sourcecode 1.73.0__tar.gz → 2.0.0__tar.gz

{sourcecode-1.73.0 → sourcecode-2.0.0}/.gitignore

@@ -35,6 +35,10 @@ Thumbs.db
 
 .planning
 
+# ContextGraph baseline — full canonical outputs (multi-MB, from external repos).
+# The light oracle (index.json) and convergence.json ARE committed.
+tests/contextgraph_baseline/baseline/artifacts/
+
 # Supabase local temp
 supabase/.temp/
 # Internal agent playbook (not distributed)

{sourcecode-1.73.0 → sourcecode-2.0.0}/CHANGELOG.md

@@ -1,5 +1,50 @@
 # Changelog
 
+## [2.0.0] — 2026-07-06
+
+**ASK Engine 2.0** — the product identity is now final. The engine is unchanged;
+this major marks the CLI/product rename and is fully backward compatible.
+
+### Changed — canonical command is now `ask`
+
+- **`ask` is the canonical CLI command.** `ask impact`, `ask migrate-check`,
+  `ask review-pr`, `ask mcp init`, `ask activate …` — one short verb that matches
+  the product name (ASK Engine).
+- **`sourcecode` becomes a deprecated compatibility alias.** It keeps working
+  (same single implementation, `prog_name` pinned to `ask`), prints a one-line
+  deprecation notice **only on an interactive terminal**, and forwards to `ask`.
+  Pipes and agents that still call `sourcecode` get byte-identical stdout **and**
+  clean (JSON-only) stderr — the machine contract is unchanged. The alias will be
+  removed in a future major.
+- **New welcome wordmark**: a large `ASK` block with an `E N G I N E` label
+  replaces the old `SOURCE`/`CODE` banner. Help and banners read `CLI: ask`.
+- **Config home moved to `~/.ask`** (canonical writes); the legacy `~/.sourcecode`
+  is still read as a fallback, so **no existing user loses their license or config**.
+  Cache dir (`.sourcecode-cache/`) and `SOURCECODE_*` env vars are unchanged.
+- **MCP**: `ask mcp init` registers the client entry under `ask`; a pre-existing
+  `sourcecode` entry is recognized and migrated (and both are removed on
+  `mcp remove`).
+- **Docs**: README, user guide, manual, tiers, demo and onboarding now say
+  **ASK Engine** and use `ask …` in every example. Package/install/config and
+  compatibility references are preserved and the compatibility strategy is
+  documented in `docs/PRODUCT_IDENTITY.md` (normative).
+
+### Compatibility
+
+- **PyPI/Homebrew distribution stays `sourcecode` this release**; installing it
+  provides both the `ask` and `sourcecode` commands. Renaming the distribution to
+  `ask-engine` is a separate, explicitly-breaking future change.
+- Python package/import name (`sourcecode`), MCP protocol identity, cache format,
+  and all serialized/JSON outputs are unchanged.
+
+### Also in this line (identity + precision, pre-2.0 increments)
+
+- **Impact/`review-pr`**: a changed repository/service now surfaces **every**
+  affected entry point (controller) instead of collapsing an N-controller blast
+  radius to one — bounded by `max_impacts`, no new semantic fact, hash-neutral.
+- **Product identity consolidation**: audited every `sourcecode` occurrence and
+  established `docs/PRODUCT_IDENTITY.md` as the normative product↔CLI mapping.
+
 ## [1.73.0] — 2026-07-01
 
 ### Fixed — audit reliability on a large non-Boot Spring monolith (Alfresco Community Repo field test)

{sourcecode-1.73.0 → sourcecode-2.0.0}/CONTRIBUTING.md

@@ -30,8 +30,8 @@ This installs `sourcecode` in editable mode with all development dependencies (`
 ### Run the CLI locally
 
 ```bash
-sourcecode . --agent
-sourcecode . prepare-context explain
+ask . --agent
+ask . prepare-context explain
 ```
 
 ### Run tests
@@ -150,7 +150,7 @@ Keep commits atomic. One logical change per commit.
 ## Reporting bugs
 
 Open an issue with:
-- `sourcecode --version` output
+- `ask --version` output
 - Command you ran
 - Expected behavior
 - Actual behavior / error output

{sourcecode-1.73.0 → sourcecode-2.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sourcecode
-Version: 1.73.0
+Version: 2.0.0
 Summary: Persistent structural context and ultra-fast repeated analysis for AI coding agents
 License-File: LICENSE
 Keywords: agents,ai,codebase,context,developer-tools,llm
@@ -36,22 +36,28 @@ Provides-Extra: mcp
 Requires-Dist: mcp>=1.0.0; extra == 'mcp'
 Description-Content-Type: text/markdown
 
