59 Commits

Author SHA1 Message Date
wyuc
cec3c6aaea
Refactor widget actions into the scene action pipeline (#796)
* refactor: align widget actions with scene pipeline

* feat(edit): migrate legacy teacherActions off interactive content on load

The widget-actions pipeline no longer persists a teacherActions authoring
layer; playback reads only scene.actions. Add migrateInteractiveContent to
strip the dead field from existing documents as they load through migrateScene
(wired into all store/classroom load paths). Satisfies the #794 forward-migration
acceptance item.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* fix(generation): default widget_setState.state to {} when the LLM omits it

The removed TeacherAction->Action converter always defaulted state to {}.
Restore that guard in the structured-output parser so an action missing
state can't forward state: undefined into the widget iframe, where
SET_WIDGET_STATE handlers dereference it.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* fix(edit): also strip nested widgetConfig.teacherActions in migration

Legacy WidgetConfig variants each declared their own teacherActions, so existing
documents can carry the dead field nested inside content.widgetConfig as well as
at the top level. Extend migrateInteractiveContent to drop both, preserving all
other widgetConfig fields.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* feat(prompts): document stable widget-action selectors for diagram/game/viz3d

The interactive-actions prompt documented stable target selectors only for
procedural-skill and simulation widgets. Add the canonical selectors the
diagram / game / visualization3d content prompts actually emit (node IDs via
revealOrder; #zoom-in-btn / #canvas-container / #speed-slider / ...; #start-btn),
plus a rule to use widget_setState or a speech-only beat instead of guessing a
target when no stable selector is known (e.g. free-form code widgets). Hardens
against widget actions silently no-oping on non-existent selectors.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: 杨慎 <117187635+cosarah@users.noreply.github.com>
2026-06-28 21:13:21 +08:00
Yizuki_Ame
243e9f3a48
feat: auto-retry transient failures during scene generation (#788)
Adds automatic retry with exponential backoff for scene generation (content/actions/TTS): shared withGenerationRetry helper at the fetch boundary, smart error classification (retries 429/5xx/timeouts/network, fails fast on 401/403/404), AI SDK RetryError unwrapping, abort-aware backoff, per-route thinking config preserved, and upstream HTTP status surfaced for client retry classification. Fixes #755.
2026-06-27 07:20:22 -04:00
杨慎
0f44e9a46f
Add PBL v2 runtime APIs and classroom UI (#799)
* feat: add PBL v2 runtime UI

* fix: ship PBL v2 instructor avatar

* fix: ship PBL v2 workspace logo

* fix: prevent scenario PBL legacy fallback

* chore: restore package lint comments

* test: cover ordinary PBL legacy fallback

* fix: front-load PBL single-call validation

* fix: preserve PBL v2 content when assembling scenes

---------

Co-authored-by: wyuc <wang-yc24@mails.tsinghua.edu.cn>
2026-06-26 11:56:02 +08:00
杨慎
09863af421
Add PBL v2 core schema and generation path (#795)
* feat: add PBL v2 core planner

* chore: restore unrelated lint comments

* fix: document PBL v2 scenario outline flags

* fix: expose PBL scenario subtype in outlines

* chore: clear PBL v2 completion stats lint warning

* chore: address PBL instructor code quality comments

* fix: address PBL v2 review findings

* chore: restore unrelated lint comments
2026-06-25 18:44:46 +08:00
wyuc
1d1ce80e04
feat(maic-agent): editor-agent line (v0) — Pro-mode "Edit with AI" (#777)
Promote the editor-agent line to main: read-then-act editor agent (read_scene_content, regenerate_scene, regenerate_scene_actions, edit_interactive_html), a routable maic-agent model stage, the agent sidebar UI, interactive-scene runtime-error capture, and the timeline/script editor. Cross-reviewed and smoke-verified; see #777.
2026-06-23 16:56:37 +08:00
wyuc
267965d6ed
feat(generation): infer concise courseTitle from outlines for readable course names (#756)
* feat(generation): infer concise courseTitle from outlines for readable course names

Generated courses were named after the raw user prompt (truncated to 500 chars
client-side, or 50 chars / first outline title server-side), which is long and
unreadable. The outline-generation step already understands the full course
semantics, so have it emit a concise `courseTitle` alongside `languageDirective`
and `outlines`, and use it as the stage name.

- Prompts (requirements-to-outlines, interactive-outlines): top-level JSON gains
  a required `courseTitle` (≤30 chars, in the teaching language, noun phrase).
- Streaming route: extract `courseTitle` head-bound like `languageDirective`,
  emit a `courseTitle` SSE event, and include it in the `done` event.
- Non-streaming outline-generator: parse and return optional `courseTitle`
  (defensive trim + 120-char cap).
- Naming: stage.name = courseTitle || outlines[0]?.title || requirement fallback
  (client preview path backfills stage.name after outlines resolve; server
  classroom-generation uses it directly).
- Session: persist `courseTitle` on GenerationSessionState for reload safety.
- Tests: add courseTitle parsing coverage; e2e mock done event carries it.

Fully optional in the pipeline — every consumer falls back to the previous
behavior when the field is absent, so legacy/LLM-skipped cases are unaffected.

* fix(generation): make courseTitle propagation robust across all outline paths

Address review feedback on the courseTitle threading.

Prompts — align every outline-prompt schema statement to the 3-key shape.
The user-prompt "final reminder" / top-level shape blocks for
requirements-to-outlines, interactive-outlines, and task-engine-outlines still
demanded the old two-key {languageDirective, outlines} object; as the last
instruction the model reads, that caused it to omit courseTitle and the stage
name to fall back to the raw requirement. Task Engine prompts now emit
courseTitle as well.

Streaming route — normalize the streamed courseTitle (trim, ignore
whitespace-only, cap length) to match the non-streaming parser, and add a
full-buffer fallback so a title emitted after the outlines array or beyond the
head-scan window is still recovered before the done event.

Client — reset latched languageDirective/title on outline retry so a
succeeding attempt that omits them falls back instead of inheriting a failed
attempt's stale value; also carry courseTitle in the stream-end resolve path
that fires when the stream closes without an explicit done event.

courseTitle remains optional on every consumer path.

---------

Co-authored-by: wyuc <zdq1204@gmail.com>
2026-06-18 18:31:38 +08:00
wyuc
25cf58d19f
feat(model): optional per-stage LLM model routing (#745) (#747)
* feat(model): optional per-stage LLM model routing (#745)

Add a config-only stage -> model map consulted during model resolution,
falling back to DEFAULT_MODEL when unset (zero behavior change unless opted in).

- lib/server/model-routes.ts: parse/validate/cache MODEL_ROUTES env JSON;
  LLM_STAGES registry of routable stages; getStageModel(stage).
- resolveModel: resolution order x-model > stage route > DEFAULT_MODEL > builtin;
  thread optional `stage` through resolveModelFromHeaders/FromRequest.
- Wire each route's resolveModel call site to its stage; classroom-generation
  resolves generate-classroom and web-search-query-rewrite independently.
- .env.example: document MODEL_ROUTES; unit tests for both modules.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(model): address cross-review findings for per-stage routing (#745)

- classroom-generation: resolve the web-search-query-rewrite model lazily,
  only when explicitly routed and inside the web-search branch, with try/catch
  fallback to the classroom model. Fixes a regression where a misconfigured
  optional route (keyless/invalid provider) threw and aborted ALL classroom
  generation even with web search disabled; also avoids wasted resolution on the
  common no-search path and preserves classroom-model inheritance when unrouted.
- resolve-model: type the stage param as LlmStage across resolveModel/
  resolveModelFromHeaders/resolveModelFromRequest so a mistyped stage literal is
  a compile error instead of silently falling through to DEFAULT_MODEL.
- model-routes: simplify the cache to a process singleton (matching
  provider-config), dropping the raw-string-keyed cache and redundant STAGE_SET.
- .env.example: clarify x-model precedence and that a route to an unconfigured
  provider fails at request time (no startup validation), like a bad DEFAULT_MODEL.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(model): stage route takes precedence over client x-model (#745)

Cross-review (codex P2 + Claude tracer) found that the browser UI always sends
its saved model as x-model, so the previous x-model > stage order made
MODEL_ROUTES inert for normal UI traffic on exactly the heavy stages the RFC
targets (scene-content, quiz, pbl-chat, chat). Flip resolution to
stage route > x-model > DEFAULT_MODEL: a configured route is the operator's
deliberate per-stage choice and wins, while unrouted stages still honor the
client's x-model. Update docs and tests accordingly.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* style(model): prettier-format changed files for #745 CI

Run the repo formatter (pnpm check / prettier) on the changed routes, the new
model-routes module, and the new tests so `prettier . --check` (CI) passes;
also correct a stale precedence comment in the resolve-model test.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(model): isolate routed model from client connection params (#745)

When a stage route overrides the client's x-model and points at a different
provider, the client-sent apiKey/baseUrl/providerType (for the client's model)
must not bleed onto the routed provider — otherwise a routed Anthropic model
would be constructed with the client's OpenAI providerType/key and fail. A
routed model now resolves its connection params purely from server config, as
if no x-model was sent. Unrouted stages still honor the client params. Adds
tests covering both the drop (routed) and keep (unrouted) cases.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs(model): correct graceful-degradation comment in classroom (#745)

resolveModel does not throw on a missing key; clarify that a keyless route
surfaces later in callLLM (degraded by the outer try/catch), while only a
resolution-time failure is caught at the rewrite re-resolve. Comment-only.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(model): route scene-content per scene type (#745)

Extend MODEL_ROUTES with composite keys scene-content:<type> for the four core
scene types (slide/quiz/interactive/pbl). getStageModel now resolves composite
`a:b` stages most-specific-first, trimming `:` segments, so scene-content:<type>
falls back to the base scene-content route, then x-model, then DEFAULT_MODEL.
The scene-content route derives its stage from outline.type. Backward
compatible: with no composite key configured, behavior is unchanged.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(model): per-stage thinking effort + drop hardcoded gpt fallback (#745)

MODEL_ROUTES values may now be {model, effort} (not just a model string) to pin
the thinking effort per stage. Arbitration mirrors model routing: a routed stage
with effort set wins over the client's thinking (effort "none" disables); routed
with no effort uses the model's default and drops client thinking; unrouted
stages keep the client thinking. resolveModel is the single arbiter — body
thinking is threaded in via resolveModelFromRequest. classroom-generation passes
the resolved thinking into its callLLM calls so generate-classroom and
web-search-query-rewrite honor route effort too.

Also: removed the hardcoded `|| 'gpt-5.4-mini'` fallback in resolveModel — if no
model resolves (no route / x-model / DEFAULT_MODEL) it now throws instead of
silently picking a vendor default.

model-routes: getStageRoute returns {model, effort?}; getStageModel delegates to
it. Docs + tests updated.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* refactor(model): route value carries full ThinkingConfig (#745)

Per-stage routing accepts the full unified ThinkingConfig in the route value
({model, thinking:{mode,effort,level,enabled,budgetTokens,excludeReasoningOutput}})
instead of just an effort string. The route's thinking is passed through
resolveModel and normalized per the model's capability by callLLM, so
budgetTokens (qwen), level (Gemini), enabled/mode, etc. all work.

(qwen3.7-plus/max thinking capability now comes from upstream #753, so this no
longer registers them.)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(model): honor routed thinking for chat-adapter; doc fixes (#745)

Cross-review (codex P2 + Claude) found chat-adapter was the only routable stage
that ignored the route's thinking: it took the routed model but built its own
thinkingConfig from the request body, so operator-pinned thinking never applied
and client thinking still leaked onto a routed model. Now pass the client
thinking into resolveModel and use the resolved thinkingConfig (route-pinned for
a routed stage, client otherwise; defaults to disabled for low-latency chat).

