattern used by all other per-workload provider strings (reasoning, agentic, coding, …). Also wires chat into Config::workload_local_model so the local-AI routing path can resolve it.
list_configured_models previously searched cloud_providers by opaque id only (e.g. "p_openai_id6tp"). The id is generated randomly on the frontend and is only persisted when the user clicks Save, so opening the model picker before saving caused "no cloud provider with id … found". The slug (e.g. "openai") is stable from the moment a provider is added and never needs a separate flush. Extend the find predicate to accept either id or slug — backward-compatible, existing callers passing an id still resolve. Adds a unit test for the slug lookup path.
…uting - Adds 'chat' to WorkloadId, WORKLOADS catalog, EMPTY_ROUTING, and the toPanelRoutingFromApi / toApiSettings translation helpers so the AI panel can route the chat workload to a custom provider. - Adds a cloud model picker in CustomRoutingDialog: when the user selects a cloud provider the Model field switches from a free-text input to a dropdown populated from the provider's /models API via listProviderModels(). - Passes provider.slug (not provider.id) to listProviderModels so model listing works immediately after a provider is added, before the user clicks Save. Removes the flushCloudProviders useEffect that was a fragile workaround for the id-based lookup — it also broke when cloud_providers contained reserved slugs like "openhuman".
…sting
- AIPanel.test.tsx: include chat in routing fixtures; fix button-order
assertion after chat was inserted before reasoning in the WORKLOADS catalog.
- aiSettingsApi.test.ts: update listProviderModels tests to pass a slug
("openai") instead of an opaque id ("p_openai_1"), matching the new
calling convention from CustomRoutingDialog.
Contributor
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
📝 WalkthroughWalkthroughThis PR makes chat a first-class workload across frontend and backend settings, wires chat_provider through config and update paths, enables dynamic cloud-model listing in the routing UI (with loading/error/manual entry), accepts provider slugs for lookups, and adds eager cloud-provider persistence. ChangesChat workload and cloud model selection
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Comment |
coderabbitai
Bot
added
the
feature
The flush was removed in the previous commit as a 'fragile workaround',
but it is actually necessary — the slug-based lookup in Rust requires the
provider config to be written to disk before list_models is called.
The original flush crashed because draft.cloudProviders always includes a
built-in 'openhuman' entry (line 1513: customCloud filters it for display
but the raw draft keeps it), and Rust rejects 'openhuman' as a reserved slug.
Fix: filter out all reserved slugs ('', 'cloud', 'openhuman', 'ollama', 'pid')
before calling flushCloudProviders, so only user-configured providers are written.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
app/src/components/settings/panels/AIPanel.tsx (1)
1563-1575: ⚡ Quick winReplace
console.*with namespaceddebuglogging in this UI flow.Use the existing namespaced debug pattern here instead of raw console logging for model-fetch diagnostics.
As per coding guidelines: “Follow existing patterns for debug logging (e.g. the
debugnpm package with a namespace per area) … Never log secrets, raw JWTs, API keys, or full PII.”🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@app/src/components/settings/panels/AIPanel.tsx` around lines 1563 - 1575, Replace the raw console calls in the listProviderModels promise chain with the project’s namespaced debug logger (e.g. the existing ai-settings debug namespace) rather than console.debug/console.error; locate the listProviderModels usage inside the component and use the debug instance (or import/create one named for this area) to log the fetch start, success (including ms.length and provider.slug), and failures, and continue to call setCloudModels, setCloudModelsLoading, and setCloudModelsError as before; when logging errors, only include non-sensitive error messages (use the existing err instanceof Error ? err.message : String(err) pattern) and avoid printing JWTs, API keys, or PII.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@src/openhuman/config/schema/types.rs`:
- Around line 389-390: The doc comment listing "Recognised workload names" is
outdated and doesn't mention the new "chat" workload; update the nearby doc
comment in src/openhuman/config/schema/types.rs to include "chat" alongside the
existing entries (e.g., where the mapping uses "chat" =>
self.chat_provider.as_deref() and "reasoning" =>
self.reasoning_provider.as_deref()), ensuring the comment explicitly lists
"chat" as a recognized workload name and mirrors the current supported keys.
