docs(readme): refresh for the agentic upload refactor by Jose-Gael-Cruz-Lopez · Pull Request #68 · SaplingLearn/Sapling

Jose-Gael-Cruz-Lopez · 2026-05-04T07:17:12Z

Summary

Bring the README up to date with the agentic upload pipeline that landed in PR re-architecture: agentic document upload + AES-256-GCM column encryption + dev-context vault #67 and the 15 MB → 100 MB upload-cap bump (commit 9912a25).
Document the new SSE upload route and event vocabulary, the X-Request-ID idempotency contract, and the post-merge migration.
Surface the dev-context vault: ADR index 0001-0012, docs/attempts/, .claude/ slash commands, the context-curator subagent.
Add a new env-vars block for LOGFIRE_TOKEN, SAPLING_MODEL_*, OCR_ASYNC_ENABLED, and the optional DBOS pair.
Add a Tests section with the canonical pytest / vitest / eval-replay commands.

No code changes — docs only. README went from 203 → 284 lines (+88 / -6).

What's accurate now

Tech Stack: Pydantic AI agents, per-task model routing, Logfire (with PII scrubber), sse-starlette streaming, Vitest + jsdom on the frontend.
Document Library feature: 100 MB cap, live progress UX.
Documents API: /upload (SSE) vs /upload/sync (JSON), full event list, idempotency on X-Request-ID, the two scan-concepts endpoints that were already in code.
Environment: every env var the new code paths read, with a note on each one's purpose and default.
Migrations: the documents.request_id ALTER inline so a fresh deployment knows exactly what to run.
Architecture & Dev Context: link to `docs/architecture.md`, full ADR index, slash commands.

Test plan

Markdown renders correctly (links resolve, tables align)
No code changes — backend/frontend unchanged
Reviewer skim for tone / accuracy

🤖 Generated with Claude Code

Summary by CodeRabbit

Documentation
- Enhanced documentation for document ingestion workflow, including streaming upload progress phases and manual concept-note rescanning
- Updated API reference with new synchronous upload and concept-scan endpoints
- Expanded configuration documentation for backend environment variables and observability features
- Added architecture context and testing documentation sections

Brings the README up to date with what landed in PR #67 (the re-architecture branch) and the post-merge upload-cap bump. Tech Stack - Notes the Pydantic AI agentic pipeline (4 typed worker agents fanned out via asyncio.gather), per-task model routing with SAPLING_MODEL_<TASK> env overrides, and which agent uses which Gemini model by default. - Adds Logfire as the observability layer, including the custom span scrubber that truncates + SHA-256-fingerprints user-content attribute paths before egress. - Notes sse-starlette for the streaming /upload route and the per-request structured logging (correlation ID, status, duration). - Calls out Vitest with jsdom + RTL on the frontend. Document Library feature - New 100 MB upload cap (was 15 MB; commit 9912a25). - Live SSE progress UX: "Classifying..." → "Extracting..." → "Saved." API Endpoints — Documents - Splits into POST /upload (streaming SSE) and POST /upload/sync (non-streaming JSON), with the full SSE event vocabulary (status:start, progress:classify, progress:classified, progress:extract, progress:extracted, progress:graph_update, progress:graph_updated, result:finalize, status:done, error:fallback, error:failed). - Documents the X-Request-ID idempotency contract. - Adds the two scan-concepts endpoints that were already in the code but not in the README. Environment Variables - LOGFIRE_TOKEN (optional) - SAPLING_MODEL_CLASSIFIER / _SUMMARY / _CONCEPTS / _SYLLABUS - OCR_ASYNC_ENABLED feature flag - DBOS_ENABLED + DBOS_DATABASE_URL (durable-execution opt-in) New sections - Tests: backend pytest commands, frontend Vitest commands, evals replay/record/live modes with the SAPLING_EVAL_MODE env var. - Architecture & Dev Context: pointer to docs/architecture.md, full ADR index (0001-0012), docs/attempts/, the .claude/ slash commands, and the context-curator subagent. - Migrations: the documents.request_id ALTER inline so anyone bringing up a fresh environment knows what needs to run. No code changes; docs only. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

coderabbitai · 2026-05-04T07:17:24Z

Caution

Review failed

Pull request was closed or merged during review

📝 Walkthrough

Walkthrough

The README was comprehensively expanded to document the streaming document-upload flow with SSE progress phases, detailed tech stack architecture (Pydantic AI agents, SSE streaming, Logfire observability, OCR fallbacks), refined API endpoint specifications including new concept-scanning endpoints, backend environment variables, testing modes, architectural context links, and a required database migration for request-ID deduplication.

Changes

Documentation Expansion

Layer / File(s)	Summary
Feature & Capability Overview `README.md` (lines 28–30, 41–46)	Document Library feature now describes streaming SSE upload phases, extracted outputs (summaries, concept notes, flashcard topics), and manual re-scanning. Tech Stack section expanded to detail frontend/backend stacks, Pydantic AI typed worker agents, model routing via env vars, and OCR pipeline.
API Endpoint Specification `README.md` (lines 124–130)	Documents API section rewritten to detail streaming `POST /api/documents/upload` lifecycle (SSE event names, error/fallback behavior, `X-Request-ID` idempotency), addition of `POST /api/documents/upload/sync`, and new concept-scan endpoints for stored documents and course graphs.
Environment & Configuration `README.md` (lines 197–204)	Backend `.env` documentation extended with Logfire token, per-task model override vars (`SAPLING_MODEL_*`), OCR async flag, and DBOS durable execution config.
Testing & Architecture Context `README.md` (lines 213–241, 242–265)	Added Tests section documenting pytest/Vitest/eval invocation with replay/record/live modes and CI behavior. Added Architecture & Dev Context section with links to architecture docs, ADR list, and development context references.
Data Integrity `README.md` (lines 266–281)	Added Migrations section documenting required Supabase SQL migration for `documents.request_id` column and unique index with null filter for idempotency.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Poem

🐰 A doc so bright, expanded with care,
SSE streams float through the air,
Models and migration paths aligned,
Architecture notes for the curious mind,
This README now tells the whole tale,
Of documents, tests, and never to fail!

