-
Notifications
You must be signed in to change notification settings - Fork 1
feat(ci): implement CISEv4 protocol #17262
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Closed
Closed
Changes from 1 commit
Commits
Show all changes
48 commits
Select commit
Hold shift + click to select a range
45a5414
feat(ci): implement CISEv4 protocol
google-labs-jules[bot] 29f73a4
fix(ci): complete workflow stabilization and version alignment
google-labs-jules[bot] 9cf3183
fix(ci): correct pnpm setup in release workflow
google-labs-jules[bot] e32187b
fix(ci): complete workflow stabilization and version alignment
google-labs-jules[bot] ebaa627
fix(ci): upgrade python to 3.11 in verify workflow
google-labs-jules[bot] b8ca2a1
fix(ci): resolve pnpm/node version conflicts and stabilize workflows
google-labs-jules[bot] 012aa37
fix(ci): align codeql workflow with project toolchain
google-labs-jules[bot] 5d70e24
fix(ci): complete workflow stabilization and version alignment
google-labs-jules[bot] 073e9ad
fix(ci): consolidate all pnpm and node version fixes
google-labs-jules[bot] f3732c9
fix(ci): final verification of docs workflow
google-labs-jules[bot] a7597ba
fix(ci): resolve all pnpm, node, and infrastructure failures
google-labs-jules[bot] 05d9b6b
fix(ci): add package script and verify workflow fixes
google-labs-jules[bot] c87e3f0
fix(ci): trigger fresh validation run
google-labs-jules[bot] 74ca760
fix(ci): strictly align pnpm version to 9.12.0
google-labs-jules[bot] 68d141c
fix(ci): complete workflow stabilization and version alignment
google-labs-jules[bot] cebc15b
fix(ci): universal pnpm version enforcement
google-labs-jules[bot] e15f4b9
fix(ci): standardize node version to 18 and pnpm to 9
google-labs-jules[bot] 297909c
fix(ci): add pnpm setup to release readiness workflow
google-labs-jules[bot] 3440a8d
fix(ci): fix pnpm and node versions across all workflows
google-labs-jules[bot] 762bbf1
fix(ci): final verification of pnpm setup in release workflow
google-labs-jules[bot] 3630566
fix(ci): complete CI/CD stabilization and evidence protocol
google-labs-jules[bot] d1d4d83
fix(ci): defer pnpm version to package.json to fix conflicts
google-labs-jules[bot] edee730
fix(ci): fix build-and-test workflow and finalize CI stabilization
google-labs-jules[bot] 85b909c
fix(ci): finalize workflow stabilization including semver check
google-labs-jules[bot] 7d21149
fix(ci): complete workflow stabilization and version alignment
google-labs-jules[bot] d3e8a12
fix(ci): consolidate all workflow fixes and verify stability
google-labs-jules[bot] 1c1949a
fix(ci): fix release readiness workflow pnpm setup
google-labs-jules[bot] 0119c10
fix(ci): complete workflow stabilization and version alignment
google-labs-jules[bot] fb88468
fix(ci): fix release-reliability workflow and finalize stabilization
google-labs-jules[bot] 96b025e
fix(ci): complete workflow stabilization and version alignment
google-labs-jules[bot] 2a31354
fix(ci): complete workflow stabilization and version alignment
google-labs-jules[bot] fee2037
fix(ci): complete workflow stabilization and version alignment
google-labs-jules[bot] 7158259
fix(ci): stabilize gates workflow and update changelog
google-labs-jules[bot] b23c299
fix(ci): final verification and stabilization
google-labs-jules[bot] d077569
fix(ci): ensure ux-governance artifact generation
google-labs-jules[bot] 5b78b07
fix(ci): standardize repro-build-check workflow
google-labs-jules[bot] cc74161
Fix auto-enqueue CI and implement CISEv4 structure
google-labs-jules[bot] 385f280
Fix CI dependency ordering and implement CISEv4 structure
google-labs-jules[bot] 5f72d80
Fix CI dependency ordering, auto-enqueue, and evidence validation; im…
google-labs-jules[bot] 14ba546
Fix pnpm setup order in gate.yml