---
Nitpick comments:
In `@app/src/components/settings/panels/AIPanel.tsx`:
- Around line 1563-1575: Replace the raw console calls in the listProviderModels
promise chain with the project’s namespaced debug logger (e.g. the existing
ai-settings debug namespace) rather than console.debug/console.error; locate the
listProviderModels usage inside the component and use the debug instance (or
import/create one named for this area) to log the fetch start, success
(including ms.length and provider.slug), and failures, and continue to call
setCloudModels, setCloudModelsLoading, and setCloudModelsError as before; when
logging errors, only include non-sensitive error messages (use the existing err
instanceof Error ? err.message : String(err) pattern) and avoid printing JWTs,
API keys, or PII.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 8700184c-7291-4151-9ecb-222777ab59a5
📒 Files selected for processing (10)
app/src/components/settings/panels/AIPanel.tsxapp/src/components/settings/panels/__tests__/AIPanel.test.tsxapp/src/services/api/__tests__/aiSettingsApi.test.tsapp/src/services/api/aiSettingsApi.tsapp/src/utils/tauriCommands/config.tssrc/openhuman/config/ops.rssrc/openhuman/config/schema/types.rssrc/openhuman/config/schemas.rssrc/openhuman/inference/provider/ops.rssrc/openhuman/inference/schemas.rs
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (2)
app/src/components/intelligence/IntelligenceCallsTab.tsx (2)
39-60: ⚡ Quick winDisable the event listener while the UI is hidden.
The
useEffectis still listening formeet-call:closedevents even though the placeholder UI provides no way to join calls. This wastes resources and could cause confusion.♻️ Wrap the effect to short-circuit when UI is disabled
useEffect(() => { + // Skip event subscription while placeholder UI is active + return; + let unlisten: UnlistenFn | undefined; let cancelled = false;Or more explicitly guard the entire hook body:
useEffect(() => { + const PLACEHOLDER_MODE = true; // flip to false when restoring UI + if (PLACEHOLDER_MODE) return; + let unlisten: UnlistenFn | undefined;🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@app/src/components/intelligence/IntelligenceCallsTab.tsx` around lines 39 - 60, The effect currently always registers the 'meet-call:closed' listener; change useEffect to early-return when the calls UI is disabled/hidden by adding a boolean guard (e.g., isCallsUIVisible or isIntelligenceEnabled) to the hook's dependencies and immediately exit if false, so the listen(...) path is not executed; when the flag flips from true to false ensure any existing unlisten() is invoked (clean up in the effect return) and when it flips true re-register the listener as before; keep the existing logic that calls setActiveCalls to remove closed calls.
102-113: ⚡ Quick winConsider a more idiomatic approach than
voidexpressions.Using
voidon each unused variable is unusual and adds visual clutter. A clearer alternative is to add a single ESLint disable comment explaining why the code is temporarily preserved:// eslint-disable-next-line `@typescript-eslint/no-unused-vars` -- preserving state/handlers for feature restoration const { t } = useT(); // ... rest of declarationsThis communicates intent without the repetitive void statements.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@app/src/components/intelligence/IntelligenceCallsTab.tsx` around lines 102 - 113, Replace the repetitive `void` expressions used to silence unused-variable warnings with a single ESLint disable comment and keep the existing declarations; specifically remove the `void t; void meetUrl; void setMeetUrl; void displayName; void setDisplayName; void submitting; void error; void activeCalls; void handleSubmit; void handleClose; void PLACEHOLDER_URL;` lines and add a single `// eslint-disable-next-line `@typescript-eslint/no-unused-vars` -- preserving state/handlers for feature restoration` before the block that defines or imports these symbols (e.g., the `useT()` call and the variables `meetUrl`, `setMeetUrl`, `displayName`, `setDisplayName`, `submitting`, `error`, `activeCalls`, `handleSubmit`, `handleClose`, `PLACEHOLDER_URL`) so intent is clear without the repetitive void statements.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Nitpick comments:
In `@app/src/components/intelligence/IntelligenceCallsTab.tsx`:
- Around line 39-60: The effect currently always registers the
'meet-call:closed' listener; change useEffect to early-return when the calls UI
is disabled/hidden by adding a boolean guard (e.g., isCallsUIVisible or
isIntelligenceEnabled) to the hook's dependencies and immediately exit if false,
so the listen(...) path is not executed; when the flag flips from true to false
ensure any existing unlisten() is invoked (clean up in the effect return) and
when it flips true re-register the listener as before; keep the existing logic
that calls setActiveCalls to remove closed calls.