Also: clarify DEFAULT_MODEL is now required for server-side stages (the
hardcoded gpt-5.4-mini fallback was removed → resolveModel throws if nothing
resolves), and fix a stale {model,effort}→{model,thinking} doc comment.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 22:26:37 +08:00
jackefn
a7cb5b5813
feat(document): add extractor provider foundation (#704) 2026-06-14 16:59:40 +08:00
wyuc
3f80a92a28
fix(generate): make outline streaming + interactive post-processing linear (was O(n²)/O(K·L)) (#732)
Two streaming generation paths do super-linear work on the model output and can
block the Node event loop (and balloon the heap) on large or pathological
responses:

1. app/api/generate/scene-outlines-stream re-parses the ENTIRE accumulated
   buffer on every streamed chunk — extractLanguageDirective (full-buffer regex)
   and extractNewOutlines (char-walk from the array start). That is O(n²) over
   the stream; a ~300 KB response blocks the event loop for ~20 s.
2. lib/generation/interactive-post-processor convertLatexDelimiters restores
   <script> placeholders by rebuilding the whole HTML string once per block —
   O(blocks × length). A widget with many <script> tags blocks for tens of
   seconds and allocates GBs.

Fixes:
- extractNewOutlines: parse incrementally, resuming from a cursor so the buffer
  is scanned once across the stream (O(n)). Behaviour-equivalent — verified
  across chunk sizes, markdown fences, flat arrays, prose preambles, and
  braces/escapes inside string values.
- extractLanguageDirective: bound the regex to the buffer head (the directive is
  the first wrapper key), O(1) per chunk.
- Restore <script> blocks in a single pass with a function replacer ($-safe).
- Stream-loop hardening: honor request abort and propagate the AbortSignal to
  the LLM call so upstream generation stops on disconnect; cap the accumulated
  buffer; guard controller.close() against double-close.

Standalone repro (copied functions): 300 KB outline stream 20.8 s -> 1.3 s;
45 MB widget HTML >30 s + OOM -> 45 ms.

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-13 13:58:08 +08:00
RongHuiQiang
50c0aefd13 fix(vocational): gate procedural content generation 2026-06-09 23:43:34 +08:00
RongHuiQiang
170b7df98f merge upstream/main into vocational task engine branch 2026-06-09 16:20:35 +08:00
RongHuiQiang
e6debb093b fix(vocational): address review feedback 2026-06-09 11:30:38 +08:00
ly-wang19
3ccd5da6da
feat(generation): opt-in parallel scene-content generation (#660)
* feat(generation): opt-in parallel scene-content generation

Scene generation was strictly serial — content -> actions -> TTS, one
outline at a time — so an N-scene classroom paid N x (content + actions
+ TTS) of wall-clock latency, which dominates the post-outline wait.

Add an opt-in hybrid two-phase path (#572):

- Phase 1 fetches scene *content* concurrently (bounded). Content is the
  only per-scene step independent of cross-scene state, so it is safe to
  parallelise; a content failure marks just that outline and does not
  pause the batch.
- Phase 2 keeps the existing in-order actions + TTS loop, so
  previousSpeeches threading, ordered addScene, the abort/epoch guards,
  and the pause-on-failure UX are all unchanged.

Gated by a server-side PARALLEL_SCENE_CONCURRENCY (default 0 = off,
clamped to 10), surfaced to the client through the existing
/api/server-providers response. With it unset the content map is null
and the loop is byte-for-byte the original serial path, so out-of-box
behaviour is unchanged.

The bounded worker pool is extracted to lib/utils/concurrency.ts
(mapWithConcurrency, with an early-stop hook for abort/epoch) and
unit-tested; getParallelSceneConcurrency env parsing/clamping is tested
too.

Closes #572

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* refactor(generation): pipeline content fetches instead of a barrier

Address @wyuc's review on #660. The previous version awaited the whole
bounded content pool before Phase 2, so for N > C scenes the user saw the
first scene, then a stall on a single page for the entire content phase,
then a burst — perceived as worse than serial despite the wall-clock win
(the gap scales with ceil((N-1)/C)).

Pipeline instead: lazyBoundedMap starts the content fetches (<= C in
flight) and returns one promise per outline immediately; the serial loop
awaits them in order, so each resolves as soon as its own content is ready
(usually already done, hidden behind the previous scene's actions/TTS). The
first scene now paints after content(1)+actions(1)+TTS(1) — same as serial
— with the full concurrency benefit and no stall.

Also from the review:
- a content fetch can no longer take its siblings down: an unexpected throw
  is caught and returned as a failure result, routed through the same
  mark-failed path as the serial loop (symmetric);
- drop the cosmetic Phase-1 setCurrentGeneratingOrder — the loop already
  sets it per outline;
- note the intentional belt-and-suspenders clamp;
- concurrency.test.ts asserts <= limit (not == limit), and gains
  lazyBoundedMap tests including the no-barrier property.

mapWithConcurrency is kept as a thin await-all wrapper over lazyBoundedMap.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: ly-wang19 <ly-wang19@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: wyuc <wang-yc24@mails.tsinghua.edu.cn>
2026-06-08 07:44:33 -04:00
wyuc
d7c0d80afe
feat(tts): per-agent auto-voice quality + register-once timbre stability (#670) (#672)
* feat(tts): voxcpm voice-design types + deterministic voice id helpers (#670)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* feat(tts): emit + persist per-agent voiceDesign descriptor (#670)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* feat(tts): voxcpm voice registration backend client (#670)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* feat(tts): voxcpm-voice ensure/register endpoint (#670)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* feat(tts): client auto-voice registration + reference-clip cache (#670)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* feat(tts): reference registered voice id in vLLM-Omni speech (#670)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* feat(tts): thread voiceDesign + backend through tts call sites (#670)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* fix(tts): match vLLM-Omni voice registration contract (#670)

Live e2e against the real backend revealed the assumed multipart contract was
wrong: POST /v1/audio/voices needs name + consent + audio_sample (not
voice_id/file), and there is no per-name GET (405) — existence must list
/v1/audio/voices and check membership.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* refactor(tts): make auto-voice register-once pattern provider-neutral (#670)

The descriptor + register-once/reference-by-id pattern is not VoxCPM-specific.
De-couple it into a provider-neutral seam so other registration-capable
providers (ElevenLabs/MiniMax/Doubao voice cloning, …) can plug in:

- lib/audio/voice-design.ts: VoiceDesign + buildVoiceDesignPrompt /
  normalizeVoiceDesign / getDeterministicVoiceId (neutral 'auto-<hash>' id,
  namespaced by providerId).
- lib/audio/voice-registration.ts: VoiceRegistrationAdapter interface +
  providerId->adapter registry + supportsVoiceRegistration.
- lib/audio/voice-registration-client.ts: neutral ensureRegisteredVoice() +
  IndexedDB clip cache.
- app/api/generate/voice (replaces .../voxcpm-voice): dispatches by providerId.
- voxcpm-registration.ts becomes the VoxCPM adapter (sole registered provider).
- AgentConfig.voiceDesign + DB cache table renamed neutral.

Behavior-preserving; VoxCPM-specific bits (inline (prompt)text, backend kinds,
capability gate) stay in the voxcpm modules. Full suite green (674).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* fix(tts): build the voice clip Blob from an inline Uint8Array (#670)

A factored-out helper returning Uint8Array widened to Uint8Array<ArrayBufferLike>,
which next build (stricter than bare tsc) rejects as a BlobPart. Inline the
buffer like the rest of the repo does.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* feat(tts): managed TTS providers resolve model server-side (#670)

A server-managed TTS provider's model was still client-driven, but the
managed-provider settings UI hides the model field — so a backend whose model
id isn't the client default (e.g. VoxCPM/vLLM-Omni serving the full model path)
always 500'd. resolveTTSModel() makes the model authoritative from server
config (${PREFIX}_MODELS, first entry) for managed providers, like key/baseUrl;
unmanaged/unconfigured providers keep the client model unchanged. Used by the
tts and voice routes.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* fix(tts): single agent-voice resolver + stable teacher narration voice (#670)

Route all TTS voice resolution (narration, discussion, preview) through one
resolveAgentVoiceOptions(agent, ...) that reads the agent profile and registers
+ references the voice by id. Eagerly warm up generated agents' voices on save.

Critically fixes the teacher narration drifting (male/female jumps): the registry
is always seeded with DEFAULT_AGENTS, so the old narration lookup
find(role==='teacher') returned the default teacher (no voiceDesign) instead of
the generated one — so narration never registered a voice and fell back to the
inline prompt. pickNarratorAgent() now prefers the teacher carrying a voiceDesign.

Also: drop language from the deterministic voice id (descriptor already encodes
it) so narration (directive) and discussion (locale) resolve the same id; log
the effective registeredVoiceId. Regression tests for pickNarratorAgent.

Verified e2e: agent-profiles -> 1 voice registration -> 16 narration TTS all
referencing the same registeredVoiceId; voice present on the backend.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* feat(tts): fall back to persona as the voice seed for agents without a voiceDesign (#670)

Preset/default agents carry no LLM voiceDesign. Rather than add a static field,
derive the bootstrap descriptor from the agent's persona when voiceDesign is
absent, so they still register one stable reference voice (stable-but-generic;
persona is not a vocal spec). Generated agents keep their LLM voiceDesign.
Also hardens replay: stage snapshots drop voiceDesign but keep persona.

Unit-tested: resolveAgentVoiceOptions uses real voiceDesign when present, persona
otherwise.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* fix(tts): match Auto Voice by its localized label in the agent voice picker (#670)

The picker filtered on voice.name ('Auto Voice'), but Auto Voice is shown via
its localized label (自动音色). Searching '自动' returned '没有匹配音色'. Match
the localized label for the Auto Voice option so it's findable in any language.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* fix(tts): address code-review round 1 (#670)

- strip parentheses in the voice-design prompt so a paren in the descriptor/
  persona can't corrupt the (prompt)text bootstrap delimiter
- gate POST /api/generate/voice on isServerTTSProviderDisabled (#665): a
  force-disabled provider was off for the tts route but not this sibling
- check voiceExists before re-registering a client-cached clip, so a cached
  voice that's still live isn't needlessly re-uploaded every session
- dedup concurrent ensureRegisteredVoice calls via an in-flight promise map
  (eager warm-up + first utterance no longer double bootstrap/register)
- warm up only the narrator (teacher), not every generated agent, to avoid
  synthesizing voices at save time for agents that may never speak
- collapse the duplicated vLLM-Omni speech payload into one object

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* chore(tts): prettier formatting (#670)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* fix(tts): key auto-voice memo by (voiceId, backend) so a base-URL change re-registers (#670)

Addresses review (cosarah): registeredThisSession/inFlight were keyed by voiceId
alone, so switching the VoxCPM base URL mid-session made ensureRegisteredVoice
short-circuit and return an id registered only on the old backend — TTS then sent
that stale registeredVoiceId and skipped the inline fallback, failing with
voice-not-found on the new backend. Memo key now includes the base URL; the
IndexedDB clip cache stays keyed by voiceId (the reference clip is
backend-independent and reused to re-register elsewhere). Regression test added.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* fix(tts): include API key in the auto-voice memo key (#670)

Addresses review (cosarah, round 2): memoKeyFor was keyed by (voiceId, baseUrl)
but not the API key. Registration/existence checks and speech calls are
auth-scoped, so switching account/key on the same base URL could reuse a
registeredVoiceId from the old credentials and skip re-validation. Memo key now
includes the API key (in-memory only, never persisted/logged). Regression test
covers the key-switch case.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: 杨慎 <117187635+cosarah@users.noreply.github.com>
2026-06-08 14:37:49 +08:00
jackefn
c58893e76f feat(vocational): add task engine and procedural skill widgets 2026-06-08 11:13:09 +08:00
wyuc
3e1e9f083b
feat(tts): unify provider-enablement model, default browser-native off (#665) (#666)
A single TTS provider-enablement model honored everywhere (picker,
auto-assignment, fallback, lecture/playback, server).