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change—a README refresh for the agentic upload refactor—and is concise and specific.
Description check	✅ Passed	The description comprehensively covers changes made, includes context from related PRs, documents the test plan, and aligns with the repository's template structure.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Commit unit tests in branch docs/readme-refresh

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Review rate limit: 0/1 reviews remaining, refill in 60 minutes.}

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

cloudflare-workers-and-pages · 2026-05-04T07:18:39Z

Deploying with Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Preview URL	Updated (UTC)
✅ Deployment successful! View logs	frontend	`781d65b`	Commit Preview URL Branch Preview URL	May 04 2026, 07:18 AM

Jose-Gael-Cruz-Lopez · 2026-05-04T07:17:12Z

Summary

Bring the README up to date with the agentic upload pipeline that landed in PR re-architecture: agentic document upload + AES-256-GCM column encryption + dev-context vault #67 and the 15 MB → 100 MB upload-cap bump (commit 9912a25).
Document the new SSE upload route and event vocabulary, the X-Request-ID idempotency contract, and the post-merge migration.
Surface the dev-context vault: ADR index 0001-0012, docs/attempts/, .claude/ slash commands, the context-curator subagent.
Add a new env-vars block for LOGFIRE_TOKEN, SAPLING_MODEL_*, OCR_ASYNC_ENABLED, and the optional DBOS pair.
Add a Tests section with the canonical pytest / vitest / eval-replay commands.

No code changes — docs only. README went from 203 → 284 lines (+88 / -6).

What's accurate now

Tech Stack: Pydantic AI agents, per-task model routing, Logfire (with PII scrubber), sse-starlette streaming, Vitest + jsdom on the frontend.
Document Library feature: 100 MB cap, live progress UX.
Documents API: /upload (SSE) vs /upload/sync (JSON), full event list, idempotency on X-Request-ID, the two scan-concepts endpoints that were already in code.
Environment: every env var the new code paths read, with a note on each one's purpose and default.
Migrations: the documents.request_id ALTER inline so a fresh deployment knows exactly what to run.
Architecture & Dev Context: link to `docs/architecture.md`, full ADR index, slash commands.

Test plan

Markdown renders correctly (links resolve, tables align)
No code changes — backend/frontend unchanged
Reviewer skim for tone / accuracy

🤖 Generated with Claude Code

Summary by CodeRabbit

Documentation
- Enhanced documentation for document ingestion workflow, including streaming upload progress phases and manual concept-note rescanning
- Updated API reference with new synchronous upload and concept-scan endpoints
- Expanded configuration documentation for backend environment variables and observability features
- Added architecture context and testing documentation sections

Brings the README up to date with what landed in PR #67 (the re-architecture branch) and the post-merge upload-cap bump. Tech Stack - Notes the Pydantic AI agentic pipeline (4 typed worker agents fanned out via asyncio.gather), per-task model routing with SAPLING_MODEL_<TASK> env overrides, and which agent uses which Gemini model by default. - Adds Logfire as the observability layer, including the custom span scrubber that truncates + SHA-256-fingerprints user-content attribute paths before egress. - Notes sse-starlette for the streaming /upload route and the per-request structured logging (correlation ID, status, duration). - Calls out Vitest with jsdom + RTL on the frontend. Document Library feature - New 100 MB upload cap (was 15 MB; commit 9912a25). - Live SSE progress UX: "Classifying..." → "Extracting..." → "Saved." API Endpoints — Documents - Splits into POST /upload (streaming SSE) and POST /upload/sync (non-streaming JSON), with the full SSE event vocabulary (status:start, progress:classify, progress:classified, progress:extract, progress:extracted, progress:graph_update, progress:graph_updated, result:finalize, status:done, error:fallback, error:failed). - Documents the X-Request-ID idempotency contract. - Adds the two scan-concepts endpoints that were already in the code but not in the README. Environment Variables - LOGFIRE_TOKEN (optional) - SAPLING_MODEL_CLASSIFIER / _SUMMARY / _CONCEPTS / _SYLLABUS - OCR_ASYNC_ENABLED feature flag - DBOS_ENABLED + DBOS_DATABASE_URL (durable-execution opt-in) New sections - Tests: backend pytest commands, frontend Vitest commands, evals replay/record/live modes with the SAPLING_EVAL_MODE env var. - Architecture & Dev Context: pointer to docs/architecture.md, full ADR index (0001-0012), docs/attempts/, the .claude/ slash commands, and the context-curator subagent. - Migrations: the documents.request_id ALTER inline so anyone bringing up a fresh environment knows what needs to run. No code changes; docs only. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

coderabbitai · 2026-05-04T07:17:24Z

Caution

Review failed

Pull request was closed or merged during review

📝 Walkthrough

Walkthrough

The README was comprehensively expanded to document the streaming document-upload flow with SSE progress phases, detailed tech stack architecture (Pydantic AI agents, SSE streaming, Logfire observability, OCR fallbacks), refined API endpoint specifications including new concept-scanning endpoints, backend environment variables, testing modes, architectural context links, and a required database migration for request-ID deduplication.

Changes

Documentation Expansion

Layer / File(s)	Summary
Feature & Capability Overview `README.md` (lines 28–30, 41–46)	Document Library feature now describes streaming SSE upload phases, extracted outputs (summaries, concept notes, flashcard topics), and manual re-scanning. Tech Stack section expanded to detail frontend/backend stacks, Pydantic AI typed worker agents, model routing via env vars, and OCR pipeline.
API Endpoint Specification `README.md` (lines 124–130)	Documents API section rewritten to detail streaming `POST /api/documents/upload` lifecycle (SSE event names, error/fallback behavior, `X-Request-ID` idempotency), addition of `POST /api/documents/upload/sync`, and new concept-scan endpoints for stored documents and course graphs.
Environment & Configuration `README.md` (lines 197–204)	Backend `.env` documentation extended with Logfire token, per-task model override vars (`SAPLING_MODEL_*`), OCR async flag, and DBOS durable execution config.
Testing & Architecture Context `README.md` (lines 213–241, 242–265)	Added Tests section documenting pytest/Vitest/eval invocation with replay/record/live modes and CI behavior. Added Architecture & Dev Context section with links to architecture docs, ADR list, and development context references.
Data Integrity `README.md` (lines 266–281)	Added Migrations section documenting required Supabase SQL migration for `documents.request_id` column and unique index with null filter for idempotency.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Poem

🐰 A doc so bright, expanded with care,
SSE streams float through the air,
Models and migration paths aligned,
Architecture notes for the curious mind,
This README now tells the whole tale,
Of documents, tests, and never to fail!