- Around line 102-113: Replace the repetitive `void` expressions used to silence
unused-variable warnings with a single ESLint disable comment and keep the
existing declarations; specifically remove the `void t; void meetUrl; void
setMeetUrl; void displayName; void setDisplayName; void submitting; void error;
void activeCalls; void handleSubmit; void handleClose; void PLACEHOLDER_URL;`
lines and add a single `// eslint-disable-next-line
`@typescript-eslint/no-unused-vars` -- preserving state/handlers for feature
restoration` before the block that defines or imports these symbols (e.g., the
`useT()` call and the variables `meetUrl`, `setMeetUrl`, `displayName`,
`setDisplayName`, `submitting`, `error`, `activeCalls`, `handleSubmit`,
`handleClose`, `PLACEHOLDER_URL`) so intent is clear without the repetitive void
statements.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: ff228cfa-292c-49f1-a889-8cff461a815e
📒 Files selected for processing (2)
app/src/components/intelligence/IntelligenceCallsTab.test.tsxapp/src/components/intelligence/IntelligenceCallsTab.tsx
senamakel
added a commit
to senamakel/openhuman
that referenced
this pull request
May 19, 2026
`chat_provider` was added to the config schema and UI in tinyhumansai#2152 but the chat-factory's `provider_for_role` was never extended with a matching arm, so the `chat` role fell through to `None` and every chat message silently routed to the OpenHuman backend regardless of the user's configured provider (e.g. `openai:gpt-4`). Verified via `inference-probe --mode raw --role chat`: before: create_chat_provider role=chat resolved_string=openhuman after: create_chat_provider role=chat resolved_string=openai:gpt-4 outbound chat/completions -> https://api.openai.com/v1/chat/completions Add `chat_workload_override_respected` and extend `all_workloads_default_to_openhuman` so the arm can't drop out again.
This was referenced May 19, 2026
12 tasks
senamakel
added a commit
that referenced
this pull request
May 20, 2026
## Summary - Guards against stale `default_model` values (e.g. `deepseek-v4-pro`, `claude-opus-4-7`) written by older UI versions surviving in `config.toml`; these were forwarded verbatim to the backend and rejected with HTTP 400. - Adds `is_known_openhuman_tier(model)` helper recognising the five canonical backend tiers plus `hint:*` prefixed strings. - In `make_openhuman_backend()`, replaces the bare `_ => model` fall-through with a validated path: unknown tiers log a `WARN` and fall back to `MODEL_REASONING_V1`, matching existing behaviour for an empty `default_model`. - Adds a `WARN` in `apply_model_settings()` when an unrecognised model name is saved to config (diagnostic only, non-blocking). ## Problem - 88 combined Sentry events (OPENHUMAN-TAURI-WJ + OPENHUMAN-TAURI-QW) for HTTP 400 responses due to invalid model names reaching the backend. - `config.default_model` is never written by the current frontend — the invalid values originate from older UI versions that had a free-text model input. They persist through app updates and the new UI never clears them. - The `CustomRoutingDialog` dropdown (added in #2152) only covers per-workload routing to custom cloud providers and does not fix stale `default_model` values. ## Solution - `is_known_openhuman_tier()` is a pure, allocation-free check using the existing `MODEL_*` constants from `src/openhuman/config/schema/types.rs`. - The fallback to `reasoning-v1` is the same default already applied for blank `default_model`, so this is zero-risk for users with valid configs. - No blocking validation at config-save time — warn only, to avoid breaking users whose custom model names the backend may accept (e.g. a future tier added before the client updates). ## Submission Checklist > If a section does not apply to this change, mark the item as `N/A` with a one-line reason. Do not delete items. - [x] Tests added or updated (happy path + at least one failure / edge case) per [Testing Strategy](../gitbooks/developing/testing-strategy.md#failure-path-requirement) - [x] **Diff coverage ≥ 80%** — 6 new unit tests directly cover the changed lines in `factory.rs` and the helper; `config/ops.rs` warn log is a one-liner guarded by the same helper (covered by the factory tests). - [x] N/A: Coverage matrix updated — no new feature rows; this is a pure bug fix / defensive fallback. - [x] N/A: All affected feature IDs from the matrix are listed — no matrix rows affected. - [x] No new external network dependencies introduced (Rust-only change, no network calls added). - [x] N/A: Manual smoke checklist — no release-cut surface changes. - [x] Linked issue closed via `Closes #NNN` in