Model
- lib/audio/provider-enablement.ts: isTTSProviderConfigured /
  isTTSProviderEnabled / listEnabledTTSProviderIds. Availability drops the
  registry defaultBaseUrl fallback (fixes Lemonade's always-shown voices),
  honors the per-provider `enabled` flag, server-disable overrides (server
  precedence).
- voice-resolver: getEnabledProvidersWithVoices (enabled server/custom
  providers) and getSelectableProvidersWithVoices (the ONE client source of
  truth = enabled providers + opt-in browser-native when the browser exposes
  voices). resolveAgentVoice picks deterministically among the given providers,
  honors a voiceConfig only while its provider is present.
- Picker + discussion build their list from getSelectableProvidersWithVoices, so
  the AgentBar and the live discussion agree on selectable voices (fixes
  student agents going silent in auto mode). Students resolve via
  resolveAgentVoice; the teacher uses the global lecture voice verbatim (same
  voice the pre-generated lecture sends), so lecture and discussion never
  diverge.
- Voice assignment vs fallback: an agent's voice is bound at generation (the
  agent-profile LLM picks from availableVoices; preset uses the user's pick).
  The fallback for a missing/invalid/unavailable voice is applied only at the
  live TTS calls, not baked into the saved agent — so it reflects current
  provider availability.

Defaults / opt-in
- Browser-native: first-class, default OFF, opt-in. Built-in providers default
  enabled:true (only surface once configured).
- TTS master toggle defaults OFF; first server-sync auto-enables it when a
  provider is configured (mirrors image/video).
- Persist v3->v4 migration normalizes the never-user-editable flags.

Server/admin disable (server precedence): server-providers.yml `enabled:false`
and env `TTS_<P>_ENABLED=false` (incl. browser-native). Surfaced as a per-provider
`disabled` flag on /api/server-providers; merged as serverDisabled; enforced at
the /api/generate/tts trust boundary, classroom media generation, and /api/health.

UI
- Settings TTS panel: per-provider enable toggle, disabled (with a hint) when the
  provider is unavailable, locked off (with a note) when server-disabled.
- AgentBar voice pills render disabled with a "No voice" placeholder when no
  provider is enabled. The toolbar media-popover TTS tab keeps its existing
  on/off toggle (no picker/CTA).

Tests: predicates, resolver determinism + unified selectable list, server
force-disable, store merge + migration + TTS auto-enable, i18n parity. Verified
in a real browser (Playwright): settings toggle states + a full Gemini classroom
generation whose TTS requests used the picked voice.

Found on main @ 2586cb5.

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: 杨慎 <117187635+cosarah@users.noreply.github.com>
2026-06-07 17:25:57 +08:00
ly-wang19
2586cb5e05
fix(tts): surface provider rate-limit errors as HTTP 429 (#644)
TTS providers throw a plain `Error` on any non-OK response, and the
`/api/generate/tts` route catches everything as `GENERATION_FAILED` (500),
so an upstream 429 (quota/concurrency) was indistinguishable from a real
failure — clients had no signal to retry/back off. `TTSRateLimitError`
already existed for exactly this (with a TODO noting the route collapses
everything uniformly), but only Doubao threw it and the route never mapped
it.

- Add a `RATE_LIMITED` API error code.
- Map upstream HTTP 429 to `TTSRateLimitError` at every provider's
  `!response.ok` site via a shared `throwIfTtsRateLimited` helper.
- Return `429 RATE_LIMITED` from the TTS route when a `TTSRateLimitError`
  is caught (all other errors unchanged).

Purely additive: non-429 responses keep their existing error messages.

Co-authored-by: ly-wang19 <ly-wang19@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: wyuc <wang-yc24@mails.tsinghua.edu.cn>
2026-06-03 12:11:15 +08:00
wyuc
2165e55bac
feat: add MiniMax web search provider (#634) 2026-06-02 11:47:13 +08:00
wyuc
35d36905d1
Make server-configured providers admin-managed, not client-overridable (#620) (#624)
* refactor(providers): make server-configured providers admin-managed, not client-overridable

A server-configured provider is now authoritative: the operator owns its API
key and base URL, and the client cannot override either. This collapses the
tri-state (server key / client base URL / client key) that was the root of a
recurring "missing API key" bug class — when the settings UI echoed a base URL
with an empty key, routes that treated "any base URL ⇒ fully client-configured"
dropped the server key. #533 patched that per-route via canUseServerApiKeyForBaseUrl;
this removes the guard entirely by fixing the design.

Server:
- resolve*ApiKey/BaseUrl ignore client values when the provider is server-
  configured; add isServerConfiguredProvider(section, id); drop
  canUseServerApiKeyForBaseUrl + normalizeProviderBaseUrl.
- getServer*Providers() no longer return base URLs — only allowed models
  (LLM/image) and the managed flag (presence) — so an internal gateway/proxy
  endpoint is never exposed to the client.
- routes (chat/image/video/tts/asr/pdf + verify-*) resolve managed providers
  purely server-side; SSRF validation now applies only to unmanaged (client)
  base URLs.

Client:
- drop serverBaseUrl from ProviderSettings, the settings store, request-building
  (TTS base URL no longer echoes the server URL) and voice resolution.
- settings UI renders managed providers read-only: the key/base-URL override
  inputs and region toggles are hidden, leaving the "managed by server" notice.

Tradeoff: overriding a server provider's key with your own for the same provider
is removed; add a separate custom provider instead. Closes #620.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* chore(providers): refresh managed-provider copy, drop dead audio-settings, add #620 e2e

- serverConfiguredNotice now says the provider is managed and not editable here,
  pointing users to add a separate provider for their own credentials (7 locales).
- delete components/settings/audio-settings.tsx — unreferenced dead code.
- add e2e/tests/managed-provider-620.spec.ts: managed provider hides the
  key/base-URL inputs; unmanaged provider keeps them.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* feat(providers): lock the model catalog for managed providers with a pinned list

When the operator pins an allowed model list (MODELS env/yaml ⇒ serverModels),
the model catalog is admin-managed too: the LLM provider panel shows the pinned
models read-only with a "Server" badge and no add / reset / edit / delete
affordances. Without a pinned list the server manages only credentials and the
user keeps curating models.

This removes the prior inconsistency where the settings panel let you add models
to a pinned managed provider that the generation toolbar then filtered out.

e2e: the managed-openai case now also asserts the catalog is locked.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* fix(providers): ignore (not reject) client overrides for managed web-search; clear legacy serverBaseUrl

Addresses review feedback on #624:

1. Managed web-search providers now ignore a client-sent key/baseUrl instead of
   validating and rejecting it. A server-configured provider is admin-owned, so
   the server config is authoritative and a stale client base URL is dropped
   rather than 400-ing the request. The allowlist validation still runs for
   unmanaged providers, where the client base URL is actually used.

2. Drop the removed `serverBaseUrl` field from persisted localStorage on
   rehydrate (settings version 2 -> 3, stripped in both migrate and merge), so
   old clients don't keep a stale server URL in client state.

Tests: web-search route test split into unmanaged-rejects-allowlist and
managed-ignores-client-baseUrl; settings rehydrate test asserts a legacy
serverBaseUrl is stripped. Full suite 381 pass; e2e 2 pass.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: 杨慎 <117187635+cosarah@users.noreply.github.com>
2026-05-31 21:28:22 +08:00
wyuc
86c8e0c543
feat: inline external assets at export for offline classrooms (#596) (#613)
* feat(export): add external-asset reference scanner for HTML inlining

* feat(export): add cached asset fetcher and data-uri encoder

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(export): recursively inline url() refs inside stylesheets

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(export): orchestrate inlining of links, scripts, images, and inline css

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* refactor(export): drop dead escapeAttr, harden importmap skip in scanner

* feat(export): inline importmap modules incl three/addons graph closure

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* refactor(export): extract shared module to break inline-assets import cycle

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(export): inline interactive-scene assets into .maic.zip at export

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(export): inline interactive assets in Resource Pack export too

* docs: document offline export asset inlining

* style: prettier formatting

* fix(test): resolve tsc type errors in export-classroom-inline test

* fix(export): keep importmap prefix fallback on partial failure, chunk base64, preserve media attr, log pptx inline failures

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* perf(export): parallelize asset fetching, share fetcher across scenes, promise-cache

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix(export): retry transient asset fetches, bound concurrency, warn user on partial inline

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* perf(export): inline only woff2 fonts, drop woff/ttf siblings to halve size

Within @font-face blocks that have a woff2 url(), rewrite sibling woff/ttf/otf/eot
refs to url(about:invalid) instead of inlining them. Falls back to full inline for
ttf-only blocks. Drops katex output from ~1.79MB to ~0.71MB (~3x fewer font fetches).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* i18n(export): translate partial-inline warning and surface failed asset hosts

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(proxy-media): follow redirects with per-hop SSRF revalidation (#398)

Replace blanket redirect rejection with a bounded 5-hop follow loop that
re-validates every Location target through validateUrlForSSRF before
fetching, preventing redirect-to-internal SSRF while allowing CDN
redirects (e.g. cdn.tailwindcss.com 302→/3.4.17).