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change—a README refresh for the agentic upload refactor—and is concise and specific.
Description check	✅ Passed	The description comprehensively covers changes made, includes context from related PRs, documents the test plan, and aligns with the repository's template structure.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Commit unit tests in branch docs/readme-refresh

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Review rate limit: 0/1 reviews remaining, refill in 60 minutes.}

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

cloudflare-workers-and-pages · 2026-05-04T07:18:39Z

Deploying with Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Preview URL	Updated (UTC)
✅ Deployment successful! View logs	frontend	`781d65b`	Commit Preview URL Branch Preview URL	May 04 2026, 07:18 AM

Jose-Gael-Cruz-Lopez · 2026-05-04T07:17:12Z

Summary

Bring the README up to date with the agentic upload pipeline that landed in PR re-architecture: agentic document upload + AES-256-GCM column encryption + dev-context vault #67 and the 15 MB → 100 MB upload-cap bump (commit 9912a25).
Document the new SSE upload route and event vocabulary, the X-Request-ID idempotency contract, and the post-merge migration.
Surface the dev-context vault: ADR index 0001-0012, docs/attempts/, .claude/ slash commands, the context-curator subagent.
Add a new env-vars block for LOGFIRE_TOKEN, SAPLING_MODEL_*, OCR_ASYNC_ENABLED, and the optional DBOS pair.
Add a Tests section with the canonical pytest / vitest / eval-replay commands.

No code changes — docs only. README went from 203 → 284 lines (+88 / -6).

What's accurate now

Tech Stack: Pydantic AI agents, per-task model routing, Logfire (with PII scrubber), sse-starlette streaming, Vitest + jsdom on the frontend.
Document Library feature: 100 MB cap, live progress UX.
Documents API: /upload (SSE) vs /upload/sync (JSON), full event list, idempotency on X-Request-ID, the two scan-concepts endpoints that were already in code.
Environment: every env var the new code paths read, with a note on each one's purpose and default.
Migrations: the documents.request_id ALTER inline so a fresh deployment knows exactly what to run.
Architecture & Dev Context: link to `docs/architecture.md`, full ADR index, slash commands.

Test plan

Markdown renders correctly (links resolve, tables align)
No code changes — backend/frontend unchanged
Reviewer skim for tone / accuracy

🤖 Generated with Claude Code

Summary by CodeRabbit

Documentation
- Enhanced documentation for document ingestion workflow, including streaming upload progress phases and manual concept-note rescanning
- Updated API reference with new synchronous upload and concept-scan endpoints
- Expanded configuration documentation for backend environment variables and observability features
- Added architecture context and testing documentation sections

Brings the README up to date with what landed in PR #67 (the re-architecture branch) and the post-merge upload-cap bump. Tech Stack - Notes the Pydantic AI agentic pipeline (4 typed worker agents fanned out via asyncio.gather), per-task model routing with SAPLING_MODEL_<TASK> env overrides, and which agent uses which Gemini model by default. - Adds Logfire as the observability layer, including the custom span scrubber that truncates + SHA-256-fingerprints user-content attribute paths before egress. - Notes sse-starlette for the streaming /upload route and the per-request structured logging (correlation ID, status, duration). - Calls out Vitest with jsdom + RTL on the frontend. Document Library feature - New 100 MB upload cap (was 15 MB; commit 9912a25). - Live SSE progress UX: "Classifying..." → "Extracting..." → "Saved." API Endpoints — Documents - Splits into POST /upload (streaming SSE) and POST /upload/sync (non-streaming JSON), with the full SSE event vocabulary (status:start, progress:classify, progress:classified, progress:extract, progress:extracted, progress:graph_update, progress:graph_updated, result:finalize, status:done, error:fallback, error:failed). - Documents the X-Request-ID idempotency contract. - Adds the two scan-concepts endpoints that were already in the code but not in the README. Environment Variables - LOGFIRE_TOKEN (optional) - SAPLING_MODEL_CLASSIFIER / _SUMMARY / _CONCEPTS / _SYLLABUS - OCR_ASYNC_ENABLED feature flag - DBOS_ENABLED + DBOS_DATABASE_URL (durable-execution opt-in) New sections - Tests: backend pytest commands, frontend Vitest commands, evals replay/record/live modes with the SAPLING_EVAL_MODE env var. - Architecture & Dev Context: pointer to docs/architecture.md, full ADR index (0001-0012), docs/attempts/, the .claude/ slash commands, and the context-curator subagent. - Migrations: the documents.request_id ALTER inline so anyone bringing up a fresh environment knows what needs to run. No code changes; docs only. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

coderabbitai · 2026-05-04T07:17:24Z

Caution

Review failed

Pull request was closed or merged during review

📝 Walkthrough

Walkthrough

The README was comprehensively expanded to document the streaming document-upload flow with SSE progress phases, detailed tech stack architecture (Pydantic AI agents, SSE streaming, Logfire observability, OCR fallbacks), refined API endpoint specifications including new concept-scanning endpoints, backend environment variables, testing modes, architectural context links, and a required database migration for request-ID deduplication.

Changes

Documentation Expansion

Layer / File(s)	Summary
Feature & Capability Overview `README.md` (lines 28–30, 41–46)	Document Library feature now describes streaming SSE upload phases, extracted outputs (summaries, concept notes, flashcard topics), and manual re-scanning. Tech Stack section expanded to detail frontend/backend stacks, Pydantic AI typed worker agents, model routing via env vars, and OCR pipeline.
API Endpoint Specification `README.md` (lines 124–130)	Documents API section rewritten to detail streaming `POST /api/documents/upload` lifecycle (SSE event names, error/fallback behavior, `X-Request-ID` idempotency), addition of `POST /api/documents/upload/sync`, and new concept-scan endpoints for stored documents and course graphs.
Environment & Configuration `README.md` (lines 197–204)	Backend `.env` documentation extended with Logfire token, per-task model override vars (`SAPLING_MODEL_*`), OCR async flag, and DBOS durable execution config.
Testing & Architecture Context `README.md` (lines 213–241, 242–265)	Added Tests section documenting pytest/Vitest/eval invocation with replay/record/live modes and CI behavior. Added Architecture & Dev Context section with links to architecture docs, ADR list, and development context references.
Data Integrity `README.md` (lines 266–281)	Added Migrations section documenting required Supabase SQL migration for `documents.request_id` column and unique index with null filter for idempotency.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Poem

🐰 A doc so bright, expanded with care,
SSE streams float through the air,
Models and migration paths aligned,
Architecture notes for the curious mind,
This README now tells the whole tale,
Of documents, tests, and never to fail!