google-labs-jules[bot] 7f35634
Fix pnpm setup order in summit-tests and gate workflows; fix helm lin…
google-labs-jules[bot] a0f130c
Fix CI pnpm setup order and verify-provenance version conflict; rever…
google-labs-jules[bot] 1d16ca2
Fix pnpm setup order in CI workflows
google-labs-jules[bot] ac859aa
Fix CI pnpm setup order in ci-verify and dependency-monitor; update C…
google-labs-jules[bot] 8e9dd0e
Fix CI pnpm setup order and update CHANGELOG
google-labs-jules[bot] 253af7e
chore: merge origin/main and resolve conflicts surgically
BrianCLong a816bca
chore: remove baggage files from old base
BrianCLong 88a8dcb
chore: merge origin/main and resolve conflicts surgically
BrianCLong File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,15 @@ | ||
| # Capability Matrix: [Target Name] | ||
|
|
||
| | Capability | Target Implementation | Summit Current | Gap | Opportunity | Risk | Evidence ID | | ||
| |------------|-----------------------|----------------|-----|-------------|------|-------------| | ||
| | Agent Orchestration | | | | | | | | ||
| | KG Schema | | | | | | | | ||
| | Ingestion | | | | | | | | ||
| | Entity Resolution | | | | | | | | ||
| | Graph Queries | | | | | | | | ||
| | Vector/Hybrid Search | | | | | | | | ||
| | UI | | | | | | | | ||
| | Connectors | | | | | | | | ||
| | RBAC/Audit | | | | | | | | ||
| | Evals | | | | | | | | ||
| | Ops | | | | | | | |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,15 @@ | ||
| # Eval Plan: [Target Name] | ||
|
|
||
| ## Metrics | ||
| | Metric | Definition | Threshold | Evidence ID | | ||
| |--------|------------|-----------|-------------| | ||
| | Latency | | | | | ||
| | Accuracy | | | | | ||
| | Cost | | | | | ||
|
|
||
| ## Scenarios | ||
| 1. [Scenario 1] | ||
| 2. [Scenario 2] | ||
|
|
||
| ## Datasets | ||
| - [Dataset 1] |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,28 @@ | ||
| # Integration Plan: [Target Name] | ||
|
|
||
| ## Summit Module Impacts | ||
| ### Agent Spine | ||
| - [Impacts] | ||
|
|
||
| ### Connector Framework | ||
| - [Impacts] | ||
|
|
||
| ### Knowledge Graph | ||
| - [Schema Diffs] | ||
| - [Migrations] | ||
|
|
||
| ### Retrieval | ||
| - [GraphRAG Updates] | ||
|
|
||
| ## Minimal Implementation Slice (MVP) | ||
| - **Feature Flag:** `FEATURE_FLAG_NAME` | ||
| - **API Shape:** | ||
| ```typescript | ||
| // Type definitions | ||
| ``` | ||
| - **Data Model:** | ||
| ```graphql | ||
| // Schema changes | ||
| ``` | ||
| - **Tests & Evals:** | ||
| - [Test Plan] |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,23 @@ | ||
| # PR Stack Plan: [Target Name] | ||
|
|
||
| ## PR 1: Docs & Evidence | ||
| - **Scope:** Add evidence artifacts and initial docs. | ||
| - **Files:** `docs/ci/[target]/*`, `evidence/ci/[target]/*` | ||
| - **Risk:** Low | ||
|
|
||
| ## PR 2: Schema Updates | ||
| - **Scope:** Apply KG schema changes. | ||
| - **Files:** `schemas/` | ||
| - **Risk:** Medium | ||
| - **Migration:** [Migration Plan] | ||
|
|
||
| ## PR 3: MVP Implementation | ||
| - **Scope:** Implement MVP slice behind feature flag. | ||
| - **Files:** `packages/`, `services/` | ||
| - **Risk:** Medium | ||
| - **Feature Flag:** `FEATURE_FLAG_NAME` | ||
|
|
||
| ## PR 4: Evals & Gates | ||
| - **Scope:** Add CI gates and evaluation logic. | ||
| - **Files:** `ci/`, `tests/` | ||
| - **Risk:** Low |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,17 @@ | ||
| # CISEv4 Report: [Target Name] | ||
|
|
||
| **Date:** [YYYY-MM-DD] | ||
| **Analyst:** [Agent Name] | ||
| **Scope:** [Scope] | ||
|
|
||
| ## Executive Summary | ||
| [Brief summary of findings, key threats, and opportunities.] | ||
|
|
||
| ## Key Findings | ||
| - **Capability 1:** [Description] | ||
