> For the complete documentation index, see [llms.txt](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/.spec_system/archive/sessions/phase38-session01-tier-0-parity-fixes/tasks.md).

# Task Checklist

**Session ID**: `phase38-session01-tier-0-parity-fixes` **Total Tasks**: 18 **Estimated Duration**: 3-4 hours **Created**: 2026-06-29

***

Legend: `[x]` completed; `[ ]` pending; `[P]` parallelizable; `[SNNMM]` session ref; `TNNN` task ID.

***

## Progress Summary

| Metric          | Value   |
| --------------- | ------- |
| Tasks Completed | 18 / 18 |
| Remaining Tasks | 0       |
| Blockers        | 0       |

***

## Setup (2 tasks)

* [x] T001 \[S3801] Verify upstream source references, current target files, and existing test owners before edits (`.spec_system/PRD/phase_38/session_01_tier_0_parity_fixes.md`)
* [x] T002 \[S3801] Record baseline targeted commands and any pre-existing blockers for Memory, seed-data, Hermes bridge, hook, and Knowledge Graph tests (`.spec_system/specs/phase38-session01-tier-0-parity-fixes/implementation-notes.md`)

***

## Foundation (3 tasks)

* [x] T003 \[S3801] \[P] Create the cross-platform seed-data script with no-clobber create-if-missing behavior, clear missing-source errors, and nonzero failure exits (`scripts/seed-data.ts`)
* [x] T004 \[S3801] \[P] Wire `seed:data` to the Bun script instead of the POSIX shell one-liner (`package.json`)
* [x] T005 \[S3801] \[P] Add seed-data tests for create, no-op existing file, and missing-source failure using temporary paths (`scripts/lib/__tests__/seed-data.test.ts`)

***

## Implementation (8 tasks)

* [x] T006 \[S3801] Replace the hardcoded Memory source tile count with `ALL_SOURCES.length` while preserving existing empty/demo states and product-facing copy (`src/routes/memory.tsx`)
* [x] T007 \[S3801] Extend Memory route tests for Pinecone-off and Pinecone-on source counts (`src/routes/__tests__/memory.test.tsx`)
* [x] T008 \[S3801] Add `graph?: boolean` to Hermes chat send options without changing existing attachment or prompt composition contracts (`src/components/hermes/chat/chat-types.ts`)
* [x] T009 \[S3801] Serialize validated `graph` chat payload options with duplicate-submit prevention and invalid-option rejection still intact (`src/hooks/use-hermes-admin.ts`)
* [x] T010 \[S3801] Add bridge-side `graph` validation with schema-validated input and explicit error mapping (`scripts/lib/hermes-admin-bridge.ts`)
* [x] T011 \[S3801] Decouple Hermes chat argv construction so `--yolo` and `-s graphify` are applied independently for all graph/yolo combinations (`scripts/lib/hermes-admin-bridge.ts`)
* [x] T012 \[S3801] Update Knowledge Graph grounded chat to send `{ toolsets: "graphify", yolo: true, graph: true }` explicitly (`src/lib/knowledge-graph-hermes-grounding.ts`)
* [x] T013 \[S3801] Update hook tests for graph serialization and invalid graph option rejection (`src/hooks/__tests__/use-hermes-admin.test.tsx`)

***

## Testing (5 tasks)

* [x] T014 \[S3801] \[P] Add bridge tests for invalid graph and graph off/yolo off, graph on/yolo off, yolo on/graph off, and both on argv combinations (`scripts/lib/__tests__/hermes-admin-bridge.test.ts`)
* [x] T015 \[S3801] \[P] Add Knowledge Graph grounding assertions for explicit `graph: true` send options (`src/lib/__tests__/knowledge-graph-hermes-grounding.test.ts`)
* [x] T016 \[S3801] Run targeted automated tests for Memory, seed-data, Hermes bridge, hook serialization, and Knowledge Graph grounding (`bun run test -- src/routes/__tests__/memory.test.tsx scripts/lib/__tests__/seed-data.test.ts scripts/lib/__tests__/hermes-admin-bridge.test.ts src/hooks/__tests__/use-hermes-admin.test.tsx src/lib/__tests__/knowledge-graph-hermes-grounding.test.ts`)
* [x] T017 \[S3801] Smoke-test `bun run seed:data` for existing-file no-op behavior and record any cross-platform harness evidence (`package.json`)
* [x] T018 \[S3801] Validate ASCII, LF, and implementation evidence before handing off to code review (`.spec_system/specs/phase38-session01-tier-0-parity-fixes/implementation-notes.md`)

***

## Completion Checklist

* [x] All tasks marked `[x]`
* [x] All tests and checks passing
* [x] All files ASCII-encoded with LF line endings
* [x] `implementation-notes.md` updated
* [x] Ready for `creview` to review and repair the completed implementation

***

## Next Steps

Run the `creview` workflow step.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/.spec_system/archive/sessions/phase38-session01-tier-0-parity-fixes/tasks.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.