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change—a README refresh for the agentic upload refactor—and is concise and specific.
Description check	✅ Passed	The description comprehensively covers changes made, includes context from related PRs, documents the test plan, and aligns with the repository's template structure.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Commit unit tests in branch docs/readme-refresh

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Review rate limit: 0/1 reviews remaining, refill in 60 minutes.}

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

cloudflare-workers-and-pages · 2026-05-04T07:18:39Z

Deploying with Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Preview URL	Updated (UTC)
✅ Deployment successful! View logs	frontend	`781d65b`	Commit Preview URL Branch Preview URL	May 04 2026, 07:18 AM

Jose-Gael-Cruz-Lopez · 2026-05-04T07:17:12Z

Summary

Bring the README up to date with the agentic upload pipeline that landed in PR re-architecture: agentic document upload + AES-256-GCM column encryption + dev-context vault #67 and the 15 MB → 100 MB upload-cap bump (commit 9912a25).
Document the new SSE upload route and event vocabulary, the X-Request-ID idempotency contract, and the post-merge migration.
Surface the dev-context vault: ADR index 0001-0012, docs/attempts/, .claude/ slash commands, the context-curator subagent.
Add a new env-vars block for LOGFIRE_TOKEN, SAPLING_MODEL_*, OCR_ASYNC_ENABLED, and the optional DBOS pair.
Add a Tests section with the canonical pytest / vitest / eval-replay commands.

No code changes — docs only. README went from 203 → 284 lines (+88 / -6).

What's accurate now

Tech Stack: Pydantic AI agents, per-task model routing, Logfire (with PII scrubber), sse-starlette streaming, Vitest + jsdom on the frontend.
Document Library feature: 100 MB cap, live progress UX.
Documents API: /upload (SSE) vs /upload/sync (JSON), full event list, idempotency on X-Request-ID, the two scan-concepts endpoints that were already in code.
Environment: every env var the new code paths read, with a note on each one's purpose and default.
Migrations: the documents.request_id ALTER inline so a fresh deployment knows exactly what to run.
Architecture & Dev Context: link to `docs/architecture.md`, full ADR index, slash commands.

Test plan

Markdown renders correctly (links resolve, tables align)
No code changes — backend/frontend unchanged
Reviewer skim for tone / accuracy

🤖 Generated with Claude Code

Summary by CodeRabbit

Documentation
- Enhanced documentation for document ingestion workflow, including streaming upload progress phases and manual concept-note rescanning
- Updated API reference with new synchronous upload and concept-scan endpoints
- Expanded configuration documentation for backend environment variables and observability features
- Added architecture context and testing documentation sections

Brings the README up to date with what landed in PR #67 (the re-architecture branch) and the post-merge upload-cap bump. Tech Stack - Notes the Pydantic AI agentic pipeline (4 typed worker agents fanned out via asyncio.gather), per-task model routing with SAPLING_MODEL_<TASK> env overrides, and which agent uses which Gemini model by default. - Adds Logfire as the observability layer, including the custom span scrubber that truncates + SHA-256-fingerprints user-content attribute paths before egress. - Notes sse-starlette for the streaming /upload route and the per-request structured logging (correlation ID, status, duration). - Calls out Vitest with jsdom + RTL on the frontend. Document Library feature - New 100 MB upload cap (was 15 MB; commit 9912a25). - Live SSE progress UX: "Classifying..." → "Extracting..." → "Saved." API Endpoints — Documents - Splits into POST /upload (streaming SSE) and POST /upload/sync (non-streaming JSON), with the full SSE event vocabulary (status:start, progress:classify, progress:classified, progress:extract, progress:extracted, progress:graph_update, progress:graph_updated, result:finalize, status:done, error:fallback, error:failed). - Documents the X-Request-ID idempotency contract. - Adds the two scan-concepts endpoints that were already in the code but not in the README. Environment Variables - LOGFIRE_TOKEN (optional) - SAPLING_MODEL_CLASSIFIER / _SUMMARY / _CONCEPTS / _SYLLABUS - OCR_ASYNC_ENABLED feature flag - DBOS_ENABLED + DBOS_DATABASE_URL (durable-execution opt-in) New sections - Tests: backend pytest commands, frontend Vitest commands, evals replay/record/live modes with the SAPLING_EVAL_MODE env var. - Architecture & Dev Context: pointer to docs/architecture.md, full ADR index (0001-0012), docs/attempts/, the .claude/ slash commands, and the context-curator subagent. - Migrations: the documents.request_id ALTER inline so anyone bringing up a fresh environment knows what needs to run. No code changes; docs only. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

coderabbitai · 2026-05-04T07:17:24Z

Caution

Review failed

Pull request was closed or merged during review

📝 Walkthrough

Walkthrough

The README was comprehensively expanded to document the streaming document-upload flow with SSE progress phases, detailed tech stack architecture (Pydantic AI agents, SSE streaming, Logfire observability, OCR fallbacks), refined API endpoint specifications including new concept-scanning endpoints, backend environment variables, testing modes, architectural context links, and a required database migration for request-ID deduplication.

Changes

Documentation Expansion

Layer / File(s)	Summary
Feature & Capability Overview `README.md` (lines 28–30, 41–46)	Document Library feature now describes streaming SSE upload phases, extracted outputs (summaries, concept notes, flashcard topics), and manual re-scanning. Tech Stack section expanded to detail frontend/backend stacks, Pydantic AI typed worker agents, model routing via env vars, and OCR pipeline.
API Endpoint Specification `README.md` (lines 124–130)	Documents API section rewritten to detail streaming `POST /api/documents/upload` lifecycle (SSE event names, error/fallback behavior, `X-Request-ID` idempotency), addition of `POST /api/documents/upload/sync`, and new concept-scan endpoints for stored documents and course graphs.
Environment & Configuration `README.md` (lines 197–204)	Backend `.env` documentation extended with Logfire token, per-task model override vars (`SAPLING_MODEL_*`), OCR async flag, and DBOS durable execution config.
Testing & Architecture Context `README.md` (lines 213–241, 242–265)	Added Tests section documenting pytest/Vitest/eval invocation with replay/record/live modes and CI behavior. Added Architecture & Dev Context section with links to architecture docs, ADR list, and development context references.
Data Integrity `README.md` (lines 266–281)	Added Migrations section documenting required Supabase SQL migration for `documents.request_id` column and unique index with null filter for idempotency.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Poem

🐰 A doc so bright, expanded with care,
SSE streams float through the air,
Models and migration paths aligned,
Architecture notes for the curious mind,
This README now tells the whole tale,
Of documents, tests, and never to fail!