* feat(export): route asset inlining through proxy-media to bypass CORS

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix(export): keep importmap prefix fallback, forward proxy 4xx, cap proxy size, re-export FetchAsset

* style: prettier formatting for proxy-media + proxied-fetch

* fix(export): report CSS-nested asset failures in inline report

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: 杨慎 <117187635+cosarah@users.noreply.github.com>
2026-05-31 18:36:39 +08:00
LooThao
6d29bbe9af
Fix server API key fallback when client echoes provider base URL (#533)
* Fix server API key fallback for provider base URLs

* Format verify PDF provider route

---------

Co-authored-by: wyuc <wang-yc24@mails.tsinghua.edu.cn>
2026-05-30 13:16:41 +08:00
Helck
679130a6b9
feat(ai): add Xiaomi MiMo Token Plan support (#578) 2026-05-17 15:24:30 +08:00
Yizuki_Ame
47cc2a510c
feat: add Brave Search and Baidu Search integration
Add Brave Search and Baidu Search providers with Baidu sub-source support, provider configuration updates, tests, and docs links.
2026-05-13 20:28:56 +08:00
杨慎
be759a8252
feat: add lemonade to provider (#508)
* feat: add lemonade to provider

* fix(lemonade): correct TTS/ASR model IDs and expand Kokoro voices

- TTS model: kokoro → kokoro-v1
- ASR model: single 'whisper' → 6 Whisper variants (Base/Large-v3/Large-v3-Turbo/Medium/Small/Tiny), default Whisper-Base
- Expand lemonade-tts voices to full Kokoro v1 set (54 voices across en-US/en-GB/zh-CN/ja-JP/es/fr-FR/hi/it-IT/pt-BR)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(lemonade): zh-TW i18n parity, real Kokoro default voice, language code consistency

- zh-TW.json: add missing providerLemonadeTTS/ASR/Image keys
- TTS default voice: 'default' → 'af_heart' (Kokoro expects real voice ID, not placeholder)
- Voice language codes: 'es'/'hi' → 'es-ES'/'hi-IN' for consistency

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test(lemonade): add unit tests for image/TTS/ASR adapters and wav-utils

Covers:
- lib/media/adapters/lemonade-image-adapter: request shape, base URL fallback, custom model, optional Bearer auth, error paths, connectivity probe
- lib/audio/tts-providers (lemonade-tts case): request body (model/voice/format), af_heart fallback, optional auth, error path
- lib/audio/asr-providers (lemonade-asr case): WAV-only validation, model/language form fields, "audio is empty" graceful empty result, error propagation, default model fallback
- lib/audio/wav-utils: isWavBlob detection by MIME and filename, normalizeASRUploadAudio pass-through and wav handling

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(lemonade): remove text path fork and harden fallbacks

* style: format lemonade tts files

* i18n: add lemonade voice language labels

* fix(lemonade): align image default model and harden wav detection

* test(lemonade): fix File BlobPart typing

* fix(lemonade): simplify tts voice selection and clear asr test state

* docs: highlight Lemonade support

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: wyuc <wang-yc24@mails.tsinghua.edu.cn>
2026-05-08 13:53:37 +08:00
wyuc
dbe1d2ec76
[codex] Add Bocha web search provider (#524)
* Add Bocha web search provider

* Address Bocha web search review feedback
2026-05-04 12:06:05 +08:00
wyuc
5e12ad892c
[codex] add VoxCPM2 TTS provider (#496)
* add voxcpm2 tts provider

* address voxcpm review feedback

* translate voxcpm locale strings

* narrow toolbar model pill

* refine toolbar media controls

* address voxcpm review followups
2026-04-26 23:45:23 +08:00
wyuc
e613b7578f
[codex] add per-model thinking config (#494)
* add per-model thinking config

* Refine thinking model controls

---------

Co-authored-by: 杨慎 <117187635+cosarah@users.noreply.github.com>
2026-04-26 19:41:10 +08:00
Yizuki_Ame
3fafca5f99
feat(prompts): conditional media snippets in generation prompts (#490)
* feat(prompts): conditional media snippets in generation prompts (#483)

Replace always-included media instructions + negative-override pattern with conditional snippet includes gated on imageEnabled/videoEnabled flags.

- Extend prompt loader with {{snippet:name?if=condition}} syntax

- Extract 15 media instruction snippets from outline and slide templates

- Wire imageEnabled/videoEnabled through outline-generator, scene-generator, and route handler

- Remove mediaGenerationPolicy negative-override from all call sites

- Close gap: slide content generation now receives media policy

- Unify pre-output checklist to labeled bullet format

* refactor(prompts): replace ?if= snippet syntax with {{#if}} inline blocks

Address review feedback on PR #490 — the file-per-fragment pattern was
too fine-grained (6 of 15 new snippets were ≤2 lines).

Changes:
- Add {{#if name}}...{{/if}} block syntax to the loader (~10 lines)
- Inline 9 micro-snippets (≤4 lines each) back into host templates
- Keep 3 large instruction snippets as {{snippet:name}} wrapped in
  {{#if}} at the call site
- Drop ?if= syntax and PromptLoadOptions.conditions — conditional
  blocks read directly from buildPrompt's variables
- Update tests and README

Processing order: snippets → conditional blocks → variable interpolation

* style: format media-conditional test with prettier
2026-04-26 14:52:09 +08:00
wyuc
fc6b186929
refactor(whiteboard): file-based prompts + geometry conflict detection (#485)
* feat(prompts): declare whiteboard role prompt IDs + whiteboard-reference snippet

* feat(prompts): add whiteboard role template skeletons + reference snippet stub

* refactor(orchestration): move buildWhiteboardGuidelines to role-specific markdown templates

* docs(prompts): whiteboard guidelines now in markdown templates

* feat(prompts): whiteboard-reference canvas + JSON output sections

* feat(prompts): whiteboard-reference action schemas for text/shape/line

* feat(prompts): whiteboard-reference action schemas for latex/chart/table

* feat(prompts): whiteboard-reference action schemas for code/delete/clear/close

* feat(prompts): whiteboard-reference LaTeX JSON escape section

* feat(prompts): whiteboard-reference bounds + overlap section

* feat(prompts): whiteboard-reference font + latex height tables

* feat(prompts): whiteboard-reference pre-output checklist

* feat(prompts): expand teacher whiteboard template

* feat(prompts): expand assistant whiteboard template

* feat(prompts): expand student whiteboard template

* test(prompts): assert whiteboard-reference sections reach every role prompt

* tune(prompts): cap teacher element budget at 4/turn, encourage wb_clear on crowded board

* tune(prompts): simplify teacher template — single conservative rule + state-awareness emphasis

* tune(prompts): add LaTeX-height × text-fontSize pairing table for visual weight consistency

* feat(orchestration): preserve image parts from UIMessage to AI SDK ModelMessage

* feat(eval): attach prior-turn whiteboard screenshot as user message image part

Gated behind EVAL_ATTACH_PRIOR_SCREENSHOT=1 env. When on, captures a
screenshot after every turn (not just checkpoints) and attaches it as a
file part with mediaType:'image/png' on the next user message. Teacher
prompt gets a new 'Prior-state image' section telling the agent to
treat it as direct visual feedback.

* fix(orchestration): strip data: prefix before passing image to AI SDK

Vercel AI SDK's streamText/generateText treats ImagePart.image as a URL
to fetch when it's a string. data: URLs fail the http/https scheme check
and throw AI_DownloadError. Strip the data URL prefix and pass raw base64
with mediaType separately — AI SDK treats base64 strings as data content.

* refactor(whiteboard): add conflict summarizer, drop prior-screenshot feature

Eval across flash (image-on vs off × repeat-3) and pro (same) showed the
prior-screenshot image-input feature gives ~0 net benefit: +0.4 overall on
flash and −0.6 on pro. The image feedback loop's theoretical upside
(agent self-correcting from visual) didn't materialize — weak models
couldn't act on the image and strong models "found things to fix" and
over-corrected. Meanwhile programmatic geometry detection on the raw JSON
cleanly lifted overlap from 6.3 → 8.1 on flash.

So: remove the image-input plumbing, keep a programmatic equivalent.

## Removed (reverts 0e07e9e, b5675bc, image half of 097ec2f)

- lib/orchestration/ai-sdk-adapter.ts: revert multimodal content passthrough
- lib/orchestration/summarizers/message-converter.ts: revert image part
  extraction; user content is back to string-only
- lib/orchestration/summarizers/conversation-summary.ts: revert multimodal
  content flattening
- lib/orchestration/director-graph.ts: revert HumanMessage multimodal cast
- tests/orchestration/message-converter.test.ts: deleted (was purely
  image-conversion tests)
- eval/whiteboard-layout/runner.ts: drop image attach, vision gate,
  per-turn screenshot capture; revert to checkpoint-only capture
- Role templates (wb-teacher / wb-assistant / wb-student): strip
  "Prior-state image" sections

## Added

- lib/orchestration/summarizers/whiteboard-conflicts.ts: pure geometry
  detector. Computes bbox IoU, line segment vs bbox intersection, and
  canvas edge clipping on the current whiteboard state. Renders a text
  block for inclusion in the system prompt.
- lib/orchestration/summarizers/state-context.ts: wires the conflict
  block in after the whiteboard element listing.
- Role templates: replace image-reading guidance with concise
  "Layout conflicts" sections pointing at the computed list, with a
  strong anti-action anchor so agents don't self-trigger wb_clear when
  the list is empty.

## Eval instrumentation (orthogonal)

- EVAL_ENABLE_THINKING=1 opt-in to enable model thinking per-request.
  app/api/chat/route.ts reads body.thinking; runner.ts forwards it.
  Default chat path stays on enabled:false for latency.
- Per-turn wall-clock timing: eval/whiteboard-layout/{runner,reporter,
  types}.ts capture and report mean/p50/p95/total turn latency.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* refactor(whiteboard): address code-review feedback

W1: drop stale "prior-state image" reference from conflict-block prose
    (lib/orchestration/summarizers/whiteboard-conflicts.ts) — the image
    feature was removed; the text now says "real visible problem on the
    current board".

W3: type `thinking` on StatelessChatRequest instead of reading it through
    a cast. `app/api/chat/route.ts` now accesses `body.thinking` directly;
    frontend callers can discover the field via TS completion.

W4: unify canvas height constant to 563 (matching the actual rendered
    pixel count from capture.ts). The geometry detector's
    CANVAS_HEIGHT, the snippet's Dimensions / coordinate system /
    layout-guide text, and examples all now agree.

N6: add tests/orchestration/whiteboard-conflicts.test.ts — 17 cases
    covering empty input, bbox overlap threshold (30%, 50%, 100%, plus
    10% sub-threshold), line-crosses-bbox (through, endpoint-inside,
    path-above), canvas clipping on all 4 edges, exact-edge placement
    (not reported), malformed elements (skipped not crashed), and
    output format.

All 43 tests pass; tsc --noEmit clean.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* refactor(eval): finish canvas-height 563 unification

Second-pass code review caught one residual 562.5 in app/eval/whiteboard/page.tsx
that the first cleanup (commit 7a006bb) missed. The 0.5px disagreement was
harmless in practice (Playwright captures rounded to 563), but inconsistent
with the geometry detector and the prompt snippet now agreeing on 563.

All 43 tests pass; tsc clean.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: prettier format whiteboard-conflicts.test + eval/runner

CI's `pnpm check` (prettier --check) caught two unformatted files:
- eval/whiteboard-layout/runner.ts
- tests/orchestration/whiteboard-conflicts.test.ts

Auto-fixed via `pnpm prettier --write`.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: 杨慎 <117187635+cosarah@users.noreply.github.com>
2026-04-25 15:18:41 +08:00
wyuc
550c43a3f3
fix(generation): unify languageDirective across outline + scene pipeline (#472) (#474)
* fix(generation): unify languageDirective across outline + scene pipeline (#472)

Root issue: languageDirective was dropped, renamed, or hardcoded at several
points in the scene-generation pipeline, silently degrading prompt-level
language control. Slide paths survived because their fallback happened to
hint requirement-language; widget paths degraded to zh-CN default.

Fix plan (all code-only threading + prompt hygiene, no schema changes):

1. Thread languageDirective through every buildPrompt in scene-generator.ts:
   - Add param to generateSlideContent / generateQuizContent / generatePBLSceneContent
   - Forward from generateSceneContent's slide / quiz / pbl branches
   - Include key in the four generateSceneActions buildPrompt calls
   - Demote generatePBLSceneContent's hardcoded English to a fallback
   - Drop the dishonest `as 'zh-CN' | 'en-US'` cast on the widget path

2. Unify variable naming across widget templates + callers:
   - Rename {{language}} → {{languageDirective}} in 6 widget templates
     (simulation / diagram / code / game / visualization3d / widget-teacher-actions)
   - generateWidgetContent and generateWidgetTeacherActions now pass
     `languageDirective: languageDirective || ''` instead of a locale-code shim

3. Make the outline LLM reliably emit the wrapper object:
   - requirements-to-outlines/system.md + user.md restructured so the
     "top-level JSON object with languageDirective + outlines" contract is
     surfaced up-front, short, and unambiguous — drowning-by-scene-examples
     removed. Important Reminders reordered: top-level shape first.
   - interactive-outlines/system.md + user.md aligned with main outliner:
     adds full Language Inference section, requires wrapper output, drops
     the orphan {{language}} placeholder that never had a value source.