| - **Threat 1:** [Description] | ||
| - **Opportunity 1:** [Description] | ||
|
|
||
| ## Recommendations | ||
| 1. [Recommendation 1] | ||
| 2. [Recommendation 2] |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,14 @@ | ||
| { | ||
| "target": { | ||
| "name": "", | ||
| "type": "repo", | ||
| "slug": "" | ||
| }, | ||
| "run": { | ||
| "date": "YYYY-MM-DD", | ||
| "analyst": "agentic", | ||
| "scope": [] | ||
| }, | ||
| "sources": [], | ||
| "claims": [] | ||
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,22 @@ | ||
| # Threat Model: [Target Name] | ||
|
|
||
| ## Attack Surface | ||
| - **Authn/Authz:** [Notes] | ||
| - **Ingestion:** [Notes] | ||
| - **Connectors:** [Notes] | ||
| - **Prompts/Tools:** [Notes] | ||
| - **KG Mutations:** [Notes] | ||
| - **Multitenancy:** [Notes] | ||
| - **Audit Integrity:** [Notes] | ||
|
|
||
| ## Abuse Cases | ||
| | ID | Abuse Case | Impact | Mitigation (Target) | Mitigation (Summit) | | ||
| |----|------------|--------|---------------------|---------------------| | ||
| | AC1 | Data Poisoning | | | | | ||
| | AC2 | Prompt Injection | | | | | ||
| | AC3 | Credential Theft | | | | | ||
|
|
||
| ## Controls | ||
| | Control | Observed in Target | Missing in Target | Proposed for Summit | | ||
| |---------|--------------------|-------------------|---------------------| | ||
| | | | | | |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,61 @@ | ||
| { | ||
| "$schema": "http://json-schema.org/draft-07/schema#", | ||
| "title": "CISEv4 Evidence Schema", | ||
| "type": "object", | ||
| "properties": { | ||
| "target": { | ||
| "type": "object", | ||
| "properties": { | ||
| "name": { "type": "string" }, | ||
| "type": { "type": "string", "enum": ["repo", "product", "paper", "platform"] }, | ||
| "slug": { "type": "string" } | ||
| }, | ||
| "required": ["name", "type", "slug"] | ||
| }, | ||
| "run": { | ||
| "type": "object", | ||
| "properties": { | ||
| "date": { "type": "string", "pattern": "^\\d{4}-\\d{2}-\\d{2}$" }, | ||
| "analyst": { "type": "string" }, | ||
| "scope": { | ||
| "type": "array", | ||
| "items": { "type": "string" } | ||
| } | ||
| }, | ||
| "required": ["date", "analyst", "scope"] | ||
| }, | ||
| "sources": { | ||
| "type": "array", | ||
| "items": { | ||
| "type": "object", | ||
| "properties": { | ||
| "id": { "type": "string" }, | ||
| "title": { "type": "string" }, | ||
| "url": { "type": "string" }, | ||
| "license_hint": { "type": "string" }, | ||
| "excerpt_sha256": { "type": "string" }, | ||
| "notes": { "type": "string" } | ||
| }, | ||
| "required": ["id", "title", "url"] | ||
| } | ||
| }, | ||
| "claims": { | ||
| "type": "array", | ||
| "items": { | ||
| "type": "object", | ||
| "properties": { | ||
| "id": { "type": "string" }, | ||
| "claim": { "type": "string" }, | ||
| "evidence": { | ||
| "type": "array", | ||
| "items": { "type": "string" } | ||
| }, | ||
| "confidence": { "type": "string", "enum": ["high", "medium", "low"] }, | ||
| "type": { "type": "string", "enum": ["fact", "inference", "proposal"] } | ||
| }, | ||
| "required": ["id", "claim", "evidence", "confidence", "type"] | ||
| } | ||
| } | ||
| }, | ||
| "required": ["target", "run", "sources", "claims"] | ||
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,94 @@ | ||
| # SUMMIT — Competitive Intelligence Subsumption Engine v4 (CISEv4) | ||
|
|
||
| Target: [COMPETITOR / PLATFORM / REPO / PRODUCT] | ||
| Scope: [DOCS | OSS REPO | BLOGS | TALKS | PAPERS | APIS | ALL PUBLIC] | ||
| Date: [YYYY-MM-DD] | ||
| Summit branch: [branch-name] | ||
| Non-negotiables: Determinism, evidence-first, minimal blast radius, zero proprietary copying. | ||
|
|
||
| ## PRIME DIRECTIVE | ||
| Convert public competitive signals into a mergeable PR stack for Summit: | ||