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change—a README refresh for the agentic upload refactor—and is concise and specific.
Description check	✅ Passed	The description comprehensively covers changes made, includes context from related PRs, documents the test plan, and aligns with the repository's template structure.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Commit unit tests in branch docs/readme-refresh

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Review rate limit: 0/1 reviews remaining, refill in 60 minutes.}

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

cloudflare-workers-and-pages · 2026-05-04T07:18:39Z

Deploying with Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Preview URL	Updated (UTC)
✅ Deployment successful! View logs	frontend	`781d65b`	Commit Preview URL Branch Preview URL	May 04 2026, 07:18 AM

Jose-Gael-Cruz-Lopez · 2026-05-04T07:17:12Z

Summary

Bring the README up to date with the agentic upload pipeline that landed in PR re-architecture: agentic document upload + AES-256-GCM column encryption + dev-context vault #67 and the 15 MB → 100 MB upload-cap bump (commit 9912a25).
Document the new SSE upload route and event vocabulary, the X-Request-ID idempotency contract, and the post-merge migration.
Surface the dev-context vault: ADR index 0001-0012, docs/attempts/, .claude/ slash commands, the context-curator subagent.
Add a new env-vars block for LOGFIRE_TOKEN, SAPLING_MODEL_*, OCR_ASYNC_ENABLED, and the optional DBOS pair.
Add a Tests section with the canonical pytest / vitest / eval-replay commands.

No code changes — docs only. README went from 203 → 284 lines (+88 / -6).

What's accurate now

Tech Stack: Pydantic AI agents, per-task model routing, Logfire (with PII scrubber), sse-starlette streaming, Vitest + jsdom on the frontend.
Document Library feature: 100 MB cap, live progress UX.
Documents API: /upload (SSE) vs /upload/sync (JSON), full event list, idempotency on X-Request-ID, the two scan-concepts endpoints that were already in code.
Environment: every env var the new code paths read, with a note on each one's purpose and default.
Migrations: the documents.request_id ALTER inline so a fresh deployment knows exactly what to run.
Architecture & Dev Context: link to `docs/architecture.md`, full ADR index, slash commands.

Test plan

Markdown renders correctly (links resolve, tables align)
No code changes — backend/frontend unchanged
Reviewer skim for tone / accuracy

🤖 Generated with Claude Code

Summary by CodeRabbit

Documentation
- Enhanced documentation for document ingestion workflow, including streaming upload progress phases and manual concept-note rescanning
- Updated API reference with new synchronous upload and concept-scan endpoints
- Expanded configuration documentation for backend environment variables and observability features
- Added architecture context and testing documentation sections

Brings the README up to date with what landed in PR #67 (the re-architecture branch) and the post-merge upload-cap bump. Tech Stack - Notes the Pydantic AI agentic pipeline (4 typed worker agents fanned out via asyncio.gather), per-task model routing with SAPLING_MODEL_<TASK> env overrides, and which agent uses which Gemini model by default. - Adds Logfire as the observability layer, including the custom span scrubber that truncates + SHA-256-fingerprints user-content attribute paths before egress. - Notes sse-starlette for the streaming /upload route and the per-request structured logging (correlation ID, status, duration). - Calls out Vitest with jsdom + RTL on the frontend. Document Library feature - New 100 MB upload cap (was 15 MB; commit 9912a25). - Live SSE progress UX: "Classifying..." → "Extracting..." → "Saved." API Endpoints — Documents - Splits into POST /upload (streaming SSE) and POST /upload/sync (non-streaming JSON), with the full SSE event vocabulary (status:start, progress:classify, progress:classified, progress:extract, progress:extracted, progress:graph_update, progress:graph_updated, result:finalize, status:done, error:fallback, error:failed). - Documents the X-Request-ID idempotency contract. - Adds the two scan-concepts endpoints that were already in the code but not in the README. Environment Variables - LOGFIRE_TOKEN (optional) - SAPLING_MODEL_CLASSIFIER / _SUMMARY / _CONCEPTS / _SYLLABUS - OCR_ASYNC_ENABLED feature flag - DBOS_ENABLED + DBOS_DATABASE_URL (durable-execution opt-in) New sections - Tests: backend pytest commands, frontend Vitest commands, evals replay/record/live modes with the SAPLING_EVAL_MODE env var. - Architecture & Dev Context: pointer to docs/architecture.md, full ADR index (0001-0012), docs/attempts/, the .claude/ slash commands, and the context-curator subagent. - Migrations: the documents.request_id ALTER inline so anyone bringing up a fresh environment knows what needs to run. No code changes; docs only. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

coderabbitai · 2026-05-04T07:17:24Z

Caution

Review failed

Pull request was closed or merged during review

📝 Walkthrough

Walkthrough

The README was comprehensively expanded to document the streaming document-upload flow with SSE progress phases, detailed tech stack architecture (Pydantic AI agents, SSE streaming, Logfire observability, OCR fallbacks), refined API endpoint specifications including new concept-scanning endpoints, backend environment variables, testing modes, architectural context links, and a required database migration for request-ID deduplication.

Changes

Documentation Expansion

Layer / File(s)	Summary
Feature & Capability Overview `README.md` (lines 28–30, 41–46)	Document Library feature now describes streaming SSE upload phases, extracted outputs (summaries, concept notes, flashcard topics), and manual re-scanning. Tech Stack section expanded to detail frontend/backend stacks, Pydantic AI typed worker agents, model routing via env vars, and OCR pipeline.
API Endpoint Specification `README.md` (lines 124–130)	Documents API section rewritten to detail streaming `POST /api/documents/upload` lifecycle (SSE event names, error/fallback behavior, `X-Request-ID` idempotency), addition of `POST /api/documents/upload/sync`, and new concept-scan endpoints for stored documents and course graphs.
Environment & Configuration `README.md` (lines 197–204)	Backend `.env` documentation extended with Logfire token, per-task model override vars (`SAPLING_MODEL_*`), OCR async flag, and DBOS durable execution config.
Testing & Architecture Context `README.md` (lines 213–241, 242–265)	Added Tests section documenting pytest/Vitest/eval invocation with replay/record/live modes and CI behavior. Added Architecture & Dev Context section with links to architecture docs, ADR list, and development context references.
Data Integrity `README.md` (lines 266–281)	Added Migrations section documenting required Supabase SQL migration for `documents.request_id` column and unique index with null filter for idempotency.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Poem

🐰 A doc so bright, expanded with care,
SSE streams float through the air,
Models and migration paths aligned,
Architecture notes for the curious mind,
This README now tells the whole tale,
Of documents, tests, and never to fail!