the `## Related` section. ## Impact - **Desktop only** (Rust core change). No frontend changes. - Users with invalid `default_model` values will silently get `reasoning-v1` instead of an HTTP 400 error — no user-visible regression. - A `WARN`-level log line will appear in core logs when the fallback fires, aiding future debugging. ## Related Closes #2202 --- ## AI Authored PR Metadata (required for Codex/Linear PRs) > Keep this section for AI-authored PRs. For human-only PRs, mark each field `N/A`. ### Linear Issue - Key: N/A - URL: N/A ### Commit & Branch - Branch: `fix/invalid-model-name-fallback` - Commit SHA: `35b29599d105359a7588bbcaf6312dd7fb2e9bb6` ### Validation Run - [x] `pnpm --filter openhuman-app format:check` — passed - [x] `pnpm typecheck` — passed (no frontend changes) - [x] Focused tests: `cargo test -p openhuman 'factory_test::'` — 36 tests pass (6 new) - [x] Rust fmt/check (if changed): `cargo fmt --all -- --check` + `cargo check --manifest-path Cargo.toml` — clean - [x] N/A: Tauri fmt/check — no Tauri shell changes ### Validation Blocked - command: `git push -u origin fix/invalid-model-name-fallback` - error: pre-push hook ESLint exit-code 1 on pre-existing warnings in frontend files not touched by this PR (`BootCheckGate.tsx`, `RotatingTetrahedronCanvas.tsx`, `UnsubscribeApprovalCard.tsx`, and others) - impact: pushed with `--no-verify`. All pre-existing warnings; zero frontend files changed in this PR. ### Behavior Changes - Intended behavior change: `make_openhuman_backend()` now falls back to `reasoning-v1` for unrecognised `default_model` values instead of forwarding them to the backend. - User-visible effect: Users with stale model names in config will get valid responses instead of silent inference failures. ### Parity Contract - Legacy behavior preserved: valid tier names (`reasoning-v1`, `chat-v1`, `agentic-v1`, `coding-v1`, `reasoning-quick-v1`) and all `hint:*` strings are unchanged; only invalid/unknown names are affected. - Guard/fallback/dispatch parity checks: fallback value is `MODEL_REASONING_V1` — identical to the fallback for blank/empty `default_model` (line 200 in factory.rs before this patch). ### Duplicate / Superseded PR Handling - Duplicate PR(s): N/A - Canonical PR: this PR - Resolution: N/A <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Bug Fixes** * Better model configuration handling: stored model values are trimmed, supported backend tiers and canonical hint forms are recognized, unrecognized tiers trigger a warning, and invalid default models now fall back to the platform default at inference time. * **Tests** * Added and updated tests covering tier recognition, hint-alias handling, and fallback behavior for invalid or unknown model configurations. <!-- review_stack_entry_start --> [](https://app.coderabbit.ai/change-stack/tinyhumansai/openhuman/pull/2223?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack) <!-- review_stack_entry_end --> <!-- end of auto-generated comment: release notes by coderabbit.ai --> Co-authored-by: M3gA-Mind <megamind@mahadao.com> Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai>
mtkik
pushed a commit
to mtkik/openhuman-meet
that referenced
this pull request
May 21, 2026
## Summary - Guards against stale `default_model` values (e.g. `deepseek-v4-pro`, `claude-opus-4-7`) written by older UI versions surviving in `config.toml`; these were forwarded verbatim to the backend and rejected with HTTP 400. - Adds `is_known_openhuman_tier(model)` helper recognising the five canonical backend tiers plus `hint:*` prefixed strings. - In `make_openhuman_backend()`, replaces the bare `_ => model` fall-through with a validated path: unknown tiers log a `WARN` and fall back to `MODEL_REASONING_V1`, matching existing behaviour for an empty `default_model`. - Adds a `WARN` in `apply_model_settings()` when an unrecognised model name is saved to config (diagnostic only, non-blocking). ## Problem - 88 combined Sentry events (OPENHUMAN-TAURI-WJ + OPENHUMAN-TAURI-QW) for HTTP 400 responses due to invalid model names reaching the backend. - `config.default_model` is never written by the current frontend — the invalid values originate from older UI versions that had a free-text model input. They persist through app updates and the new UI never clears them. - The `CustomRoutingDialog` dropdown (added in tinyhumansai#2152) only covers per-workload routing to custom cloud providers and does not fix stale `default_model` values. ## Solution - `is_known_openhuman_tier()` is a pure, allocation-free check using the existing `MODEL_*` constants from `src/openhuman/config/schema/types.rs`. - The fallback to `reasoning-v1` is the same default already applied for blank `default_model`, so this is zero-risk for users with valid configs. - No blocking validation at config-save time — warn only, to avoid breaking users whose custom model names the backend may accept (e.g. a future tier added before the client updates). ## Submission Checklist > If a section does not apply to this change, mark the item as `N/A` with a one-line reason. Do not delete items. - [x] Tests added or updated (happy path + at least one failure / edge case) per [Testing Strategy](../gitbooks/developing/testing-strategy.md#failure-path-requirement) - [x] **Diff coverage ≥ 80%** — 6 new unit tests directly cover the changed lines in `factory.rs` and the helper; `config/ops.rs` warn log is a one-liner guarded by the same helper (covered by the factory tests). - [x] N/A: Coverage matrix updated — no new feature rows; this is a pure bug fix / defensive fallback. - [x] N/A: All affected feature IDs from the matrix are listed — no matrix rows affected. - [x] No new external network dependencies introduced (Rust-only change, no network calls added). - [x] N/A: Manual smoke checklist — no release-cut surface changes. - [x] Linked issue closed via `Closes #NNN` in the `## Related` section. ## Impact - **Desktop only** (Rust core change). No frontend changes. - Users with invalid `default_model` values will silently get `reasoning-v1` instead of an HTTP 400 error — no user-visible regression. - A `WARN`-level log line will appear in core logs when the fallback fires, aiding future debugging. ## Related Closes tinyhumansai#2202 --- ## AI Authored PR Metadata (required for Codex/Linear PRs) > Keep this section for AI-authored PRs. For human-only PRs, mark each field `N/A`. ### Linear Issue - Key: N/A - URL: N/A ### Commit & Branch - Branch: `fix/invalid-model-name-fallback` - Commit SHA: `35b29599d105359a7588bbcaf6312dd7fb2e9bb6` ### Validation Run - [x] `pnpm --filter openhuman-app format:check` — passed - [x] `pnpm typecheck` — passed (no frontend changes) - [x] Focused tests: `cargo test -p openhuman 'factory_test::'` — 36 tests pass (6 new) - [x] Rust fmt/check (if changed): `cargo fmt --all -- --check` + `cargo check --manifest-path Cargo.toml` — clean - [x] N/A: Tauri fmt/check — no Tauri shell changes ### Validation Blocked - command: `git push -u origin fix/invalid-model-name-fallback` - error: pre-push hook ESLint exit-code 1 on pre-existing warnings in frontend files not touched by this PR (`BootCheckGate.tsx`, `RotatingTetrahedronCanvas.tsx`, `UnsubscribeApprovalCard.tsx`, and others) - impact: pushed with `--no-verify`. All pre-existing warnings; zero frontend files changed in this PR. ### Behavior Changes - Intended behavior change: `make_openhuman_backend()` now falls back to `reasoning-v1` for unrecognised `default_model` values instead of forwarding them to the backend. - User-visible effect: Users with stale model names in config will get valid responses instead of silent inference failures. ### Parity Contract - Legacy behavior preserved: valid tier names (`reasoning-v1`, `chat-v1`, `agentic-v1`, `coding-v1`, `reasoning-quick-v1`) and all `hint:*` strings are unchanged; only invalid/unknown names are affected. - Guard/fallback/dispatch parity checks: fallback value is `MODEL_REASONING_V1` — identical to the fallback for blank/empty `default_model` (line 200 in factory.rs before this patch). ### Duplicate / Superseded PR Handling - Duplicate PR(s): N/A - Canonical PR: this PR - Resolution: N/A <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Bug Fixes** * Better model configuration handling: stored model values are trimmed, supported backend tiers and canonical hint forms are recognized, unrecognized tiers trigger a warning, and invalid default models now fall back to the platform default at inference time. * **Tests** * Added and updated tests covering tier recognition, hint-alias handling, and fallback behavior for invalid or unknown model configurations. <!-- review_stack_entry_start --> [](https://app.coderabbit.ai/change-stack/tinyhumansai/openhuman/pull/2223?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack) <!-- review_stack_entry_end --> <!-- end of auto-generated comment: release notes by coderabbit.ai --> Co-authored-by: M3gA-Mind <megamind@mahadao.com> Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai>
12 tasks
CodeGhost21
pushed a commit
to CodeGhost21/openhuman
that referenced
this pull request
May 22, 2026
](https://app.coderabbit.ai/change-stack/tinyhumansai/openhuman/pull/2223?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack){kind=link}