-# sourcecode
+# ASK Engine
 
 **Persistent structural context and ultra-fast repeated analysis for AI coding agents.**
 
-![Version](https://img.shields.io/badge/version-1.59.0-blue)
+![Version](https://img.shields.io/badge/version-2.0.0-blue)
 ![Python](https://img.shields.io/badge/python-3.9%2B-green)
 
+> **ASK Engine** is the product. The CLI command is **`ask`**. The legacy
+> **`sourcecode`** command still works as a deprecated compatibility alias (it prints
+> a one-line notice and forwards to `ask`) and remains the Python/PyPI package name
+> for now. The authoritative version is whatever `ask version` reports. See
+> [docs/PRODUCT_IDENTITY.md](docs/PRODUCT_IDENTITY.md).
+
 ---
 
 ## The problem
 
 Every time an AI coding agent starts a new session, it has to re-parse the repository from scratch. For a large Java or TypeScript monolith, that means 5–15 seconds per invocation. Multiply by dozens of agent turns per hour, and repo context acquisition becomes a real bottleneck — not just latency, but tokens, compute, and iteration velocity.
 
-`sourcecode` solves this with a persistent structural cache keyed on file content hashes. After the first scan, every subsequent invocation returns pre-built context in milliseconds. The repo doesn't change? The cache doesn't expire.
+ASK Engine solves this with a persistent structural cache keyed on file content hashes. After the first scan, every subsequent invocation returns pre-built context in milliseconds. The repo doesn't change? The cache doesn't expire.
 
-**The cache is not a performance optimization. It is what makes sourcecode usable as infrastructure rather than a one-off tool.**
+**The cache is not a performance optimization. It is what makes ASK Engine usable as infrastructure rather than a one-off tool.**
 
 ---
 
@@ -77,19 +83,19 @@ Cache keyed on content hashes — invalidated only when source changes. On repea
 
 ## What changes at 0.3s vs 2.7s
 
-At 2.7s per call, you use sourcecode to occasionally inspect a repo.
+At 2.7s per call, you use ASK Engine to occasionally inspect a repo.
 
-At 0.3s per call, you use sourcecode as **constant infrastructure** inside agent loops:
+At 0.3s per call, you use ASK Engine as **constant infrastructure** inside agent loops:
 
 ```
 agent loop iteration:
-  1. sourcecode . --compact          # 0.3s — instant structural context
-  2. sourcecode impact PaymentService . --depth 1   # 0.4s — blast radius check
+  1. ask . --compact          # 0.3s — instant structural context
+  2. ask impact PaymentService . --depth 1   # 0.4s — blast radius check
   3. agent makes targeted change
   4. repeat
 ```
 
-Sub-second context retrieval changes the cost model for agent workflows. You can call sourcecode before every edit, before every PR review, before every test run — without batching or caching calls manually.
+Sub-second context retrieval changes the cost model for agent workflows. You can call ASK Engine before every edit, before every PR review, before every test run — without batching or caching calls manually.
 
 ---
 
@@ -110,11 +116,20 @@ pip install sourcecode
 pipx install sourcecode
 ```
 
+> **Package vs. command.** The install package is still named `sourcecode` this
+> release (renaming the PyPI/Homebrew distribution is a separate, breaking change).
+> Installing it gives you the canonical **`ask`** command plus the deprecated
+> **`sourcecode`** alias. A future release will publish `ask-engine` and drop the
+> alias.
+
 ### Verify
 
 ```bash
+ask version
+# ask 2.0.0
+
+# the deprecated alias still works (prints a one-line notice to stderr):
 sourcecode version
-# sourcecode 1.59.0
 ```
 
 ---
@@ -123,52 +138,52 @@ sourcecode version
 
 ```bash
 # High-signal summary — warm cache: ~0.3s, cold: 2–10s depending on repo size
-sourcecode --compact
+ask --compact
 
 # Add git hotspots and uncommitted file count
-sourcecode --compact --git-context
+ask --compact --git-context
 
 # Structured output for AI agents — bounded, noise-free, ready to inject
-sourcecode --agent
+ask --agent
 
 # Blast radius: what breaks if this class changes?
-sourcecode impact OrderService /path/to/repo
+ask impact OrderService /path/to/repo
 
