How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

hve-resiliency-researcher-consolidate-2 - Prompt

Name: hve-resiliency-researcher-consolidate-2
Author: christopherromero

Prompt file imported from christopherromero/HVE-Resiliency (.github/prompts/researcher/hve-resiliency-researcher-consolidate-2.prompt.md). Copyright stays with the author.

HVE Resiliency Researcher Consolidate - Part C (Sections 6-9)

Use Resiliency Research Platform Context.

Run /hve-resiliency-researcher-consolidate-0 and /hve-resiliency-researcher-consolidate-1 first. This pass finishes the research file and is the final consolidation step before Phase 4 (Planning).

# HVE Task Researcher Prompt - Consolidation Part C (Sections 6-9 and Index)

You are acting as a Senior Cloud Application Architect completing the final consolidation of resiliency research.

## OBJECTIVE

Append Sections 6 through 8, then the authoritative Research Findings Index (Section 9), to the existing research file, and run the quality bar. After this pass the research file is complete and ready for the Planner.

Read first:
- `.copilot-tracking/research/YYYY-MM-DD-<repo-name>-findings-manifest.md` - the authoritative finding IDs, groups, and target sections.
- `.copilot-tracking/research/YYYY-MM-DD-<repo-name>-research.md` - the research file with Sections 1-5 already written (do NOT rewrite existing sections).
- The upstream Phase 1 and Phase 2 research artifacts that supply the evidence for these findings.

## NON-NEGOTIABLE RULES

- Evidence-only: do NOT provide remediation steps or design changes.
- Every finding MUST include the REQUIRED FINDINGS FORMAT below in full.
- Do NOT use advisory language ("should", "recommend").
- If a section has no applicable findings, state "None found".
- Use the finding IDs from the manifest **unchanged**. Do not renumber, reorder, or invent IDs.

## FINDING ORDER

Within each section, emit findings in ascending `PX-NNN` order. Place each finding under the section named by its manifest `Target Section`.

## REQUIRED FINDINGS FORMAT

### Finding P0-001 (example heading; replace with the actual PX-NNN from the manifest)

- **Priority:** P0 / P1 / P2 / P3
- **Description:** Evidence-based statement of current behavior
- **Evidence:** `file.ext:L123-146`

#### Why this is a risk to app, zone or region failover

- {{Reason 1}}
- {{Reason N}}

#### Impact(s) if this is not changed

- {{Operational impact}}
- {{Data or financial impact}}
- {{Customer-visible impact (if applicable)}}

#### Existing Mitigations

- {{Mitigation 1 (if any)}}
- _None identified_ (explicitly state if empty)

#### Constraints

- {{Technical constraint}}
- {{Organizational / business constraint}}
- {{Regulatory or architectural constraint}}

If none found, state: "None found".

## SECTIONS TO APPEND (use this exact structure and heading order)

------------------------------------------------------------

## 6. Shared and Cross-Repository Dependencies

For each finding with `Target Section` 6, use the REQUIRED FINDINGS FORMAT.

------------------------------------------------------------

## 7. Hard-coded values or secrets in code or files

For each finding with `Target Section` 7, use the REQUIRED FINDINGS FORMAT.

------------------------------------------------------------

## 8. Other Findings Not Categorized Above

For each finding with `Target Section` 8, use the REQUIRED FINDINGS FORMAT.

------------------------------------------------------------

## 9. Research Findings Index (Authoritative)

Build this table directly from the manifest so it lists **every** finding across Sections 2-8. Order by priority tier (P0, P1, P2, P3) then ascending `NNN`.

| Finding ID | Priority | Category | Short Description | Evidence (File:Line) |
|-----------|----------|----------|-------------------|---------------------|

------------------------------------------------------------

## QUALITY BAR CHECK

- No remediation text present anywhere in the research file.
- Every finding has a priority and code evidence.
- Every manifest finding appears exactly once in the body (Sections 2-8) and once in the Section 9 index, with the same ID.
- Findings are in ascending `PX-NNN` order within each section and in the index.
- Sections are complete even if empty ("None found").
- Findings are internally consistent.

Next Step

After completing this prompt:

Next step: Run /clear, then /hve-resiliency-planner-0 to begin Phase 4 (Planning).

Output Review

Review notice: Carefully review this prompt's output before relying on it. AI-assisted analysis may contain inaccuracies, omitted evidence, misclassified findings, or internal inconsistencies. Validate every claim against the cited file and line references, confirm priority assignments, and reconcile any contradictions before advancing to the next prompt or phase.

