> 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/phase33-session03-harden-trend-finder-projection/tasks.md).

# Task Checklist

**Session ID**: `phase33-session03-harden-trend-finder-projection` **Total Tasks**: 16 **Estimated Duration**: 3-4 hours **Created**: 2026-06-25

***

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

***

## Setup (3 tasks)

* [x] T001 \[S3303] Verify Session 01 and Session 02 evidence, count deltas, and projection gaps (`.spec_system/specs/phase33-session02-freeze-public-fixtures/implementation-notes.md`)
* [x] T002 \[S3303] Inspect current Trend Finder exporter, parser, Engine Replay schema, and focused tests (`scripts/lib/pages-demo-snapshot.ts`)
* [x] T003 \[S3303] Run a baseline dry-run snapshot count review before changing projection behavior (`bun run demo:snapshot --dry-run --json`)

***

## Foundation (4 tasks)

* [x] T004 \[S3303] Implement retained-ID selection helpers for topics, evidence, sources, and dependent artifacts with bounded limits and deterministic ordering (`scripts/lib/pages-demo-snapshot.ts`)
* [x] T005 \[S3303] Implement public-safe Trend Finder artifact projection helpers with schema-validated input and explicit error mapping (`scripts/lib/pages-demo-snapshot.ts`)
* [x] T006 \[S3303] Add explicit failure behavior when sanitized source Engine Replay data would be exported as missing (`scripts/lib/pages-demo-snapshot.ts`)
* [x] T007 \[S3303] Extend Trend Finder manifest field policy and count handling for retained trace and advanced artifacts (`scripts/lib/pages-demo-snapshot.ts`)

***

## Implementation (5 tasks)

* [x] T008 \[S3303] Wire relationship-aware limits into `projectTrendFinderData()` for retained topics, cited evidence plus reserve, sources, watchlist, movement rows, prediction/retro/story rows, narratives, clusters, and events (`scripts/lib/pages-demo-snapshot.ts`)
* [x] T009 \[S3303] Preserve public-safe Engine Replay summaries filtered to retained topic, evidence, source, artifact, and watchlist references (`scripts/lib/pages-demo-snapshot.ts`)
* [x] T010 \[S3303] Preserve schema-valid frozen demo provenance labels, notes, and selected valid analysis state without adding new provenance strings (`scripts/lib/pages-demo-snapshot.ts`)
* [x] T011 \[S3303] Regenerate committed public demo fixtures with duplicate target rejection and atomic write behavior preserved (`bun run demo:snapshot`)
* [x] T012 \[S3303] Record count deltas and fixture review evidence without raw private payload bodies (`.spec_system/specs/phase33-session03-harden-trend-finder-projection/implementation-notes.md`)

***

## Testing (4 tasks)

* [x] T013 \[S3303] Add a populated Trend Finder fixture regression test that asserts positive exported counts and `parseTrendFinderData()` success (`scripts/lib/__tests__/pages-demo-snapshot.test.ts`)
* [x] T014 \[S3303] Add reference-coherence tests for retained topics, evidence, sources, run narratives, demand clusters, industry events, movement rows, and Engine Replay summaries (`scripts/lib/__tests__/pages-demo-snapshot.test.ts`)
* [x] T015 \[S3303] Add privacy regression tests for private fields, local paths, raw logs, prompts, provider bodies, protected bridge URLs, and token-like strings in newly retained artifacts (`scripts/lib/__tests__/pages-demo-snapshot.test.ts`)
* [x] T016 \[S3303] Run focused tests, snapshot dry-run, fixture scan, JSON parse, ASCII/LF checks, and final count review (`bun run test -- scripts/lib/__tests__/pages-demo-snapshot.test.ts scripts/lib/__tests__/pages-demo-privacy-scan.test.ts`)

***

## 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 implementation changes

***

## 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/phase33-session03-harden-trend-finder-projection/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.