 # Spring Boot 2→3 migration readiness: javax→jakarta blockers, removed APIs
-sourcecode migrate-check /path/to/repo
+ask migrate-check /path/to/repo
 
 # Spring semantic audit: TX anomalies + security surface (free)
-sourcecode spring-audit /path/to/repo
+ask spring-audit /path/to/repo
 
 # Impact chain: systemic blast radius with TX/SEC enrichment (free)
-sourcecode impact-chain OrderService /path/to/repo
+ask impact-chain OrderService /path/to/repo
 
 # Event topology: publisher → event → consumer graph (free)
-sourcecode impact-chain OrderPlacedEvent /path/to/repo --type events
+ask impact-chain OrderPlacedEvent /path/to/repo --type events
 
 # REST endpoint surface
-sourcecode endpoints /path/to/repo
+ask endpoints /path/to/repo
 
 # Request-body validation per endpoint: constraints + custom validators (free)
 # Recovers constraints from the OpenAPI spec, or directly from Java DTO
 # bean-validation annotations when no spec is present.
-sourcecode validation /path/to/repo
+ask validation /path/to/repo
 
 # Onboard to an unfamiliar codebase
-sourcecode onboard /path/to/repo
+ask onboard /path/to/repo
 
 # PR review: risk, test gaps, changed modules
-sourcecode review-pr /path/to/repo --since main
+ask review-pr /path/to/repo --since main
 
 # Bug triage: risk-ranked files by symptom
-sourcecode fix-bug /path/to/repo --symptom "NullPointerException in checkout"
+ask fix-bug /path/to/repo --symptom "NullPointerException in checkout"
 ```
 
 ---
 
 ## Cache system
 
-sourcecode maintains a persistent cache at `.sourcecode-cache/` inside each repository. Two layers:
+ASK Engine maintains a persistent cache at `.sourcecode-cache/` inside each repository. Two layers:
 
 - **L1 (core):** analysis result keyed by `(git_sha, analysis_flags)`. Survives format changes — you can regenerate `--compact` vs `--agent` views from the same core.
 - **L2 (view):** rendered output keyed by `(core_hash, view_flags)`. Exact output match — no recomputation.
@@ -179,21 +194,21 @@ sourcecode maintains a persistent cache at `.sourcecode-cache/` inside each repo
 
 ```bash
 # Inspect cache state
-sourcecode cache status
+ask cache status
 
 # Warm the cache ahead of an agent session
-sourcecode cache warm
+ask cache warm
 
 # Clear cache
-sourcecode cache clear
+ask cache clear
 
 # Check RIS freshness relative to current git HEAD
-sourcecode cache freshness
+ask cache freshness
 ```
 
 **`--no-cache`** bypasses both layers and forces a fresh scan. Use in CI or when you need to verify a fresh result.
 
-**Visibility:** Cache hits are silent. Use `sourcecode cache status` to see cache size, hit keys, and last-warmed timestamp.
+**Visibility:** Cache hits are silent. Use `ask cache status` to see cache size, hit keys, and last-warmed timestamp.
 
 ---
 
@@ -203,75 +218,75 @@ sourcecode cache freshness
 
 ```bash
 # Inject as first message to agent (bounded, deterministic)
-sourcecode /repo --compact              # ~2,500–4,000 tokens
-sourcecode /repo --agent               # ~4,500–5,500 tokens — more detail
-sourcecode onboard /repo               # task-structured: entry points, key files, gaps
+ask /repo --compact              # ~2,500–4,000 tokens
+ask /repo --agent               # ~4,500–5,500 tokens — more detail
+ask onboard /repo               # task-structured: entry points, key files, gaps
 ```
 
 ### Before every change — blast radius + TX/SEC check
 
 ```bash
 # Always target the INTERFACE in Spring projects, not the implementation:
-sourcecode impact OrderService /repo           # ✓ 30 callers, 11 endpoints
-sourcecode impact OrderServiceImpl /repo       # ✗ 0 callers (Spring DI blindness)
+ask impact OrderService /repo           # ✓ 30 callers, 11 endpoints
+ask impact OrderServiceImpl /repo       # ✗ 0 callers (Spring DI blindness)
 
 # Impact chain: blast radius enriched with TX boundary and security surfaces
-sourcecode impact-chain OrderService /repo
+ask impact-chain OrderService /repo
 