| 1) Harvest (capabilities + patterns + threats + benchmarks) | ||
| 2) Subsume (native modules/APIs/data model/workflows/ops/governance) | ||
| 3) Surpass (novel capabilities + architectural leverage) | ||
| 4) Moat & gate (defensible differentiators enforced by controls) | ||
|
|
||
| ## LEGAL / ETHICAL / IP GUARDRAILS (HARD) | ||
| - Use only public information present in sources captured in this run. | ||
| - No proprietary code, no paywalled copying, no reverse engineering of closed binaries. | ||
| - For OSS: respect licenses; do not copy code. Re-implement concepts independently. | ||
| - Every claim must map to a captured source (URL + excerpt hash) OR be explicitly marked as inference. | ||
| - Anything not source-backed is labeled: (INFERENCE) or (PROPOSAL). | ||
|
|
||
| ## REQUIRED OUTPUTS (STRICT) | ||
| A) docs/ci/[target_slug]/REPORT.md | ||
| B) docs/ci/[target_slug]/SOURCES.json (deterministic, sorted) | ||
| C) docs/ci/[target_slug]/CAPABILITY_MATRIX.md | ||
| D) docs/ci/[target_slug]/THREAT_MODEL.md | ||
| E) docs/ci/[target_slug]/INTEGRATION_PLAN.md | ||
| F) docs/ci/[target_slug]/EVAL_PLAN.md | ||
| G) PR_STACK_PLAN.md (stacked PRs with gates + acceptance tests) | ||
| H) If any code is proposed: implement at least one “MVP slice” behind a feature flag with tests. | ||
|
|
||
| ## PHASE 0 — INPUT NORMALIZATION | ||
| 1. Identify the “target surface”: | ||
| - Product claims, architecture diagrams, API docs, user workflows, deployment model. | ||
| 2. Capture sources: | ||
| - Build SOURCES.json with fields: | ||
| - id (stable), title, url, retrieved_at (date only), content_hash (sha256 of excerpt), license_hint, notes | ||
| - Deterministic sorting: by url asc, then id asc. | ||
|
|
||
| ## PHASE 1 — HARVEST (FACTS ONLY) | ||
| Produce CAPABILITY_MATRIX.md: | ||
| - Rows: capabilities (agent orchestration, KG schema, ingestion, ER, graph queries, vector/hybrid search, UI, connectors, RBAC/audit, evals, ops) | ||
| - Columns: {Target, Summit-now, Gap, Opportunity, Risk, Evidence(source_id)} | ||
| No “marketing” language; use testable statements. | ||
|
|
||
| Produce THREAT_MODEL.md: | ||
| - Attack surface: authn/authz, ingestion, connectors, prompts/tools, KG mutations, multitenancy, audit integrity | ||
| - Abuse cases: data poisoning, prompt injection, connector credential exfiltration, graph inference leakage | ||
| - Controls observed in target (source-backed), controls missing, controls Summit should add | ||
|
|
||
| ## PHASE 2 — SUBSUME (SUMMIT FIT) | ||
| Produce INTEGRATION_PLAN.md with: | ||
| - Mapping to Summit modules: | ||
| - agent spine impacts (registry/contracts/routing) | ||
| - connector framework impacts (auth, rate limiting, provenance) | ||
| - knowledge graph impacts (schema diff, migrations, constraints) | ||
| - retrieval impacts (GraphRAG, hybrid search, caching) | ||
| - A minimal implementation slice: | ||
| - feature flag name | ||
| - public API shape (types) | ||
| - data model additions (migrations) | ||
| - tests and eval hooks | ||
|
|
||
| ## PHASE 3 — SURPASS (NEW ADVANTAGE) | ||
| Produce 3 “surpass moves” that are: | ||
| - Measurable (latency, cost, accuracy, analyst time-to-insight) | ||
| - Enforceable (CI checks / policy gates) | ||
| - Hard to replicate (network effects, governance automation, eval harness) | ||
|
|
||
| Each surpass move must include: | ||
| - hypothesis | ||
| - design sketch | ||
| - eval metric | ||
| - failure mode & rollback plan | ||
|
|
||
| ## PHASE 4 — MOAT & GATE (CONTROL POINTS) | ||
| Define moat gates as repository-enforced controls: | ||
| - Example categories: | ||
| - provenance: source-cited transformations | ||
| - integrity: append-only audit, tamper evidence | ||