4. Remove lib/prompts/loader.ts prompt/snippet caches:
   - Disk reads for prompt templates are not on any hot path (LLM call
     dominates by 5 orders of magnitude). The cache's only observable
     effect was blocking prompt edits from taking effect without restart
     — which masked the wrapper bug during this investigation.

Verification:
- 7 new regression tests in tests/generation cover directive threading at
  each buildPrompt site plus the PBL caller-forwarding guarantee.
- outline-language eval (50 scenarios, gemini-3-flash-preview inference,
  qwen-3.5-flash judge): 48/50 (96%). The 2 persistent failures are in
  the proxy-request category (teacher / tutor preparing lessons for
  students) where the system prompt's rule 5 has genuine ambiguity —
  orthogonal to this fix.
- Curl burst tests: 8/8 runs each for regular-mode and interactive-mode
  outline endpoints emit the wrapper object and extract a detailed
  inferred directive.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* style: apply prettier formatting to loader.ts and new test file

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix: thread languageDirective in scene-builder and classroom-generation

Code review caught two additional sites missing the directive:
- lib/server/classroom-generation.ts:371 — generateSceneActions call
  was missing languageDirective, reproducing the issue #472 symptom
  in the shareable-classroom server generation path.
- lib/generation/scene-builder.ts:114 — buildSceneFromOutline's
  generateSceneActions call had the same miss; latent (no current
  live caller) but wrong for consistency.

Also renumber duplicate `8.` in requirements-to-outlines/system.md
scene-level rules.

Extend regression tests with a buildSceneFromOutline end-to-end case
that captures both the content and actions prompts via a stub aiCall
and asserts the directive reaches both phases — this would have
caught the scene-builder miss.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* review: widget-path test + docs + fallback constant (PR #474)

Address @cosarah's review feedback:

- Add widget-path regression test (tests/generation/...): interactive
  scene with widgetType=simulation captures both widget content and
  widget-teacher-actions prompts, asserts the directive reaches each
  and no `{{language}}` / `{{languageDirective}}` placeholder leaks.
  This is exactly the path issue #472 was filed for.

- Rewrite lib/prompts/README.md "Caching" section: the cache was
  removed in this PR; README still instructed callers to use a
  clearPromptCache() function that no longer exists.

- Sync interactive-outlines/user.md with the main outliner's
  "## Language Context" reminder block (line 13-19) so both outline
  paths give the LLM the same language-inference reminders.

- Hoist 'Teach in the language that matches the user requirement.'
  into DEFAULT_LANGUAGE_DIRECTIVE, exported from outline-generator.
  Replaces 4 copies across outline-generator, scene-generator, and
  the scene-outlines-stream route.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-23 23:00:06 +08:00
wyuc
f40c92f1aa
refactor(orchestration): migrate prompt builders to file-based templates (#459)
* refactor(prompts): move loader to lib/prompts/

Move file-based prompt loader from lib/generation/prompts/ to
project-level lib/prompts/ so it can be shared by orchestration
and PBL prompts in subsequent commits.

- Templates and snippets moved alongside the loader
- getPromptsDir() now points at lib/prompts/
- Generation pipeline imports updated to @/lib/prompts
  (outline-generator, scene-generator, search-query-builder,
   scene-outlines-stream route)
- Add tests/prompts/loader.test.ts as sanity gate

Pure file move — no behavior change.

* test(orchestration): add baseline snapshots for prompt builders

Snapshot tests cover variant matrix:
- buildStructuredPrompt: role × scene-type × peer/ledger/discussion/profile
- convertMessagesToOpenAI: mixed message kinds
- summarizeConversation: truncation
- buildDirectorPrompt: Q&A vs discussion, ledger, profile
- buildPBLSystemPrompt: default config

These lock current output so the body refactor in subsequent
commits can be verified byte-equal.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test(orchestration): plug snapshot coverage gaps from review

- Split convertMessagesToOpenAI test: same-agent (existing) +
  cross-agent (new). The original test passed currentAgentId
  matching the message's agentId, so the cross-agent role-conversion
  branch was never exercised.

- Add 'teacher / quiz scene' snapshot to lock the spotlight/laser
  strip path in getEffectiveActions. The previous variant-7 test
  (whiteboard-open) only triggered the mutual-exclusion warning,
  not the strip — renamed it to reflect what it actually tests.

- Add assistant-role variant (was uncovered: ROLE_GUIDELINES,
  buildLengthGuidelines, buildWhiteboardGuidelines all branch on
  role).

* refactor(orchestration): extract summarizers from prompt-builder.ts

Move state-context, virtual whiteboard ledger replay, peer context,
message converter, and conversation summary out of the 890-line
prompt-builder.ts into focused modules under lib/orchestration/summarizers/.

prompt-builder.ts now only owns prompt assembly. director-graph
imports updated to the new locations.

Snapshot tests pass byte-equal — no behavior change.

* refactor(orchestration): move agent-system prompt to template file

The buildStructuredPrompt template literal is now
lib/prompts/templates/agent-system/system.md, assembled by a
thin variable-pass through the shared prompt loader.

Per-variant ternaries (format example, ordering, spotlight
examples, mutual-exclusion note) are kept as module-level
constants in prompt-builder.ts. ROLE_GUIDELINES,
buildLengthGuidelines, and buildWhiteboardGuidelines stay too
(they may further migrate to template partials in Phase 2).

Also: PROMPT_IDS gains a 'satisfies Record<string, PromptId>'
clause to prevent constant/union drift as more IDs are added.

Snapshot tests (12 prompt-builder + 4 director + 1 pbl) pass
byte-equal.

* refactor(prompts): align agent-system template with project conventions

- Rename agent-system placeholders snake_case → camelCase to match
  the convention already used by slide-actions/user.md and other
  generation templates. Settles convention before Task 5 lands two
  more templates that would otherwise inherit drift.

- Extract '## Speech Guidelines (CRITICAL)' into
  lib/prompts/snippets/speech-guidelines.md for reuse by director
  and PBL prompts in Task 5.

Snapshot tests pass byte-equal — placeholder name changes are
invisible in rendered output, and snippet inclusion happens at
load time.

* refactor(orchestration,pbl): move director + PBL prompts to templates

director-prompt.ts and pbl-system-prompt.ts now use the shared
template loader. Bodies collapse to thin variable assembly.

Three orchestration-tier prompts now share one infrastructure:
agent-system, director, pbl-design.

Snapshot tests pass byte-equal.

* refactor(orchestration): extract WhiteboardActionRecord + AgentTurnSummary to types module

These two interfaces are imported by 6+ modules including
summarizers/ — having them live in director-prompt.ts created
an awkward upward import direction (summarizers reaching back
to a sibling prompt builder for types).

Move them to lib/orchestration/types.ts and update all callers.
director-prompt.ts now imports them too.

Pure type-location refactor — snapshots pass byte-equal.

* test: remove snapshot tests in favor of eval-as-integration-test

Per review feedback: byte-equal snapshots were the wrong invariant
for this refactor. The goal was a stable substrate for editing
prompts, not a frozen contract. Snapshots would have generated
maintenance churn (~100-200 line diffs per intentional Phase 2
prompt tweak) without providing value the eval doesn't already.

Test posture going forward:
- tests/prompts/loader.test.ts (3 tests) — bounds the loader
  infrastructure (template load, snippet inclusion, variable
  interpolation, missing-id behavior)
- pnpm eval:whiteboard — bounds end-to-end agent loop, template
  composition, and integration with chat/director/state-manager

Removed: 1879 lines of .snap + 320 lines of test scaffolding +
fixtures. Net PR diff drops by ~2200 lines.

* docs(prompts): add README + structural assertion tests (review feedback)

Addresses two items flagged by PR #459 final review:

1. lib/prompts/README.md — conventions, syntax, gotchas, and local-testing
   recipe for template authors. Previously there was no doc for the stated
   goal of "non-engineers can edit prompts."

2. tests/prompts/templates.test.ts — 8 structural assertions covering:
   - no surviving {{...}} placeholders in any rendered template
   - role dispatch (teacher → LEAD TEACHER, student → not)
   - scene-type action stripping (quiz scene has no spotlight/laser)
   - director prompt output spec mentions next_agent

   These replace the removed byte-equal snapshot suite at much lower
   maintenance cost — they assert behaviors the refactor must preserve,
   not exact bytes.

* chore(prompts): relocate templates added on main during rebase

PR #461 (interactive mode clean) added 7 new templates under
lib/generation/prompts/templates/ (the pre-refactor location).
Rebase onto origin/main landed them at the old path; git's rename
detection didn't forward them through the directory move in db56c40.

Manually move them to lib/prompts/templates/ to match the new
convention, and fix scene-generator.ts's relative import
('./prompts/types' → '@/lib/prompts/types') since the dir no
longer exists as a sibling.

No behavior change — templates read from PROMPT_IDS values via
getPromptsDir() which already points at lib/prompts/.

* refactor(prompts): address review feedback from @cosarah

- loadSnippet now throws on missing file instead of silently returning
  a literal {{snippet:id}} string. A typo like {{snippet:speach-guidelines}}
  now fails at load time instead of reaching the LLM.

- README gains a "Still in TypeScript" section listing the role-conditional
  content that still lives in prompt-builder.ts (ROLE_GUIDELINES,
  buildLengthGuidelines, buildWhiteboardGuidelines) so contributors
  expecting a pure-markdown workflow know where to look.

- Expand tests/prompts/templates.test.ts to cover the conditional branches
  Phase 2 is most likely to touch (9 new assertions):
  - assistant role dispatch
  - peer-context section toggles on agentResponses presence
  - language constraint toggles on stage.languageDirective presence
  - director Q&A vs discussion mode branching
  - pbl-design {{issueCount}} substituted at all 3 occurrences
  - placeholder-naming-convention lint scans every template for
    non-camelCase placeholders (slide-content grandfathered)

- Comment above interpolateVariables regex documents why kebab-case
  placeholders pass through silently (the lint test now catches them).

- New test in loader.test.ts locks the throw-on-missing-snippet behavior.

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-20 13:41:17 +08:00
Shangqing Tu
c02a607377
feat: interactive mode clean (#461)
* feat: add interactive mode

* feat: add TeacherActions for interactive mode

* fix: better prompt for ultra mode

* feat: upgrade normal mode's interactive generation with 5 widget type and actions

* feat: make interactive mode button clear

* fix: remove unused TeacherOverlay

* fix: resolve PR #458 review feedback

- Revert unrelated infra changes (Dockerfile, docker-compose.yml)
- Fix placeholder strings in generateWidgetContent
- Rename ultraMode to interactiveMode consistently across codebase
- Extract duplicated patchHtmlForIframe to shared utility
- Fix widget store race condition by keying callbacks by sceneId
- Fix teacher-action ID collisions by using descriptive IDs in prompt
- Relax outline prompt constraints for flexibility
- Optimize sidebar thumbnail with IntersectionObserver lazy loading
- Add trailing newlines to modified files

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* fix: update generateSceneActions call signatures

The function signature changed to individual parameters instead of
options object pattern after cherry-pick.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* style: fix prettier formatting

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* fix: removed extra language arg

* style: fix prettier formatting v2

* fix:  add missing i18n keys

---------

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
2026-04-19 21:35:30 +08:00
wyuc
91c4015732
feat(pdf): add MinerU Cloud API as PDF parsing provider (#438)
* feat(pdf): add MinerU Cloud API as PDF parsing provider

Add MinerU Cloud (v4 API) as a new PDF provider alongside unpdf (built-in)
and MinerU (self-hosted). Users can now parse PDFs via the cloud API without
deploying a self-hosted MinerU instance.