 # Event topology: who publishes/consumes this event, and in what TX phase?
-sourcecode impact-chain OrderPlacedEvent /repo --type events
+ask impact-chain OrderPlacedEvent /repo --type events
 
 # Spring audit: catch TX anomalies before they hit production
-sourcecode spring-audit /repo --scope tx
+ask spring-audit /repo --scope tx
 ```
 
 ### Continuous agent loop — delta context
 
 ```bash
 # Only changed files + their transitive importers — minimal token cost:
-sourcecode prepare-context delta /repo --since HEAD~1
-sourcecode . --changed-only --git-context
+ask prepare-context delta /repo --since HEAD~1
+ask . --changed-only --git-context
 ```
 
 ### PR review — structured risk signal
 
 ```bash
 # JSON for programmatic use:
-sourcecode review-pr /repo --since main --output review.json
+ask review-pr /repo --since main --output review.json
 jq '.ci_decision' review.json    # "analysis_success" | "git_ref_error"
 
 # Markdown for GitHub comment:
-sourcecode review-pr /repo --since main --format github-comment
+ask review-pr /repo --since main --format github-comment
 ```
 
 ### Bug triage — symptom-driven
 
 ```bash
 # Specific symptoms produce the best signal:
-sourcecode fix-bug /repo --symptom "OIDC token refresh fails after realm update"
-sourcecode fix-bug /repo --symptom "NullPointerException in OrderService during checkout"
+ask fix-bug /repo --symptom "OIDC token refresh fails after realm update"
+ask fix-bug /repo --symptom "NullPointerException in OrderService during checkout"
 
 # Generic symptoms produce noisy output — be specific.
-sourcecode fix-bug /repo --symptom "payment timeout" --output triage.json
+ask fix-bug /repo --symptom "payment timeout" --output triage.json
 ```
 
 ### In CI — cached, deterministic, fast
 
 ```bash
 # Content-hash cached — safe to run on every commit; cold only when code changes
-sourcecode /repo --compact --output context.json
+ask /repo --compact --output context.json
 
 # PR gate
-sourcecode review-pr /repo --since $BASE_REF --output review.json
+ask review-pr /repo --since $BASE_REF --output review.json
 DECISION=$(jq -r '.ci_decision' review.json)
 if [ "$DECISION" != "analysis_success" ]; then echo "Review failed: $DECISION"; fi
 ```
 
 ---
 
-## What sourcecode does (and doesn't)
+## What ASK Engine does (and doesn't)
 
-**sourcecode reduces exploration cost.** It accelerates context acquisition and minimizes repeated repo parsing. It does not replace reading code — it reduces how often an agent needs to.
+**ASK Engine reduces exploration cost.** It accelerates context acquisition and minimizes repeated repo parsing. It does not replace reading code — it reduces how often an agent needs to.
 
 Specifically:
 
@@ -317,10 +332,10 @@ when the work gets bigger or automated.
 | Offline, no data egress, no account | ✅ | ✅ |
 
 **Non-Java repos are free at any size** — the size limit counts Java source
-files only, by design. sourcecode monetises enterprise Java monoliths.
+files only, by design. ASK Engine monetises enterprise Java monoliths.
 
 ```bash
-sourcecode activate <key>      # activate a license key
+ask activate <key>      # activate a license key
 ```
 
 Full breakdown: [docs/PRODUCT_TIERS.md](docs/PRODUCT_TIERS.md).
@@ -341,9 +356,9 @@ Core flags. Feed directly to AI agents as first-message context.
 ### `impact` — blast-radius analysis  [free ≤500 Java files · Pro above]
 
 ```bash
-sourcecode impact ClassName /path/to/repo
-sourcecode impact org.example.OrderService /path/to/repo   # FQN also accepted
-sourcecode impact OrderService . --depth 2                 # limit BFS depth
+ask impact ClassName /path/to/repo
+ask impact org.example.OrderService /path/to/repo   # FQN also accepted
+ask impact OrderService . --depth 2                 # limit BFS depth
 ```
 
 | Field | Description |
@@ -368,9 +383,9 @@ sourcecode impact OrderService . --depth 2                 # limit BFS depth
 ### `endpoints` — REST API surface
 