| - safety: prompt/tool sandboxing, connector least privilege | ||
| - quality: eval thresholds, regression budgets | ||
| Write each as: Gate Name → What it prevents → How enforced → Evidence artifact | ||
|
|
||
| ## PHASE 5 — PR STACK (MERGEABLE) | ||
| Write PR_STACK_PLAN.md with 3–7 PRs: | ||
| - PR title, scope, files changed, risk level, rollout strategy, acceptance tests | ||
| - Each PR must be independently mergeable and pass CI | ||
| - Deterministic artifacts only (stable sorting, no timestamps except stamp.json) | ||
|
|
||
| ## STOP CONDITIONS | ||
| - If sources are insufficient, ship “docs-only” PR stack: SOURCES + matrices + plans + eval harness scaffolding. | ||
| - Do not fabricate. Mark unknowns explicitly. | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,11 @@ | ||
| You are Agent A (Evidence Harvester). | ||
| Goal: Produce SOURCES.json and a source-cited bullet digest. | ||
|
|
||
| Rules: | ||
| - Capture only public sources. | ||
| - For each source: url, title, license hint if obvious, excerpt (<=500 words), sha256 hash of excerpt. | ||
| - No commentary except minimal notes for relevance. | ||
| - Deterministic ordering and stable IDs. | ||
| Deliverables: | ||
| - docs/ci/[target]/SOURCES.json | ||
| - docs/ci/[target]/SOURCE_DIGEST.md (each claim references source_id) | ||
BrianCLong marked this conversation as resolved.
Outdated
Show resolved
Hide resolved
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,10 @@ | ||
| You are Agent B (Architecture Mapper). | ||
| Goal: Build a source-backed conceptual system map (no proprietary RE). | ||
|
|
||
| Output: | ||
| - docs/ci/[target]/ARCHITECTURE.md | ||
| Includes: | ||
| - components, data flows, trust boundaries, failure modes | ||
| - API conventions and error handling patterns (as observed) | ||
| - scalability posture (stateless/stateful split, caching, queues) | ||
| All statements must cite sources or be labeled INFERENCE. | ||
BrianCLong marked this conversation as resolved.
Outdated
Show resolved
Hide resolved
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,9 @@ | ||
| You are Agent C (KG + Retrieval Analyst). | ||
| Goal: | ||
| - Extract graph schema patterns, ER/dedup approach, ingestion transformations, vector/hybrid retrieval. | ||
|
|
||
| Deliverables: | ||
| - docs/ci/[target]/KG_MODEL.md (entities/edges/properties + constraints) | ||
| - docs/ci/[target]/RETRIEVAL.md (indexing, query patterns, caching) | ||
| - A Summit schema diff proposal (what to add, what not to add) | ||
BrianCLong marked this conversation as resolved.
Outdated
Show resolved
Hide resolved
|
||
| Cite sources; otherwise mark INFERENCE/PROPOSAL. | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,11 @@ | ||
| You are Agent D (Security + Controls). | ||
| Goal: | ||
| - Threat model the target; propose Summit gates. | ||
|
|
||
| Deliverables: | ||
| - docs/ci/[target]/THREAT_MODEL.md | ||
| - docs/ci/[target]/GOVERNANCE_GATES.md | ||
BrianCLong marked this conversation as resolved.
Outdated
Show resolved
Hide resolved
|
||
| Include: | ||
| - abuse cases (poisoning, injection, credential theft) | ||
| - controls observed vs missing | ||
| - CI-enforceable gates (lint/check scripts + evidence artifacts) | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,11 @@ | ||
| You are Agent E (PR Stack Engineer). | ||
| Goal: | ||
| - Convert plans into a minimal, mergeable PR stack. | ||
|
|
||
| Deliverables: | ||
| - PR_STACK_PLAN.md | ||
| - Implement 1 MVP slice behind a feature flag with tests + eval hook. | ||
| Constraints: | ||
| - minimal blast radius | ||
| - deterministic outputs | ||
| - no breaking changes without migration |
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.