Install hve-resiliency-researcher-consolidate-2 and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

# HVE Resiliency Researcher Consolidate - Part C (Sections 6-9) Use [Resiliency Research Platform Context](../../../instructions/hve-resiliency-platform-context.instructions.md). Run `/hve-resiliency-researcher-consolidate-0` and `/hve-resiliency-researcher-consolidate-1` first. This pass finishes the research file and is the final consolidation step before Phase 4 (Planning). ```text # HVE Task Researcher Prompt - Consolidation Part C (Sections 6-9 and Index) You are acting as a Senior Cloud Application Architect completing the final consolidation of resiliency research. ## OBJECTIVE Append Sections 6 through 8, then the authoritative Research Findings Index (Section 9), to the existing research file, and run the quality bar. After this pass the research file is complete and ready for the Planner. Read first: - `.copilot-tracking/research/YYYY-MM-DD-<repo-name>-findings-manifest.md` - the authoritative finding IDs, groups, and target sections. - `.copilot-tracking/research/YYYY-MM-DD-<repo-name>-research.md` - the research file with Sections 1-5 already written (do NOT rewrite existing sections). - The upstream Phase 1 and Phase 2 research artifacts that supply the evidence for these findings. ## NON-NEGOTIABLE RULES - Evidence-only: do NOT provide remediation steps or design changes. - Every finding MUST include the REQUIRED FINDINGS FORMAT below in full. - Do NOT use advisory language ("should", "recommend"). - If a section has no applicable findings, state "None found". - Use the finding IDs from the manifest **unchanged**. Do not renumber, reorder, or invent IDs. ## FINDING ORDER Within each section, emit findings in ascending `PX-NNN` order. Place each finding under the section named by its manifest `Target Section`. ## REQUIRED FINDINGS FORMAT ### Finding P0-001 (example heading; replace with the actual PX-NNN from the manifest) - **Priority:** P0 / P1 / P2 / P3 - **Description:** Evidence-based statement of current behavior - **Evidence:** `file.ext:L123-146` #### Why this is a risk to app, zone or region failover - {{Reason 1}} - {{Reason N}} #### Impact(s) if this is not changed - {{Operational impact}} - {{Data or financial impact}} - {{Customer-visible impact (if applicable)}} #### Existing Mitigations - {{Mitigation 1 (if any)}} - _None identified_ (explicitly state if empty) #### Constraints - {{Technical constraint}} - {{Organizational / business constraint}} - {{Regulatory or architectural constraint}} If none found, state: "None found". ## SECTIONS TO APPEND (use this exact structure and heading order) ------------------------------------------------------------ ## 6. Shared and Cross-Repository Dependencies For each finding with `Target Section` 6, use the REQUIRED FINDINGS FORMAT. ------------------------------------------------------------ ## 7. Hard-coded values or secrets in code or files For each finding with `Target Section` 7, use the REQUIRED FINDINGS FORMAT. ------------------------------------------------------------ ## 8. Other Findings Not Categorized Above For each finding with `Target Section` 8, use the REQUIRED FINDINGS FORMAT. ------------------------------------------------------------ ## 9. Research Findings Index (Authoritative) Build this table directly from the manifest so it lists **every** finding across Sections 2-8. Order by priority tier (P0, P1, P2, P3) then ascending `NNN`. | Finding ID | Priority | Category | Short Description | Evidence (File:Line) | |-----------|----------|----------|-------------------|---------------------| ------------------------------------------------------------ ## QUALITY BAR CHECK - No remediation text present anywhere in the research file. - Every finding has a priority and code evidence. - Every manifest finding appears exactly once in the body (Sections 2-8) and once in the Section 9 index, with the same ID. - Findings are in ascending `PX-NNN` order within each section and in the index. - Sections are complete even if empty ("None found"). - Findings are internally consistent. ``` ## Next Step After completing this prompt: > **Next step:** Run `/clear`, then `/hve-resiliency-planner-0` to begin Phase 4 (Planning). ## Output Review > **Review notice:** Carefully review this prompt's output before relying on it. AI-assisted analysis may contain inaccuracies, omitted evidence, misclassified findings, or internal inconsistencies. Validate every claim against the cited file and line references, confirm priority assignments, and reconcile any contradictions before advancing to the next prompt or phase.