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change—a README refresh for the agentic upload refactor—and is concise and specific.
Description check	✅ Passed	The description comprehensively covers changes made, includes context from related PRs, documents the test plan, and aligns with the repository's template structure.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Commit unit tests in branch docs/readme-refresh

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Review rate limit: 0/1 reviews remaining, refill in 60 minutes.}

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

cloudflare-workers-and-pages · 2026-05-04T07:18:39Z

Deploying with Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Preview URL	Updated (UTC)
✅ Deployment successful! View logs	frontend	`781d65b`	Commit Preview URL Branch Preview URL	May 04 2026, 07:18 AM

Jose-Gael-Cruz-Lopez · 2026-05-04T07:17:12Z

Summary

Bring the README up to date with the agentic upload pipeline that landed in PR re-architecture: agentic document upload + AES-256-GCM column encryption + dev-context vault #67 and the 15 MB → 100 MB upload-cap bump (commit 9912a25).
Document the new SSE upload route and event vocabulary, the X-Request-ID idempotency contract, and the post-merge migration.
Surface the dev-context vault: ADR index 0001-0012, docs/attempts/, .claude/ slash commands, the context-curator subagent.
Add a new env-vars block for LOGFIRE_TOKEN, SAPLING_MODEL_*, OCR_ASYNC_ENABLED, and the optional DBOS pair.
Add a Tests section with the canonical pytest / vitest / eval-replay commands.

No code changes — docs only. README went from 203 → 284 lines (+88 / -6).

What's accurate now

Tech Stack: Pydantic AI agents, per-task model routing, Logfire (with PII scrubber), sse-starlette streaming, Vitest + jsdom on the frontend.
Document Library feature: 100 MB cap, live progress UX.
Documents API: /upload (SSE) vs /upload/sync (JSON), full event list, idempotency on X-Request-ID, the two scan-concepts endpoints that were already in code.
Environment: every env var the new code paths read, with a note on each one's purpose and default.
Migrations: the documents.request_id ALTER inline so a fresh deployment knows exactly what to run.
Architecture & Dev Context: link to `docs/architecture.md`, full ADR index, slash commands.

Test plan

Markdown renders correctly (links resolve, tables align)
No code changes — backend/frontend unchanged
Reviewer skim for tone / accuracy

🤖 Generated with Claude Code

Summary by CodeRabbit

Documentation
- Enhanced documentation for document ingestion workflow, including streaming upload progress phases and manual concept-note rescanning
- Updated API reference with new synchronous upload and concept-scan endpoints
- Expanded configuration documentation for backend environment variables and observability features
- Added architecture context and testing documentation sections

Brings the README up to date with what landed in PR #67 (the re-architecture branch) and the post-merge upload-cap bump. Tech Stack - Notes the Pydantic AI agentic pipeline (4 typed worker agents fanned out via asyncio.gather), per-task model routing with SAPLING_MODEL_<TASK> env overrides, and which agent uses which Gemini model by default. - Adds Logfire as the observability layer, including the custom span scrubber that truncates + SHA-256-fingerprints user-content attribute paths before egress. - Notes sse-starlette for the streaming /upload route and the per-request structured logging (correlation ID, status, duration). - Calls out Vitest with jsdom + RTL on the frontend. Document Library feature - New 100 MB upload cap (was 15 MB; commit 9912a25). - Live SSE progress UX: "Classifying..." → "Extracting..." → "Saved." API Endpoints — Documents - Splits into POST /upload (streaming SSE) and POST /upload/sync (non-streaming JSON), with the full SSE event vocabulary (status:start, progress:classify, progress:classified, progress:extract, progress:extracted, progress:graph_update, progress:graph_updated, result:finalize, status:done, error:fallback, error:failed). - Documents the X-Request-ID idempotency contract. - Adds the two scan-concepts endpoints that were already in the code but not in the README. Environment Variables - LOGFIRE_TOKEN (optional) - SAPLING_MODEL_CLASSIFIER / _SUMMARY / _CONCEPTS / _SYLLABUS - OCR_ASYNC_ENABLED feature flag - DBOS_ENABLED + DBOS_DATABASE_URL (durable-execution opt-in) New sections - Tests: backend pytest commands, frontend Vitest commands, evals replay/record/live modes with the SAPLING_EVAL_MODE env var. - Architecture & Dev Context: pointer to docs/architecture.md, full ADR index (0001-0012), docs/attempts/, the .claude/ slash commands, and the context-curator subagent. - Migrations: the documents.request_id ALTER inline so anyone bringing up a fresh environment knows what needs to run. No code changes; docs only. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

coderabbitai · 2026-05-04T07:17:24Z

Caution

Review failed

Pull request was closed or merged during review

📝 Walkthrough

Walkthrough

The README was comprehensively expanded to document the streaming document-upload flow with SSE progress phases, detailed tech stack architecture (Pydantic AI agents, SSE streaming, Logfire observability, OCR fallbacks), refined API endpoint specifications including new concept-scanning endpoints, backend environment variables, testing modes, architectural context links, and a required database migration for request-ID deduplication.

Changes

Documentation Expansion

Layer / File(s)	Summary
Feature & Capability Overview `README.md` (lines 28–30, 41–46)	Document Library feature now describes streaming SSE upload phases, extracted outputs (summaries, concept notes, flashcard topics), and manual re-scanning. Tech Stack section expanded to detail frontend/backend stacks, Pydantic AI typed worker agents, model routing via env vars, and OCR pipeline.
API Endpoint Specification `README.md` (lines 124–130)	Documents API section rewritten to detail streaming `POST /api/documents/upload` lifecycle (SSE event names, error/fallback behavior, `X-Request-ID` idempotency), addition of `POST /api/documents/upload/sync`, and new concept-scan endpoints for stored documents and course graphs.
Environment & Configuration `README.md` (lines 197–204)	Backend `.env` documentation extended with Logfire token, per-task model override vars (`SAPLING_MODEL_*`), OCR async flag, and DBOS durable execution config.
Testing & Architecture Context `README.md` (lines 213–241, 242–265)	Added Tests section documenting pytest/Vitest/eval invocation with replay/record/live modes and CI behavior. Added Architecture & Dev Context section with links to architecture docs, ADR list, and development context references.
Data Integrity `README.md` (lines 266–281)	Added Migrations section documenting required Supabase SQL migration for `documents.request_id` column and unique index with null filter for idempotency.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Poem

🐰 A doc so bright, expanded with care,
SSE streams float through the air,
Models and migration paths aligned,
Architecture notes for the curious mind,
This README now tells the whole tale,
Of documents, tests, and never to fail!

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change—a README refresh for the agentic upload refactor—and is concise and specific.
Description check	✅ Passed	The description comprehensively covers changes made, includes context from related PRs, documents the test plan, and aligns with the repository's template structure.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Commit unit tests in branch docs/readme-refresh

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Review rate limit: 0/1 reviews remaining, refill in 60 minutes.}

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

cloudflare-workers-and-pages · 2026-05-04T07:18:39Z

Deploying with Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Preview URL	Updated (UTC)
✅ Deployment successful! View logs	frontend	`781d65b`	Commit Preview URL Branch Preview URL	May 04 2026, 07:18 AM

Jose-Gael-Cruz-Lopez · 2026-05-04T07:17:12Z

Summary

Bring the README up to date with the agentic upload pipeline that landed in PR re-architecture: agentic document upload + AES-256-GCM column encryption + dev-context vault #67 and the 15 MB → 100 MB upload-cap bump (commit 9912a25).
Document the new SSE upload route and event vocabulary, the X-Request-ID idempotency contract, and the post-merge migration.
Surface the dev-context vault: ADR index 0001-0012, docs/attempts/, .claude/ slash commands, the context-curator subagent.
Add a new env-vars block for LOGFIRE_TOKEN, SAPLING_MODEL_*, OCR_ASYNC_ENABLED, and the optional DBOS pair.
Add a Tests section with the canonical pytest / vitest / eval-replay commands.