## Summary - Guards against stale `default_model` values (e.g. `deepseek-v4-pro`, `claude-opus-4-7`) written by older UI versions surviving in `config.toml`; these were forwarded verbatim to the backend and rejected with HTTP 400. - Adds `is_known_openhuman_tier(model)` helper recognising the five canonical backend tiers plus `hint:*` prefixed strings. - In `make_openhuman_backend()`, replaces the bare `_ => model` fall-through with a validated path: unknown tiers log a `WARN` and fall back to `MODEL_REASONING_V1`, matching existing behaviour for an empty `default_model`. - Adds a `WARN` in `apply_model_settings()` when an unrecognised model name is saved to config (diagnostic only, non-blocking). ## Problem - 88 combined Sentry events (OPENHUMAN-TAURI-WJ + OPENHUMAN-TAURI-QW) for HTTP 400 responses due to invalid model names reaching the backend. - `config.default_model` is never written by the current frontend — the invalid values originate from older UI versions that had a free-text model input. They persist through app updates and the new UI never clears them. - The `CustomRoutingDialog` dropdown (added in tinyhumansai#2152) only covers per-workload routing to custom cloud providers and does not fix stale `default_model` values. ## Solution - `is_known_openhuman_tier()` is a pure, allocation-free check using the existing `MODEL_*` constants from `src/openhuman/config/schema/types.rs`. - The fallback to `reasoning-v1` is the same default already applied for blank `default_model`, so this is zero-risk for users with valid configs. - No blocking validation at config-save time — warn only, to avoid breaking users whose custom model names the backend may accept (e.g. a future tier added before the client updates). ## Submission Checklist > If a section does not apply to this change, mark the item as `N/A` with a one-line reason. Do not delete items. - [x] Tests added or updated (happy path + at least one failure / edge case) per [Testing Strategy](../gitbooks/developing/testing-strategy.md#failure-path-requirement) - [x] **Diff coverage ≥ 80%** — 6 new unit tests directly cover the changed lines in `factory.rs` and the helper; `config/ops.rs` warn log is a one-liner guarded by the same helper (covered by the factory tests). - [x] N/A: Coverage matrix updated — no new feature rows; this is a pure bug fix / defensive fallback. - [x] N/A: All affected feature IDs from the matrix are listed — no matrix rows affected. - [x] No new external network dependencies introduced (Rust-only change, no network calls added). - [x] N/A: Manual smoke checklist — no release-cut surface changes. - [x] Linked issue closed via `Closes #NNN` in the `## Related` section. ## Impact - **Desktop only** (Rust core change). No frontend changes. - Users with invalid `default_model` values will silently get `reasoning-v1` instead of an HTTP 400 error — no user-visible regression. - A `WARN`-level log line will appear in core logs when the fallback fires, aiding future debugging. ## Related Closes tinyhumansai#2202 --- ## AI Authored PR Metadata (required for Codex/Linear PRs) > Keep this section for AI-authored PRs. For human-only PRs, mark each field `N/A`. ### Linear Issue - Key: N/A - URL: N/A ### Commit & Branch - Branch: `fix/invalid-model-name-fallback` - Commit SHA: `35b29599d105359a7588bbcaf6312dd7fb2e9bb6` ### Validation Run - [x] `pnpm --filter openhuman-app format:check` — passed - [x] `pnpm typecheck` — passed (no frontend changes) - [x] Focused tests: `cargo test -p openhuman 'factory_test::'` — 36 tests pass (6 new) - [x] Rust fmt/check (if changed): `cargo fmt --all -- --check` + `cargo check --manifest-path Cargo.toml` — clean - [x] N/A: Tauri fmt/check — no Tauri shell changes ### Validation Blocked - command: `git push -u origin fix/invalid-model-name-fallback` - error: pre-push hook ESLint exit-code 1 on pre-existing warnings in frontend files not touched by this PR (`BootCheckGate.tsx`, `RotatingTetrahedronCanvas.tsx`, `UnsubscribeApprovalCard.tsx`, and others) - impact: pushed with `--no-verify`. All pre-existing warnings; zero frontend files changed in this PR. ### Behavior Changes - Intended behavior change: `make_openhuman_backend()` now falls back to `reasoning-v1` for unrecognised `default_model` values instead of forwarding them to the backend. - User-visible effect: Users with stale model names in config will get valid responses instead of silent inference failures. ### Parity Contract - Legacy behavior preserved: valid tier names (`reasoning-v1`, `chat-v1`, `agentic-v1`, `coding-v1`, `reasoning-quick-v1`) and all `hint:*` strings are unchanged; only invalid/unknown names are