 ```bash
-sourcecode endpoints /path/to/repo
-sourcecode endpoints /path/to/repo --output endpoints.json
-sourcecode endpoints /path/to/repo --by-controller
+ask endpoints /path/to/repo
+ask endpoints /path/to/repo --output endpoints.json
+ask endpoints /path/to/repo --by-controller
 ```
 
 Extracts all Spring MVC (`@GetMapping`, `@PostMapping`, `@RequestMapping`, etc.) and JAX-RS (`@GET`, `@POST`, `@Path`) endpoint methods. Returns HTTP method, path, controller class, and handler method. Each endpoint also carries its `return_type`. `--by-controller` groups the surface per controller (`{by_controller, controller_count, total}`) for an API-surface view.
@@ -399,10 +414,10 @@ Matching endpoints then report `policy: "custom"` with `annotation`, `resourceNa
 ### `export` — architecture views for downstream tooling
 
 ```bash
-sourcecode export /path/to/repo --by-directory      # code map, path:line refs
-sourcecode export /path/to/repo --module-graph       # module→module dependencies
-sourcecode export /path/to/repo --integrations       # outbound HTTP/LDAP/JMS clients
-sourcecode export /path/to/repo --c4                  # unified architecture + manifest
+ask export /path/to/repo --by-directory      # code map, path:line refs
+ask export /path/to/repo --module-graph       # module→module dependencies
+ask export /path/to/repo --integrations       # outbound HTTP/LDAP/JMS clients
+ask export /path/to/repo --c4                  # unified architecture + manifest
 ```
 
 Emits **structured, tool-agnostic** codebase views as plain JSON/YAML — the kind of input an architecture-doc generator, diagram renderer, or code-search agent can consume directly instead of walking the tree file by file. Section labels map to the open [C4 model](https://c4model.com) (an open architecture notation, not a product); the schema is vendor-neutral.
@@ -419,15 +434,15 @@ The section flags compose (pass several for one multi-section document); `--c4`
 ### `spring-audit` — Spring semantic audit [free]
 
 ```bash
-sourcecode spring-audit /path/to/repo
-sourcecode spring-audit /path/to/repo --scope tx           # TX anomalies only
-sourcecode spring-audit /path/to/repo --scope security     # security surface only
-sourcecode spring-audit /path/to/repo --min-severity high
+ask spring-audit /path/to/repo
+ask spring-audit /path/to/repo --scope tx           # TX anomalies only
+ask spring-audit /path/to/repo --scope security     # security surface only
+ask spring-audit /path/to/repo --min-severity high
 
 # CI/CD gate: exit 1 on any finding
-sourcecode spring-audit . --ci
-sourcecode spring-audit . --ci --min-severity high         # exit 1 only on high/critical
-sourcecode spring-audit . --ci --format github-comment     # Markdown output + exit 1
+ask spring-audit . --ci
+ask spring-audit . --ci --min-severity high         # exit 1 only on high/critical
+ask spring-audit . --ci --format github-comment     # Markdown output + exit 1
 ```
 
 Detects structural Spring anomalies that survive code review and tests, but cause production failures:
@@ -450,9 +465,9 @@ Endpoints guarded by a project-specific authorization annotation are treated as
 ### `impact-chain` — systemic blast radius with TX/SEC enrichment [free]
 
 ```bash
-sourcecode impact-chain OrderService /path/to/repo
-sourcecode impact-chain com.example.OrderService#placeOrder /path/to/repo
-sourcecode impact-chain PaymentService . --depth 6
+ask impact-chain OrderService /path/to/repo
+ask impact-chain com.example.OrderService#placeOrder /path/to/repo
+ask impact-chain PaymentService . --depth 6
 ```
 
 Unlike `impact` (which traces the caller graph), `impact-chain` builds on the SpringSemanticModel to enrich every step of the blast cone with transaction and security context:
@@ -479,7 +494,7 @@ Unlike `impact` (which traces the caller graph), `impact-chain` builds on the Sp
 **Event topology** — query the publisher/consumer graph for a Spring event class:
 
 ```bash
-sourcecode impact-chain OrderPlacedEvent /path/to/repo --type events
+ask impact-chain OrderPlacedEvent /path/to/repo --type events
 ```
 
 | Field | Description |
@@ -499,8 +514,8 @@ sourcecode impact-chain OrderPlacedEvent /path/to/repo --type events
 ### `cold-start` — RIS bootstrap context
 
 ```bash
-sourcecode cold-start /path/to/repo
-sourcecode cold-start /path/to/repo --compact   # ~10K token subset
+ask cold-start /path/to/repo
+ask cold-start /path/to/repo --compact   # ~10K token subset
 ```
 
 Returns the Repository Intelligence Snapshot (RIS) instantly — zero re-analysis. The RIS is built by a prior warm cache pass and includes stacks, entry points, endpoint surface, and Spring semantic signals. Status field: `cold_start_ready` | `cold_start_stale` | `no_ris`.
@@ -510,12 +525,12 @@ Use `--compact` to get a ~10K token subset safe for direct LLM injection. Full s
 ### `repo-ir` — symbol-level IR
 