- New provider `mineru-cloud` with API key auth and optional base URL
- Cloud flow: batch create → presigned upload → poll → ZIP download → parse
- Extract shared `mineru-parser.ts` from inline code (used by both paths)
- Settings UI adapted for cloud (API key required) vs self-hosted (base URL required)
- Server-side env var support: PDF_MINERU_CLOUD_API_KEY / PDF_MINERU_CLOUD_BASE_URL
- SSRF protection on cloud verification endpoint
- i18n translations for en-US, zh-CN, ja-JP, ru-RU

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(provider-config): revert PDF activation to requiresBaseUrl

Reverts the PDF section from keylessProviders back to requiresBaseUrl: true
to fix failing test: mineru with only apiKey (no baseUrl) should not activate.
mineru-cloud API key can be configured via browser settings UI instead.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(pdf-settings): enable test button when API key is server-configured

The test connection button was disabled when the API key was only
configured server-side (not entered by user in browser). Now checks
isServerConfigured in addition to user-entered values.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-16 15:15:55 +08:00
杨慎
470aa5e42e
feat: inline language inference for outline and PBL generation (#412)
* feat: inline language inference in outline generation

Replace manual language selection with automatic inference from user
requirement text. The outline generator now produces a languageDirective
that propagates through the entire generation pipeline.

Key changes:
- Rewrite Language Inference section in outline prompt with decision
  rules for foreign language learning, cross-language PDF, proxy
  requests, and terminology handling
- Reorder pipeline: outlines before agents, so agent profiles can
  use the inferred languageDirective
- Pass languageDirective through scene content/actions generation
- Add SSE streaming of languageDirective from outline generation
- Remove manual language selection UI

Eval test suite:
- 50 test cases covering 9 scenario types: single-language, language
  learning, immersive, explicit instruction, code-switching, minimal
  input, user profiles, cross-language PDF, locale mismatch
- LLM-as-judge evaluation with configurable inference/judge models
- 50/50 pass rate with gemini-3-flash-preview + gpt-4o judge
- Excluded from CI (requires LLM API keys)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: remove useless attributes in test case

* feat: pass languageDirective to PBL, remove hardcoded zh-CN/en-US

- Remove pblConfig.language field, use languageDirective from outline
  inference instead
- Delete all Chinese prompt duplicates in pbl-system-prompt.ts,
  agent-templates.ts; keep English templates with languageDirective
  injection
- Remove zh-CN/en-US branches in generate-pbl.ts (initial prompt,
  post-process context, welcome message)
- Pipe languageDirective through scene-generator → generatePBLContent
  → IssueboardMCP → agent templates
- Remove i18n template wrapping from PBL welcome messages in
  pbl-renderer.tsx and use-pbl-chat.ts; use LLM-generated content
  directly to avoid language mismatch when UI locale ≠ course language
- Update pblConfig schema in outline prompt (remove language field)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor: clean up legacy language fields, pass languageDirective through buildSceneFromOutline

- Add languageDirective param to buildSceneFromOutline, combining with
  outline.languageNote via buildLanguageText
- Remove dead types: AudienceProfile, StylePreferences, LegacyUserRequirements,
  SceneOutline.language
- Remove Stage.language and all its propagation (storage, stageInfo, prompt-builder fallback)
- Remove GenerateClassroomInput.language and job store inputSummary.language
- Remove unused pdfLanguageSample from outline SSE route

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: persist languageDirective to IndexedDB, fix TTS preview and dead refs

- Add languageDirective to StageRecord and stage-storage write path
- Add DB v9 migration: convert legacy language locale codes to directives
- Use voice.language for TTS preview text instead of dead localStorage key
- Omit empty ## Language section in PBL agent prompts
- Use JSON.parse for extractLanguageDirective unescape (\uXXXX support)
- Remove dead i18n keys: toolbar.languageHint, pbl.chat.welcomeMessage

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-13 21:49:56 +08:00
wyuc
c071e02d83
feat: ACCESS_CODE site-level authentication (#407) (#411)
* feat(access-code): add status API endpoint

Returns whether ACCESS_CODE is enabled and whether the current user is
authenticated via cookie, to support the frontend access gate.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(access-code): add verify API endpoint

Creates POST /api/access-code/verify that validates ACCESS_CODE env var
and sets an HttpOnly 7-day cookie on success.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(access-code): add Next.js middleware to gate API routes

Intercepts all requests when ACCESS_CODE env var is set. API routes
return 401 without the openmaic_access cookie; page requests pass
through so the frontend can render the access-code modal.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(i18n): add accessCode translations for all 4 locales

Add accessCode top-level key to en-US, zh-CN, ja-JP, and ru-RU locale
files with title, placeholder, submit, and error strings.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* docs: add ACCESS_CODE documentation to .env.example

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat: add AccessCodeGuard component and integrate into root layout

Wraps page children with an access-code gate that checks /api/access-code/status on mount and renders AccessCodeModal when authentication is required.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(access-code): add AccessCodeModal component

Adds the modal dialog component that prompts users for an access code,
using existing Dialog/Button/Input UI components and i18n translation keys.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix(access-code): fix lint error and format files

- Fix useEffect setState pattern in access-code-guard.tsx
- Format middleware.ts and layout.tsx with Prettier

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* style(access-code): redesign modal as full-screen gate

Replace generic Radix Dialog with a custom full-screen gate:
- Mesh gradient background with noise texture
- Frosted glass card with backdrop-blur
- Staggered motion animations on mount
- Inline submit button inside input field
- Success state animation before dismissal
- Proper dark mode support

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(access-code): address code review findings

Critical:
- Middleware now validates HMAC-signed cookie tokens, not just existence
- Verify endpoint uses timingSafeEqual for constant-time comparison
- Cookie value is now `timestamp.HMAC(ACCESS_CODE, timestamp)` instead of UUID

Important:
- Middleware 401 response includes `errorCode` matching apiError shape
- Status endpoint uses apiSuccess wrapper for consistency
- Remove unused `accessCode.submit` i18n key from all 4 locales

Suggestions:
- Guard renders children during loading (overlay on top, not blocking)
- Network error defaults to enabled=true (safer than silently disabling)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(access-code): use Web Crypto API in middleware for Edge Runtime

Node.js crypto module is not available in Next.js Edge Runtime.
Replace createHmac/timingSafeEqual with crypto.subtle HMAC and
manual constant-length XOR comparison.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: 杨慎 <117187635+cosarah@users.noreply.github.com>
2026-04-12 22:14:14 +08:00
Yizuki_Ame
96a4448feb
fix: resolve DNS before SSRF validation to prevent rebinding bypass (#386)
- Make validateUrlForSSRF async; resolve hostnames via dns.promises.lookup
  with { all: true, verbatim: true } and reject if any address is private
- Add isPrivateIP helper covering IPv4 private ranges, IPv6 loopback/ULA/
  link-local, IPv4-mapped IPv6, deprecated fec0::/10 site-local, 6to4
  tunnel (2002::/16), and Teredo tunnel (2001:0000::/32)
- Detect IP literals via net.isIP() and validate directly without DNS
- Fail closed on DNS resolution errors
- Propagate async to resolveModel, resolveModelFromHeaders, and all 20+
  route-level callers; preserve existing production-only gating
- Add 14 unit tests covering public pass-through, private literals, DNS
  rebinding, mixed DNS answers, tunnel addresses, and DNS failure

Closes #378
2026-04-11 15:51:30 +08:00
f1re
2c26e3a461
feat: Ollama local LLM support (#94)
* feat: Ollama local LLM support

- Ollama as a built-in provider (OpenAI-compatible, no API key needed)
- 8 default models: llama3.3, llama3.2, qwen2.5, qwen2.5:32b, mistral, gemma3, deepseek-r1, phi4
- Keyless provider activation: providers with only a baseUrl (no API key) now activate correctly
- isProviderKeyRequired() helper for consistent key validation across routes
- i18n strings for Ollama (zh-CN + en-US) and missing Doubao strings
- SSRF guard documentation clarifying server-configured URLs bypass safely

Previously, clients could send `x-requires-api-key: false` (header) or
`requiresApiKey: false` (body) to skip API key validation for ANY provider,
including ones like OpenAI that require keys. This meant a client could
consume server-configured credentials without authorization.

Fix: the server now derives requiresApiKey exclusively from its own provider
registry. The client header and body field are removed from all server-side
parsing. For Ollama, the registry says `requiresApiKey: false` so it works
keyless. For OpenAI, the registry says `true` so the check is enforced
regardless of what a client sends.

* fix: address reviewer feedback on Ollama integration

- Fix env-var activation so OLLAMA_BASE_URL alone activates the provider
- Move SSRF bypass comment from ssrf-guard.ts to resolve-model.ts
- Add ollama and doubao provider names to i18n locale files

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* Fixed issues from reviewer notes.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* style: format provider-config.ts with Prettier

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: 杨慎 <117187635+cosarah@users.noreply.github.com>
2026-04-09 21:07:35 +08:00
kaiyuan Zhang
cce7087f67
Fix action filtering logic and add safety improvements (#163)
* fix: fix 3 bugs found during code review

1. formatQuestionsForPrompt called .join() on QuizOption objects,
   producing "[object Object]" in AI prompts instead of readable
   option text (e.g. "A. Option1, B. Option2").

2. json-repair Fix 1 regex double-escaped valid JSON escapes (\t,
   \n, \r, \b, \f) and couldn't handle strings with escaped quotes.
   Now uses a proper string-aware regex and preserves valid escapes.

3. PlaybackEngine spotlight/laser actions used synchronous recursion
   via processNext(), risking stack overflow with many consecutive
   non-speech actions. Now uses queueMicrotask() to break recursion.

https://claude.ai/code/session_01JdigqQtiAvomeifvWSQbjm

* fix: ensure allowedActions whitelist applies to non-slide scenes

The early return in Step 6 (slide-only action filter) caused Step 7
(allowedActions whitelist) to be skipped for non-slide scenes. This
meant hallucinated actions from agents in quiz/interactive/pbl scenes
were not filtered by the role-based allowedActions whitelist.

Refactored to use a mutable result variable instead of early returns
so both filters always apply.

https://claude.ai/code/session_01JdigqQtiAvomeifvWSQbjm

* fix: prevent video playback hang and division by zero in CJK detection

1. executePlayVideo could hang forever if the video element was invalid
   or the state change was missed between playVideo() and subscribe().
   Added a 5-minute safety timeout to prevent indefinite blocking.

2. CJK language detection in browser TTS divided by chunkText.length
   without checking for empty strings, producing NaN. Now guards
   against zero-length text.

https://claude.ai/code/session_01JdigqQtiAvomeifvWSQbjm

* fix: prevent ordered entry with invalid index when partial text has no remaining content

When a previously-partial text item completed but all content had
already been streamed as deltas (remaining is empty), the code still
pushed an ordered entry pointing to textChunks.length - 1, which
could be -1 or reference an unrelated chunk. This caused spurious
warnings in director-graph and potential text loss.