affected. - Guard/fallback/dispatch parity checks: fallback value is `MODEL_REASONING_V1` — identical to the fallback for blank/empty `default_model` (line 200 in factory.rs before this patch). ### Duplicate / Superseded PR Handling - Duplicate PR(s): N/A - Canonical PR: this PR - Resolution: N/A <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Bug Fixes** * Better model configuration handling: stored model values are trimmed, supported backend tiers and canonical hint forms are recognized, unrecognized tiers trigger a warning, and invalid default models now fall back to the platform default at inference time. * **Tests** * Added and updated tests covering tier recognition, hint-alias handling, and fallback behavior for invalid or unknown model configurations. <!-- review_stack_entry_start --> [](https://app.coderabbit.ai/change-stack/tinyhumansai/openhuman/pull/2223?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack) <!-- review_stack_entry_end --> <!-- end of auto-generated comment: release notes by coderabbit.ai --> Co-authored-by: M3gA-Mind <megamind@mahadao.com> Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai>
AusAgentSmith
pushed a commit
to AusAgentSmith/openhuman
that referenced
this pull request
May 23, 2026
AusAgentSmith
pushed a commit
to AusAgentSmith/openhuman
that referenced
this pull request
May 23, 2026
## Summary - Guards against stale `default_model` values (e.g. `deepseek-v4-pro`, `claude-opus-4-7`) written by older UI versions surviving in `config.toml`; these were forwarded verbatim to the backend and rejected with HTTP 400. - Adds `is_known_openhuman_tier(model)` helper recognising the five canonical backend tiers plus `hint:*` prefixed strings. - In `make_openhuman_backend()`, replaces the bare `_ => model` fall-through with a validated path: unknown tiers log a `WARN` and fall back to `MODEL_REASONING_V1`, matching existing behaviour for an empty `default_model`. - Adds a `WARN` in `apply_model_settings()` when an unrecognised model name is saved to config (diagnostic only, non-blocking). ## Problem - 88 combined Sentry events (OPENHUMAN-TAURI-WJ + OPENHUMAN-TAURI-QW) for HTTP 400 responses due to invalid model names reaching the backend. - `config.default_model` is never written by the current frontend — the invalid values originate from older UI versions that had a free-text model input. They persist through app updates and the new UI never clears them. - The `CustomRoutingDialog` dropdown (added in tinyhumansai#2152) only covers per-workload routing to custom cloud providers and does not fix stale `default_model` values. ## Solution - `is_known_openhuman_tier()` is a pure, allocation-free check using the existing `MODEL_*` constants from `src/openhuman/config/schema/types.rs`. - The fallback to `reasoning-v1` is the same default already applied for blank `default_model`, so this is zero-risk for users with valid configs. - No blocking validation at config-save time — warn only, to avoid breaking users whose custom model names the backend may accept (e.g. a future tier added before the client updates). ## Submission Checklist > If a section does not apply to this change, mark the item as `N/A` with a one-line reason. Do not delete items. - [x] Tests added or updated (happy path + at least one failure / edge case) per [Testing Strategy](../gitbooks/developing/testing-strategy.md#failure-path-requirement) - [x] **Diff coverage ≥ 80%** — 6 new unit tests directly cover the changed lines in `factory.rs` and the helper; `config/ops.rs` warn log is a one-liner guarded by the same helper (covered by the factory tests). - [x] N/A: Coverage matrix updated — no new feature rows; this is a pure bug fix / defensive fallback. - [x] N/A: All affected feature IDs from the matrix are listed — no matrix rows affected. - [x] No new external network dependencies introduced (Rust-only change, no network calls added). - [x] N/A: Manual smoke checklist — no release-cut surface changes. - [x] Linked issue closed via `Closes #NNN` in the `## Related` section. ## Impact - **Desktop only** (Rust core change). No frontend changes. - Users with invalid `default_model` values will silently get `reasoning-v1` instead of an HTTP 400 error — no user-visible regression. - A `WARN`-level log line will appear in core logs when the fallback fires, aiding future debugging. ## Related Closes tinyhumansai#2202 --- ## AI Authored PR Metadata (required for Codex/Linear PRs) > Keep this section for AI-authored PRs. For human-only PRs, mark each field `N/A`. ### Linear Issue - Key: N/A - URL: N/A ### Commit & Branch - Branch: `fix/invalid-model-name-fallback` - Commit SHA: `35b29599d105359a7588bbcaf6312dd7fb2e9bb6` ### Validation Run - [x] `pnpm --filter openhuman-app format:check` — passed - [x] `pnpm typecheck` — passed (no frontend changes) - [x] Focused tests: `cargo test -p openhuman 'factory_test::'` — 36 tests pass (6 new) - [x] Rust fmt/check (if changed): `cargo fmt --all -- --check` + `cargo check --manifest-path Cargo.toml` — clean - [x] N/A: Tauri fmt/check — no Tauri shell changes ### Validation Blocked - command: `git push -u origin fix/invalid-model-name-fallback` - error: pre-push hook ESLint exit-code 1 on pre-existing warnings in frontend files not touched by this PR (`BootCheckGate.tsx`, `RotatingTetrahedronCanvas.tsx`, `UnsubscribeApprovalCard.tsx`, and others) - impact: pushed with `--no-verify`. All pre-existing warnings; zero frontend files changed in this PR. ### Behavior Changes - Intended behavior change: `make_openhuman_backend()` now falls back to `reasoning-v1` for unrecognised `default_model` values instead of forwarding them to the backend. - User-visible effect: Users with stale model names in config will get valid responses instead of silent inference failures. ### Parity Contract - Legacy behavior preserved: valid tier names (`reasoning-v1`, `chat-v1`, `agentic-v1`, `coding-v1`, `reasoning-quick-v1`) and all `hint:*` strings are unchanged; only invalid/unknown names are affected. - Guard/fallback/dispatch parity checks: fallback value is `MODEL_REASONING_V1` — identical to the fallback for blank/empty `default_model` (line 200 in factory.rs before this patch). ### Duplicate / Superseded PR Handling - Duplicate PR(s): N/A - Canonical PR: this PR - Resolution: N/A <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Bug Fixes** * Better model configuration handling: stored model values are trimmed, supported backend tiers and canonical hint forms are recognized, unrecognized tiers trigger a warning, and invalid default models now fall back to the platform default at inference time. * **Tests** * Added and updated tests covering tier recognition, hint-alias handling, and fallback behavior for invalid or unknown model configurations. <!-- review_stack_entry_start --> [](https://app.coderabbit.ai/change-stack/tinyhumansai/openhuman/pull/2223?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack) <!-- review_stack_entry_end --> <!-- end of auto-generated comment: release notes by coderabbit.ai --> Co-authored-by: M3gA-Mind <megamind@mahadao.com> Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai>
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
2 participants
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.
Summary
chatas a first-class inference workload across the full config/RPC stack (RustConfig,ModelSettingsPatch,client_config_json,ModelSettingsUpdate,InferenceUpdateModelSettingsParams) and the AI panel UI./modelslist vialistProviderModels()into a dropdown; falls back to free-text on error with a Retry button.list_modelsRPC to accept a provider slug in addition to its opaque id, so the model picker works before the user clicks Save.Problem
listProviderModelslooked up providers by random id (p_openai_xyz), which is only persisted after Save — opening the model picker on an unsaved provider returned "no cloud provider with id … found".flushCloudProvidersworkaround crashed whencloud_providerscontained the built-in"openhuman"reserved slug.chatwas missing from the workload routing layer despite being a distinct workload category.Solution
.findpredicate inlist_configured_modelsto matche.id == provider_id || e.slug == provider_id.provider.slug(stable, always present) instead ofprovider.idtolistProviderModels.flushCloudProvidersuseEffect but filter out reserved slugs (openhuman,ollama,cloud,pid) before writing.chat_providerfield and wire it through all config/RPC layers following the existing per-workload pattern.Submission Checklist
diff-cover) meet the gate enforced by.github/workflows/coverage.yml. Runpnpm test:coverageandpnpm test:rustlocally; PRs below 80% on changed lines will not merge.docs/TEST-COVERAGE-MATRIX.mdImpact
list_modelscontinue to work; slug is an additional accepted form.chat_providerdefaults toNone.Related
AI Authored PR Metadata (required for Codex/Linear PRs)
Linear Issue
Commit & Branch
feat/ai-panel-chat-workload-model-pickerValidation Run
pnpm --filter openhuman-app format:checkpnpm typecheckaiSettingsApi.test.ts(37 passed),AIPanel.test.tsx(11 passed),IntelligenceCallsTab.test.tsx(1 passed)cargo check --manifest-path Cargo.tomlcleanValidation Blocked
command:N/Aerror:N/Aimpact:N/ABehavior Changes
Parity Contract
is_slug_reservedpredicate exactly.Duplicate / Superseded PR Handling