No code changes — docs only. README went from 203 → 284 lines (+88 / -6).

What's accurate now

Tech Stack: Pydantic AI agents, per-task model routing, Logfire (with PII scrubber), sse-starlette streaming, Vitest + jsdom on the frontend.
Document Library feature: 100 MB cap, live progress UX.
Documents API: /upload (SSE) vs /upload/sync (JSON), full event list, idempotency on X-Request-ID, the two scan-concepts endpoints that were already in code.
Environment: every env var the new code paths read, with a note on each one's purpose and default.
Migrations: the documents.request_id ALTER inline so a fresh deployment knows exactly what to run.
Architecture & Dev Context: link to `docs/architecture.md`, full ADR index, slash commands.

Test plan

Markdown renders correctly (links resolve, tables align)
No code changes — backend/frontend unchanged
Reviewer skim for tone / accuracy

🤖 Generated with Claude Code

Summary by CodeRabbit

Documentation
- Enhanced documentation for document ingestion workflow, including streaming upload progress phases and manual concept-note rescanning
- Updated API reference with new synchronous upload and concept-scan endpoints
- Expanded configuration documentation for backend environment variables and observability features
- Added architecture context and testing documentation sections

Brings the README up to date with what landed in PR #67 (the re-architecture branch) and the post-merge upload-cap bump. Tech Stack - Notes the Pydantic AI agentic pipeline (4 typed worker agents fanned out via asyncio.gather), per-task model routing with SAPLING_MODEL_<TASK> env overrides, and which agent uses which Gemini model by default. - Adds Logfire as the observability layer, including the custom span scrubber that truncates + SHA-256-fingerprints user-content attribute paths before egress. - Notes sse-starlette for the streaming /upload route and the per-request structured logging (correlation ID, status, duration). - Calls out Vitest with jsdom + RTL on the frontend. Document Library feature - New 100 MB upload cap (was 15 MB; commit 9912a25). - Live SSE progress UX: "Classifying..." → "Extracting..." → "Saved." API Endpoints — Documents - Splits into POST /upload (streaming SSE) and POST /upload/sync (non-streaming JSON), with the full SSE event vocabulary (status:start, progress:classify, progress:classified, progress:extract, progress:extracted, progress:graph_update, progress:graph_updated, result:finalize, status:done, error:fallback, error:failed). - Documents the X-Request-ID idempotency contract. - Adds the two scan-concepts endpoints that were already in the code but not in the README. Environment Variables - LOGFIRE_TOKEN (optional) - SAPLING_MODEL_CLASSIFIER / _SUMMARY / _CONCEPTS / _SYLLABUS - OCR_ASYNC_ENABLED feature flag - DBOS_ENABLED + DBOS_DATABASE_URL (durable-execution opt-in) New sections - Tests: backend pytest commands, frontend Vitest commands, evals replay/record/live modes with the SAPLING_EVAL_MODE env var. - Architecture & Dev Context: pointer to docs/architecture.md, full ADR index (0001-0012), docs/attempts/, the .claude/ slash commands, and the context-curator subagent. - Migrations: the documents.request_id ALTER inline so anyone bringing up a fresh environment knows what needs to run. No code changes; docs only. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

coderabbitai · 2026-05-04T07:17:24Z

Caution

Review failed

Pull request was closed or merged during review

📝 Walkthrough

Walkthrough

The README was comprehensively expanded to document the streaming document-upload flow with SSE progress phases, detailed tech stack architecture (Pydantic AI agents, SSE streaming, Logfire observability, OCR fallbacks), refined API endpoint specifications including new concept-scanning endpoints, backend environment variables, testing modes, architectural context links, and a required database migration for request-ID deduplication.

Changes

Documentation Expansion

Layer / File(s)	Summary
Feature & Capability Overview `README.md` (lines 28–30, 41–46)	Document Library feature now describes streaming SSE upload phases, extracted outputs (summaries, concept notes, flashcard topics), and manual re-scanning. Tech Stack section expanded to detail frontend/backend stacks, Pydantic AI typed worker agents, model routing via env vars, and OCR pipeline.
API Endpoint Specification `README.md` (lines 124–130)	Documents API section rewritten to detail streaming `POST /api/documents/upload` lifecycle (SSE event names, error/fallback behavior, `X-Request-ID` idempotency), addition of `POST /api/documents/upload/sync`, and new concept-scan endpoints for stored documents and course graphs.
Environment & Configuration `README.md` (lines 197–204)	Backend `.env` documentation extended with Logfire token, per-task model override vars (`SAPLING_MODEL_*`), OCR async flag, and DBOS durable execution config.
Testing & Architecture Context `README.md` (lines 213–241, 242–265)	Added Tests section documenting pytest/Vitest/eval invocation with replay/record/live modes and CI behavior. Added Architecture & Dev Context section with links to architecture docs, ADR list, and development context references.
Data Integrity `README.md` (lines 266–281)	Added Migrations section documenting required Supabase SQL migration for `documents.request_id` column and unique index with null filter for idempotency.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Poem

🐰 A doc so bright, expanded with care,
SSE streams float through the air,
Models and migration paths aligned,
Architecture notes for the curious mind,
This README now tells the whole tale,
Of documents, tests, and never to fail!

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change—a README refresh for the agentic upload refactor—and is concise and specific.
Description check	✅ Passed	The description comprehensively covers changes made, includes context from related PRs, documents the test plan, and aligns with the repository's template structure.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Commit unit tests in branch docs/readme-refresh

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Review rate limit: 0/1 reviews remaining, refill in 60 minutes.}

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

cloudflare-workers-and-pages · 2026-05-04T07:18:39Z

Deploying with Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Preview URL	Updated (UTC)
✅ Deployment successful! View logs	frontend	`781d65b`	Commit Preview URL Branch Preview URL	May 04 2026, 07:18 AM

Jose-Gael-Cruz-Lopez · 2026-05-04T07:17:12Z

Summary

Bring the README up to date with the agentic upload pipeline that landed in PR re-architecture: agentic document upload + AES-256-GCM column encryption + dev-context vault #67 and the 15 MB → 100 MB upload-cap bump (commit 9912a25).
Document the new SSE upload route and event vocabulary, the X-Request-ID idempotency contract, and the post-merge migration.
Surface the dev-context vault: ADR index 0001-0012, docs/attempts/, .claude/ slash commands, the context-curator subagent.
Add a new env-vars block for LOGFIRE_TOKEN, SAPLING_MODEL_*, OCR_ASYNC_ENABLED, and the optional DBOS pair.
Add a Tests section with the canonical pytest / vitest / eval-replay commands.