Now only pushes the ordered entry when there is actual remaining
content to emit.

https://claude.ai/code/session_01JdigqQtiAvomeifvWSQbjm

* fix: validate quiz points parameter and fix parse-pdf metadata spread order

1. quiz-grade: `points` from request body was used without validation,
   causing NaN in score calculation and invalid JSON responses when
   points was undefined, negative, or non-numeric. Now validates it
   is a positive finite number.

2. parse-pdf: metadata spread order put the default `pageCount` before
   `...result.metadata`, so the spread would overwrite the fallback.
   Fixed by spreading metadata first, then applying defaults after.
   Also changed `||` to `??` so pageCount=0 is preserved correctly.

https://claude.ai/code/session_01JdigqQtiAvomeifvWSQbjm

* fix: crash in moveUpElement, dead-code in video options, wrong parens in canCombine

1. use-order-element.ts: moveUpElement crashed with TypeError when a
   grouped element was already at the top of the z-order. The code
   accessed copyOfElementList[maxLevel + 1] without bounds checking,
   then dereferenced .groupId on undefined. Added early return guard
   matching the pattern used in the non-grouped branch.

2. video-providers.ts: normalizeVideoOptions had a dead-code ternary
   inside an if-block that already proved the condition was false.
   Simplified to directly use the fallback value.

3. use-canvas-operations.ts: canCombine check had incorrect
   parenthesization: (el.groupId && el.groupId) === firstGroupId
   evaluated the && first, which is equivalent to just el.groupId.
   Fixed to: el.groupId && el.groupId === firstGroupId.

https://claude.ai/code/session_01JdigqQtiAvomeifvWSQbjm

* style: fix prettier formatting in 3 files

https://claude.ai/code/session_01JdigqQtiAvomeifvWSQbjm

* fix: use valid ApiErrorCode in quiz-grade route

INVALID_PARAMETER is not a member of API_ERROR_CODES. Use
INVALID_REQUEST instead, which is the appropriate code for
invalid request parameters.

https://claude.ai/code/session_01JdigqQtiAvomeifvWSQbjm

---------

Co-authored-by: Claude <noreply@anthropic.com>
2026-04-04 12:46:27 +08:00
Yizuki_Ame
95b5c2bf55
fix: persist agent configs in server-generated classrooms (#336)
* fix: persist agent configs in server-generated classrooms (#316)

Server-generated classrooms via /api/generate-classroom silently skip all discussion actions because agent configurations are never embedded in the persisted Stage object.

Changes:

- Add optional generatedAgentConfigs field to Stage interface

- Inject agent configs (with avatar/color/priority) into Stage during server-side generation

- Hydrate agents into IndexedDB/registry when loading from server storage on client

Closes #316

* fix: extract shared agent constants and fix avatar paths

- Extract AGENT_COLOR_PALETTE and AGENT_DEFAULT_AVATARS into
  lib/constants/agent-defaults.ts to eliminate duplication
- Fix invalid avatar paths (student.png -> assist.png, etc.)
  to match actual files in public/avatars/
- Remove duplicated inline constants from classroom-generation.ts
  and agent-profiles/route.ts

Addresses reviewer feedback on #336

---------
2026-04-02 16:23:16 +08:00
Mohit Neerukonda
531b3c101f
feat: make Tavily web search query context-aware when PDF is uploaded (#258)
* fix(web-search): rewrite search query for pdf and long requirements

* fix(web-search): address query rewrite review feedback
2026-04-02 15:01:53 +08:00
Yizuki_Ame
25f7908ffb
fix: add structured request context to all API error logs (#337)
* fix: add structured request context to all API error logs (#323)

Replace generic log.error messages across 23 API routes with structured, context-rich error logs that include provider, model, input summary, and other request parameters for faster incident triage.

- Hoist key request params above try blocks for catch-block access

- Add createLogger imports to routes that lacked logging

- Truncate user-controlled strings (query, requirement) to prevent log flooding

- No behavioral changes — purely observability improvement

Closes #323

* style: run prettier on all API routes

* chore: remove accidental server.log from tracking
2026-04-01 15:37:46 +08:00
wyuc
3c687dd523
fix(tts): unify model selection to per-provider and fix ElevenLabs model_id (#326)
* fix(tts): unify model selection to per-provider and fix ElevenLabs model_id (#324)

- Move model selection from global ttsModelId to per-provider
  ttsProvidersConfig[providerId].modelId
- Remove supportsModelSelection flag, use models.length > 0 instead
- Add defaultModelId to TTSProviderConfig and ASRProviderConfig
- Add providerOptions field to TTSModelConfig for future extensibility
- Fix ElevenLabs hardcoded model_id: 'eleven_multilingual_v2'
- Fix MiniMax TTS using config.model instead of config.modelId
- Update model lists from provider docs:
  - Qwen: add qwen3-tts-instruct-flash, qwen-tts
  - ElevenLabs: add eleven_flash_v2_5, eleven_flash_v2
  - MiniMax: remove non-existent speech-2.8 series
- Replace custom model CRUD UI with simple Select dropdown
- Remove MiniMax-specific hardcoded model selector from audio-settings
- Add migration for old ttsModelId/asrModelId/model fields

* feat(tts): voice picker groups by provider:model, sets both model and voice

Voice selection in agent bar now groups voices by model. Picking a
voice from a model group sets both modelId and voiceId on the agent.
TTS settings shows available models as display-only chips.

- Add compatibleModels field to TTSVoiceInfo (OpenAI marin/cedar restricted to gpt-4o-mini-tts)
- Add modelId to agent voiceConfig and ResolvedVoice
- Add ModelVoiceGroup to ProviderWithVoices, build groups in getAvailableProvidersWithVoices
- Update AgentVoicePill and TeacherVoicePill to iterate modelGroups
- Thread modelId from voice selection through discussion TTS pipeline
- Replace model Select with display-only chips in tts-settings

* fix(tts): show provider name in voice picker group headers

* fix(tts): restore MiniMax speech-01 models per official API docs

* fix(tts): add MiniMax speech-2.8 models per official docs, default to speech-2.8-hd

* feat(tts): expand MiniMax voice list with recommended voices

* fix(tts): remove non-official MiniMax recommended voices, keep 10 from official list

* fix: address CR findings - align defaults, fix test mocks, ASR modelId fallback

* fix(tts): pass modelId in voice preview and classroom generation

* fix(tts): voice picker highlights only the exact model:voice match

---------

Co-authored-by: 杨慎 <117187635+cosarah@users.noreply.github.com>
2026-03-30 17:21:19 +08:00
wyuc
9badd59856 feat: add and expand MiniMax provider support (#182)
Add MiniMax LLM models (M2–M2.7), TTS provider (speech-2.8/2.6/02/01),
image generation (image-01), and video generation (Hailuo 2.3/02,
T2V-01). Unify base URLs to api.minimaxi.com and add MiniMax-specific
base URL normalization for the Anthropic-compatible endpoint.

Co-authored-by: Hi-Jiajun <3138947285@qq.com>
2026-03-30 12:41:43 +08:00
wyuc
5adf91c6f3 feat(settings): add configurable model selection for TTS and ASR (#108)
Add ttsModelId/asrModelId to persisted settings, model management UI
for providers that support model selection, and propagate selected
model through preview, generation, and transcription flows.

Co-authored-by: 刘少杰 <liushaojie@cvte.com>
2026-03-30 11:29:54 +08:00
wyuc
ddb52241fb
feat: add Discussion TTS with per-agent voice assignment (#211)
* feat(tts): add resolveVoice() and getServerVoiceList() utilities

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(tts): add AudioIndicator equalizer bars component

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(tts): add onSegmentSealed callback to StreamBuffer

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(tts): add voiceOverrides field to AgentConfig and AgentTemplate

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(tts): add useDiscussionTTS hook with audio queue and cleanup

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(tts): add audio state indicator to Roundtable bubble

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(tts): wire onSegmentSealed callback through chat sessions

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(tts): add per-agent voice dropdown to AgentBar

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(tts): integrate useDiscussionTTS in Stage and pass state to Roundtable

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* style(tts): refine voice dropdown to pill-style selector

Replace native select styling with a compact rounded-full pill
that blends into the agent row. Remove border, use muted bg,
smaller text, and a custom chevron icon.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* style(tts): use shadcn Select for voice dropdown, link with TTS toggle

- Replace native <select> with shadcn Select component for consistent UI
- Hide voice dropdown when TTS is muted (ttsMuted)
- Compact pill-style trigger with rounded-full, no border, muted bg

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* style(tts): add voice label prefix and always show dropdown

Show "音色: Alloy" instead of plain "Alloy" in the voice pill.
Always show dropdown regardless of mute state (voice config is
independent of playback).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* style(tts): add volume icon hint in collapsed AgentBar

Show a small Volume2 icon in the collapsed pill when voice config
is available, hinting that voice settings are inside.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(tts): fix voice dropdown layout and click handling

- Move voice pill below agent name (second line) to prevent
  horizontal overflow in English
- Wrap Select in div with onPointerDown stopPropagation to fix
  Radix click-through to parent row
- Add line-clamp-1 to descriptions for consistent row height
- Use items-start instead of items-center for better multi-line alignment

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor(tts): redesign AgentBar voice layout for compactness

- Single-line layout: checkbox · avatar · name · role · voice pill
- Remove descriptions from agent rows (saves vertical space)
- Extract AgentVoicePill component to isolate Select event handling
- Smaller avatars (size-7), tighter row padding (py-1.5)
- Voice pill uses Volume2 icon + voice name (no prefix text)
- Works in both Chinese and English without overflow

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(tts): cross-provider voice selection per agent

- Change voiceConfig from per-provider lookup to explicit
  { providerId, voiceId } per agent
- Each agent can use a different TTS provider's voice
- Voice picker dropdown groups voices by provider
- useDiscussionTTS routes TTS requests per agent's provider
- resolveAgentVoice falls back to global provider if no config

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(tts): align role badge and voice pill across agent rows

Give role badge fixed width (w-14 text-right) so role text
and voice pills align vertically across all rows regardless
of agent name length.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(tts): fix role badge and voice pill alignment

Wrap role badge + voice pill in a fixed-width container
(w-[9.5rem] justify-end) so both align vertically across
all agent rows regardless of name or role text length.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* style(tts): align role badge and voice pill across agent rows

Add min-w-[52px] text-right to role badge so it starts at a
consistent position regardless of agent name length.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(tts): use fixed w-[60px] for role badge alignment

* fix(tts): use fixed w-[88px] for voice pill alignment

* fix(tts): prevent click-outside from closing AgentBar when Select portal is open

* fix(tts): comprehensive voice picker rewrite

- Replace Radix Select with Popover + button list (fixes click issue)
- Fix getAvailableProvidersWithVoices to always include global provider
- Widen panel from w-80 to w-96 (prevents name truncation)
- Voice pill uses primary color instead of gray (more visible)
- Extract renderAgentRow helper to reduce duplication
- Popover shows voices grouped by provider with active state
- Add findVoiceDisplayName utility

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(tts): align voice provider availability with toolbar logic

* fix(tts): fallback to first available provider when global provider has no voices

* refactor(tts): remove global provider fallback from voice resolution

Voice resolution now only depends on available providers (those with
API keys or server-configured). No more globalProviderId parameter.
Fallback is first available provider, then browser-native-tts.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(tts): add browser native TTS voices to agent voice picker

Load speechSynthesis.getVoices() in AgentBar and include as a
"Browser Native" provider group in the voice popover. No API key
needed - always available if browser supports it.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(tts): simplify toolbar TTS to on/off toggle, add disabled state