{ "prompt": "# HVE Resiliency Researcher Consolidate - Part C (Sections 6-9)\n\nUse [Resiliency Research Platform Context](../../../instructions/hve-resiliency-platform-context.instructions.md).\n\nRun `/hve-resiliency-researcher-consolidate-0` and `/hve-resiliency-researcher-consolidate-1` first. This pass finishes the research file and is the final consolidation step before Phase 4 (Planning).\n\n```text\n# HVE Task Researcher Prompt - Consolidation Part C (Sections 6-9 and Index)\n\nYou are acting as a Senior Cloud Application Architect completing the final consolidation of resiliency research.\n\n## OBJECTIVE\n\nAppend Sections 6 through 8, then the authoritative Research Findings Index (Section 9), to the existing research file, and run the quality bar. After this pass the research file is complete and ready for the Planner.\n\nRead first:\n- `.copilot-tracking/research/YYYY-MM-DD-<repo-name>-findings-manifest.md` - the authoritative finding IDs, groups, and target sections.\n- `.copilot-tracking/research/YYYY-MM-DD-<repo-name>-research.md` - the research file with Sections 1-5 already written (do NOT rewrite existing sections).\n- The upstream Phase 1 and Phase 2 research artifacts that supply the evidence for these findings.\n\n## NON-NEGOTIABLE RULES\n\n- Evidence-only: do NOT provide remediation steps or design changes.\n- Every finding MUST include the REQUIRED FINDINGS FORMAT below in full.\n- Do NOT use advisory language (\"should\", \"recommend\").\n- If a section has no applicable findings, state \"None found\".\n- Use the finding IDs from the manifest **unchanged**. Do not renumber, reorder, or invent IDs.\n\n## FINDING ORDER\n\nWithin each section, emit findings in ascending `PX-NNN` order. Place each finding under the section named by its manifest `Target Section`.\n\n## REQUIRED FINDINGS FORMAT\n\n### Finding P0-001 (example heading; replace with the actual PX-NNN from the manifest)\n\n- **Priority:** P0 / P1 / P2 / P3\n- **Description:** Evidence-based statement of current behavior\n- **Evidence:** `file.ext:L123-146`\n\n#### Why this is a risk to app, zone or region failover\n\n- {{Reason 1}}\n- {{Reason N}}\n\n#### Impact(s) if this is not changed\n\n- {{Operational impact}}\n- {{Data or financial impact}}\n- {{Customer-visible impact (if applicable)}}\n\n#### Existing Mitigations\n\n- {{Mitigation 1 (if any)}}\n- _None identified_ (explicitly state if empty)\n\n#### Constraints\n\n- {{Technical constraint}}\n- {{Organizational / business constraint}}\n- {{Regulatory or architectural constraint}}\n\nIf none found, state: \"None found\".\n\n## SECTIONS TO APPEND (use this exact structure and heading order)\n\n------------------------------------------------------------\n\n## 6. Shared and Cross-Repository Dependencies\n\nFor each finding with `Target Section` 6, use the REQUIRED FINDINGS FORMAT.\n\n------------------------------------------------------------\n\n## 7. Hard-coded values or secrets in code or files\n\nFor each finding with `Target Section` 7, use the REQUIRED FINDINGS FORMAT.\n\n------------------------------------------------------------\n\n## 8. Other Findings Not Categorized Above\n\nFor each finding with `Target Section` 8, use the REQUIRED FINDINGS FORMAT.\n\n------------------------------------------------------------\n\n## 9. Research Findings Index (Authoritative)\n\nBuild this table directly from the manifest so it lists **every** finding across Sections 2-8. Order by priority tier (P0, P1, P2, P3) then ascending `NNN`.\n\n| Finding ID | Priority | Category | Short Description | Evidence (File:Line) |\n|-----------|----------|----------|-------------------|---------------------|\n\n------------------------------------------------------------\n\n## QUALITY BAR CHECK\n\n- No remediation text present anywhere in the research file.\n- Every finding has a priority and code evidence.\n- Every manifest finding appears exactly once in the body (Sections 2-8) and once in the Section 9 index, with the same ID.\n- Findings are in ascending `PX-NNN` order within each section and in the index.\n- Sections are complete even if empty (\"None found\").\n- Findings are internally consistent.\n```\n\n## Next Step\n\nAfter completing this prompt:\n\n> **Next step:** Run `/clear`, then `/hve-resiliency-planner-0` to begin Phase 4 (Planning).\n\n## Output Review\n\n> **Review notice:** Carefully review this prompt's output before relying on it. AI-assisted analysis may contain inaccuracies, omitted evidence, misclassified findings, or internal inconsistencies. Validate every claim against the cited file and line references, confirm priority assignments, and reconcile any contradictions before advancing to the next prompt or phase.", "variables": [], "notes": "Consolidation Part C - append Shared Dependencies, Hard-coded values, Other findings, and the authoritative Research Findings Index, then run the quality bar", "metadata": { "source": { "provider": "github-prompts", "repository": "https://github.com/christopherromero/HVE-Resiliency", "path": ".github/prompts/researcher/hve-resiliency-researcher-consolidate-2.prompt.md", "ref": "ae2c2edbd2a7cc502fd2400458cc1e0913d8eb56", "url": "https://github.com/christopherromero/HVE-Resiliency/blob/ae2c2edbd2a7cc502fd2400458cc1e0913d8eb56/.github/prompts/researcher/hve-resiliency-researcher-consolidate-2.prompt.md", "key": "christopherromero/HVE-Resiliency/.github/prompts/researcher/hve-resiliency-researcher-consolidate-2.prompt.md" } } }

hve-resiliency-researcher-consolidate-2

About

HVE Resiliency Researcher Consolidate - Part C (Sections 6-9)

Next Step

Output Review

Install hve-resiliency-researcher-consolidate-2 and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Use it

Manifest

Reviews