No code changes — docs only. README went from 203 → 284 lines (+88 / -6).

What's accurate now

Tech Stack: Pydantic AI agents, per-task model routing, Logfire (with PII scrubber), sse-starlette streaming, Vitest + jsdom on the frontend.
Document Library feature: 100 MB cap, live progress UX.
Documents API: /upload (SSE) vs /upload/sync (JSON), full event list, idempotency on X-Request-ID, the two scan-concepts endpoints that were already in code.
Environment: every env var the new code paths read, with a note on each one's purpose and default.
Migrations: the documents.request_id ALTER inline so a fresh deployment knows exactly what to run.
Architecture & Dev Context: link to `docs/architecture.md`, full ADR index, slash commands.

Test plan

Markdown renders correctly (links resolve, tables align)
No code changes — backend/frontend unchanged
Reviewer skim for tone / accuracy

🤖 Generated with Claude Code

Summary by CodeRabbit

Documentation
- Enhanced documentation for document ingestion workflow, including streaming upload progress phases and manual concept-note rescanning
- Updated API reference with new synchronous upload and concept-scan endpoints
- Expanded configuration documentation for backend environment variables and observability features
- Added architecture context and testing documentation sections

Brings the README up to date with what landed in PR #67 (the re-architecture branch) and the post-merge upload-cap bump. Tech Stack - Notes the Pydantic AI agentic pipeline (4 typed worker agents fanned out via asyncio.gather), per-task model routing with SAPLING_MODEL_<TASK> env overrides, and which agent uses which Gemini model by default. - Adds Logfire as the observability layer, including the custom span scrubber that truncates + SHA-256-fingerprints user-content attribute paths before egress. - Notes sse-starlette for the streaming /upload route and the per-request structured logging (correlation ID, status, duration). - Calls out Vitest with jsdom + RTL on the frontend. Document Library feature - New 100 MB upload cap (was 15 MB; commit 9912a25). - Live SSE progress UX: "Classifying..." → "Extracting..." → "Saved." API Endpoints — Documents - Splits into POST /upload (streaming SSE) and POST /upload/sync (non-streaming JSON), with the full SSE event vocabulary (status:start, progress:classify, progress:classified, progress:extract, progress:extracted, progress:graph_update, progress:graph_updated, result:finalize, status:done, error:fallback, error:failed). - Documents the X-Request-ID idempotency contract. - Adds the two scan-concepts endpoints that were already in the code but not in the README. Environment Variables - LOGFIRE_TOKEN (optional) - SAPLING_MODEL_CLASSIFIER / _SUMMARY / _CONCEPTS / _SYLLABUS - OCR_ASYNC_ENABLED feature flag - DBOS_ENABLED + DBOS_DATABASE_URL (durable-execution opt-in) New sections - Tests: backend pytest commands, frontend Vitest commands, evals replay/record/live modes with the SAPLING_EVAL_MODE env var. - Architecture & Dev Context: pointer to docs/architecture.md, full ADR index (0001-0012), docs/attempts/, the .claude/ slash commands, and the context-curator subagent. - Migrations: the documents.request_id ALTER inline so anyone bringing up a fresh environment knows what needs to run. No code changes; docs only. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

coderabbitai · 2026-05-04T07:17:24Z

Caution

Review failed

Pull request was closed or merged during review

📝 Walkthrough

Walkthrough

The README was comprehensively expanded to document the streaming document-upload flow with SSE progress phases, detailed tech stack architecture (Pydantic AI agents, SSE streaming, Logfire observability, OCR fallbacks), refined API endpoint specifications including new concept-scanning endpoints, backend environment variables, testing modes, architectural context links, and a required database migration for request-ID deduplication.

Changes

Documentation Expansion

Layer / File(s)	Summary
Feature & Capability Overview `README.md` (lines 28–30, 41–46)	Document Library feature now describes streaming SSE upload phases, extracted outputs (summaries, concept notes, flashcard topics), and manual re-scanning. Tech Stack section expanded to detail frontend/backend stacks, Pydantic AI typed worker agents, model routing via env vars, and OCR pipeline.
API Endpoint Specification `README.md` (lines 124–130)	Documents API section rewritten to detail streaming `POST /api/documents/upload` lifecycle (SSE event names, error/fallback behavior, `X-Request-ID` idempotency), addition of `POST /api/documents/upload/sync`, and new concept-scan endpoints for stored documents and course graphs.
Environment & Configuration `README.md` (lines 197–204)	Backend `.env` documentation extended with Logfire token, per-task model override vars (`SAPLING_MODEL_*`), OCR async flag, and DBOS durable execution config.
Testing & Architecture Context `README.md` (lines 213–241, 242–265)	Added Tests section documenting pytest/Vitest/eval invocation with replay/record/live modes and CI behavior. Added Architecture & Dev Context section with links to architecture docs, ADR list, and development context references.
Data Integrity `README.md` (lines 266–281)	Added Migrations section documenting required Supabase SQL migration for `documents.request_id` column and unique index with null filter for idempotency.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Poem

🐰 A doc so bright, expanded with care,
SSE streams float through the air,
Models and migration paths aligned,
Architecture notes for the curious mind,
This README now tells the whole tale,
Of documents, tests, and never to fail!

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change—a README refresh for the agentic upload refactor—and is concise and specific.
Description check	✅ Passed	The description comprehensively covers changes made, includes context from related PRs, documents the test plan, and aligns with the repository's template structure.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Commit unit tests in branch docs/readme-refresh

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Review rate limit: 0/1 reviews remaining, refill in 60 minutes.}

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

cloudflare-workers-and-pages · 2026-05-04T07:18:39Z

Deploying with Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Preview URL	Updated (UTC)
✅ Deployment successful! View logs	frontend	`781d65b`	Commit Preview URL Branch Preview URL	May 04 2026, 07:18 AM

Jose-Gael-Cruz-Lopez merged commit 818535d into mainMay 4, 2026
3 of 4 checks passed

AndresL230 deleted the docs/readme-refresh branch May 4, 2026 21:27