Toolbar:
- Replace volume slider with simple TTS on/off toggle button
- Remove ttsMuted/ttsVolume/onVolumeChange props from CanvasToolbar
- Toggle now controls ttsEnabled (not ttsMuted)

AgentBar:
- Collapsed: show VolumeX icon when TTS disabled
- Voice pills show disabled state (gray, cursor-not-allowed, no popover)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor(tts): simplify Settings TTS tab to toggle + provider config

Remove voice selection, speed slider, preview/test, Azure locale
filter from Settings TTS tab. Voice is now per-agent in AgentBar.
Keep: on/off toggle, provider selector, API key + base URL config.
Add hint text pointing to AgentBar for voice configuration.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor(tts): simplify media popover TTS tab to toggle only

* fix(tts): add voice config hint to media popover TTS tab

* feat(tts): add per-voice preview button in voice picker

Each voice row in the popover has a small speaker icon button.
Click to preview the voice with "欢迎来到AI课堂" / "Welcome to
AI Classroom" (follows i18n). Browser native uses Web Speech API,
server TTS calls /api/generate/tts. Click again or close popover
to stop. Shows spinner while generating.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(tts): preview text follows course language instead of UI language

* refactor(tts): redesign AgentBar expanded panel layout

- Teacher always at top with voice pill (works in both modes)
- Mode tabs moved below teacher
- Auto mode: single compact row with shuffle icon + description
- Max turns: compact inline row with smaller input
- Preset mode: only student agents listed (teacher already above)
- Remove large shuffle animation from auto mode

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor(tts): merge max turns into teacher row

* refactor(tts): separate teacher row and max turns, use stepper UI

- Teacher row: avatar + name + voice pill only
- Max turns: bottom row with MessageSquare icon + compact stepper
  (minus/number/plus in a rounded pill)
- Remove Input component dependency

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(tts): increase voice pill contrast in dark mode

* fix(tts): make max turns input editable, tighten panel padding

* fix(tts): restore shuffle animation in auto mode (compact version)

* fix(tts): adjust auto mode text spacing and add voice auto-assign hint

* fix(tts): auto-close voice popover after selecting a voice

* fix(tts): increase auto mode vertical padding for better balance

* fix(tts): push auto mode text toward bottom with flex spacer

* fix(tts): reduce auto mode bottom padding

* feat(tts): wait for TTS audio to finish before next agent turn

Add waitForDrain() to useDiscussionTTS that returns a promise
resolving when the audio queue is empty. The agent loop in
useChatSessions now awaits this after buffer drain, so the next
agent's turn doesn't start until the current agent's TTS audio
finishes playing.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(tts): keep bubble visible while TTS audio is still playing

When buffer drains (text=null) but audio indicator is still active,
don't clear liveSpeech. Clear it only when audio state goes idle.
This keeps the speech bubble visible until TTS finishes.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(tts): hold discussion bubble until TTS audio finishes

When StreamBuffer fires the done signal (onLiveSpeech null), Stage
now checks if TTS is still playing. If so, it defers clearing the
bubble state. The bubble stays visible until onAllAudioEnd fires
from the TTS hook (queue empty + nothing playing), then clears.

This prevents the jarring UX where the bubble disappears while
the agent's voice is still audible.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(tts): fix bubble hold - guard onStopSession instead of onLiveSpeech

Root cause: bubble disappears because doSessionCleanup fires via
onStopSession when the agent loop ends naturally, NOT because of
onLiveSpeech(null, null).

Fix: when onStopSession fires and TTS is still playing, defer
doSessionCleanup to onAllAudioEnd callback. Manual stop (user
presses button) still cleans up immediately via handleStopDiscussion.

Use doSessionCleanupRef to avoid circular dependency between
discussionTTS hook and doSessionCleanup useCallback.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(tts): guard BOTH onLiveSpeech and onStopSession for bubble hold

Two paths clear the bubble:
1. onLiveSpeech(null, null) from StreamBuffer done → clears liveSpeech
2. onStopSession → doSessionCleanup → clears all state

Both fire when agent loop ends. Path 1 fires first (tick loop),
path 2 fires after (waitUntilDrained resolves). Both must be
guarded when TTS is still playing.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(tts): hold bubble during TTS playback and respect playback speed

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(tts): LLM picks voice matching agent persona during generation

- Client sends available voices (providerId + voiceId + name) to
  /api/generate/agent-profiles
- LLM prompt asks to pick a voice matching each agent's personality
- Parse "providerId::voiceId" from response, save as voiceConfig
- Fallback to index-based assignment if LLM doesn't pick
- Browser native voices hidden when server providers are available
- saveGeneratedAgents accepts and persists voiceConfig

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(tts): restore volume slider in classroom toolbar

Revert the toolbar simplification from 36e3997 that replaced the
volume slider with a TTS on/off toggle. The volume control with
hover slider is a core classroom UX. TTS on/off is controlled via
Settings and Media popover instead.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(tts): teacher uses global lecture voice in discussion when no voiceConfig override

* fix(tts): teacher always uses global lecture voice, no overrides

* fix(tts): sync playback speed to currently playing audio in real-time

* fix(tts): address code review issues

- Issue 2: enabled flag now checks ttsEnabled && !ttsMuted in stage.tsx
- Issue 4: remove unused browserAvailableVoices from useDiscussionTTS
- Issue 5: remove dead code in audio-settings.tsx (Slider, Loader2, handleTTSVoiceChange, handleTTSSpeedChange, handleTestTTS, testingTTS, ttsTestStatus, ttsTestMessage, testText, ttsSpeed, setTTSSpeed, and unused browser-tts-preview imports)
- Issue 6: shouldHold now checks queue length in addition to isPlayingRef
- Issue 8: hide AgentVoicePill for teacher row in agent-bar.tsx (teacher voice is controlled in Settings)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix(tts): address PR review — abort preview fetch, defer error recovery

1. Add AbortController to voice preview server TTS fetch, abort on
   stopPreview to prevent stale responses on rapid switching
2. Use queueMicrotask for processQueue calls in error/ended handlers
   to prevent synchronous recursion if multiple items fail consecutively
3. Add ordering invariant comment on sealLastText's onSegmentSealed

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(tts): restore teacher voice pill, respect voiceConfig override

* fix(tts): sync volume and mute to discussion TTS audio in real-time

* fix(tts): allow browser-native TTS alongside server providers

* fix(tts): remove top padding from voice popover content

* fix(tts): make selectedAgents reactive to voiceConfig changes

* fix(tts): use agents record instead of listAgents() to avoid infinite loop

* fix(tts): single source of truth for teacher voice

Teacher voice pill now reads/writes global ttsProviderId + ttsVoice
(same settings used by lecture TTS). This ensures lecture and
discussion always use the same teacher voice. Student agents still
use per-agent voiceConfig.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: add avatar descriptions for smarter LLM avatar selection

Each avatar now has a one-line description (appearance, vibe) sent
to the agent-profiles generation API. LLM picks avatars matching
agent personality instead of guessing from file paths.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: 杨慎 <117187635+cosarah@users.noreply.github.com>
2026-03-23 17:35:09 +08:00
wyuc
1f84f4c4a7
fix: use resolved API key in chat route instead of client-sent key (#221)
* fix: use resolved API key in chat route instead of client-sent key (#220)

PR #114 refactored the chat route to use resolveModel() but replaced the
server-resolved API key with the raw client-sent body.apiKey for both the
401 check and the statelessGenerate call. This broke server-configured
providers (e.g. OPENAI_API_KEY env var) where the client sends no key.

- Add apiKey field to ResolvedModel interface so callers can access the
  effective key after server-side fallback resolution
- Use the resolved apiKey for the 401 guard and pass it to statelessGenerate

Fixes #220

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: allow keyless providers (e.g. local Ollama) to bypass API key check

Add requiresApiKey !== false guard so providers that don't need an API
key are not rejected by the 401 check.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-23 13:39:25 +08:00
Mohit Neerukonda
d0c324cbe9
fix: forward providerType to chat API for custom provider support (#114) 2026-03-22 23:35:51 +08:00
杨慎
fbe8399678
feat(generate): server-side media & TTS generation (#75)
* feat(generate): server-side media & TTS generation in classroom pipeline

When `enableImageGeneration`, `enableVideoGeneration`, or `enableTTS` flags
are passed to /api/generate-classroom, the server now actually generates
media files and TTS audio, persists them to disk, and replaces placeholders
in the classroom JSON with serving URLs.

- Add media serving API route (GET /api/classroom-media/[id]/[...path])
- Add server-side media generation utility (image, video, TTS)
- Wire generation phases into classroom pipeline with progress steps
- Update AudioPlayer to support URL-based playback (server-generated TTS)
- Add audioUrl field to SpeechAction type
- Extend /api/health with capabilities detection
- Pass through feature flags in generate-classroom route
- Update skill docs for optional feature configuration

Closes #49

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* style: fix prettier formatting

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(generate): add agentMode support for server-side classroom generation

Allow callers to choose between built-in default agents ('default') or
LLM-generated custom agent profiles ('generate') via a new agentMode
field on GenerateClassroomInput. The resolved agents are injected into
outline, scene content, and scene action prompts via teacherContext.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(media): harden download, parallelize media gen, fix TTS concatenation

- Add timeout (2min) and max size (100MB) guard to downloadToBuffer
- Run image and video generation in parallel via Promise.all
- Only split TTS text for MP3 (frame-based); skip for WAV/OGG/AAC
  whose container headers break on naive byte concatenation
- Remove unnecessary type assertion for speechAction.audioUrl

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* style: fix prettier formatting

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(media): harden media serving and TTS generation

- Add realpath check to prevent symlink-based path traversal in media route
- Stream files via createReadStream instead of readFile to avoid OOM on large videos
- Truncate TTS text for non-concatenable formats (WAV/OGG/AAC) when exceeding provider limit
- Add 'researching' step to distinguish web search from outline generation progress

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(tts): split long speech actions instead of concatenating audio bytes

Adopt the same strategy as client-side: split a long speech action into
multiple shorter actions before TTS generation, so each sub-action gets
its own audio file. This avoids the broken byte-concatenation approach
that corrupted non-MP3 formats (WAV/OGG/AAC container headers).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor(tts): extract shared TTS splitting logic into lib/audio/tts-utils

Both client-side (use-scene-generator) and server-side (classroom-media-generation)
had duplicated TTS_MAX_TEXT_LENGTH, text splitting, and action splitting logic.
Extract into a shared module to keep them in sync.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: remove unused TTS_MAX_TEXT_LENGTH import

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: wyuc <wang-yc24@mails.tsinghua.edu.cn>
2026-03-19 14:40:04 +08:00
Wing900
371aaee01e
Fix SSRF/credential forwarding via client-supplied baseUrl (#30)
* Fix SSRF/credential forwarding via client-supplied baseUrl

* chore: format SSRF fix
2026-03-17 12:39:22 +08:00
wyuc
c61cec0306 fix: address review issues in classroom generation pipeline
- Fix Prettier formatting on 4 files failing CI
- Fix race condition in classroom page by using setStage() and adding
  try/catch around server-side fetch fallback
- Consolidate duplicate classroom storage: api/classroom/route.ts now
  uses shared persistClassroom/readClassroom from classroom-storage.ts
- Add per-job mutex (withJobLock) to prevent concurrent read-modify-write
  on job files
- Add stale job detection: jobs stuck in "running" for >30 min are
  auto-marked as failed when read
- Validate provider API key before starting generation pipeline to
  fail fast with actionable error message

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-14 15:00:39 +08:00