 ```bash
-sourcecode repo-ir /path/to/repo --summary-only                  # ~20K tokens
-sourcecode repo-ir /path/to/repo --since HEAD~1                   # symbol-level diff
-sourcecode repo-ir /path/to/repo --files src/.../OrderService.java
-sourcecode repo-ir /path/to/repo --max-nodes 200 --max-edges 500  # limit graph size
-sourcecode repo-ir /path/to/repo --output ir.json.gz --gzip       # compressed output (~70-80% smaller)
-sourcecode repo-ir /path/to/repo --include-tests                   # include test files
+ask repo-ir /path/to/repo --summary-only                  # ~20K tokens
+ask repo-ir /path/to/repo --since HEAD~1                   # symbol-level diff
+ask repo-ir /path/to/repo --files src/.../OrderService.java
+ask repo-ir /path/to/repo --max-nodes 200 --max-edges 500  # limit graph size
+ask repo-ir /path/to/repo --output ir.json.gz --gzip       # compressed output (~70-80% smaller)
+ask repo-ir /path/to/repo --include-tests                   # include test files
 ```
 
 Builds a deterministic symbol graph: classes, methods, import/injection edges, Spring roles, subsystems.
@@ -536,9 +551,9 @@ Builds a deterministic symbol graph: classes, methods, import/injection edges, S
 ### `explain` — architectural summary for a class
 
 ```bash
-sourcecode explain UserService
-sourcecode explain OrderController /path/to/repo
-sourcecode explain UserService --format json
+ask explain UserService
+ask explain OrderController /path/to/repo
+ask explain UserService --format json
 ```
 
 Human-readable architectural summary derived entirely from static analysis: Spring stereotype, public methods, incoming callers, outgoing dependencies, events published/consumed, `@Transactional` boundaries, security constraints, and related REST endpoints. JAVA/SPRING ONLY.
@@ -546,8 +561,8 @@ Human-readable architectural summary derived entirely from static analysis: Spri
 ### `pr-impact` — PR blast-radius report
 
 ```bash
-sourcecode pr-impact --files changed_files.txt
-sourcecode pr-impact /path/to/repo --files diff.txt --format json
+ask pr-impact --files changed_files.txt
+ask pr-impact /path/to/repo --files diff.txt --format json
 ```
 
 Takes a file listing changed Java files (one path per line) and produces a consolidated report: modified classes, affected REST endpoints reachable through the call chain, direct callers of each changed class, event publishers/consumers triggered, `@Transactional` methods in changed classes, and a consolidated risk level (`CRITICAL` / `HIGH` / `MEDIUM` / `LOW`). JAVA/SPRING ONLY.
@@ -555,13 +570,13 @@ Takes a file listing changed Java files (one path per line) and produces a conso
 ```bash
 # Typical CI usage: pipe git diff to a file, then run
 git diff --name-only main | grep '\.java$' > changed.txt
-sourcecode pr-impact . --files changed.txt --format json
+ask pr-impact . --files changed.txt --format json
 ```
 
 ### `onboard` — codebase orientation
 
 ```bash
-sourcecode onboard /path/to/repo
+ask onboard /path/to/repo
 ```
 
 Entry points, architecture summary, key files, confidence level, and gaps. Designed to be injected as agent context at the start of a session.
@@ -569,8 +584,8 @@ Entry points, architecture summary, key files, confidence level, and gaps. Desig
 ### `review-pr` — PR review context  [free ≤500 Java files · Pro above]
 
 ```bash
-sourcecode review-pr /path/to/repo --since main
-sourcecode review-pr /path/to/repo --since HEAD~3
+ask review-pr /path/to/repo --since main
+ask review-pr /path/to/repo --since HEAD~3
 ```
 
 Changed files, risk ranking, test coverage gaps, affected modules, and blast radius of changed classes. Returns a `ci_decision` field for CI/CD integration.
@@ -578,7 +593,7 @@ Changed files, risk ranking, test coverage gaps, affected modules, and blast rad
 ### `fix-bug` — Bug triage context  [free ≤500 Java files · Pro above]
 
 ```bash
-sourcecode fix-bug /path/to/repo --symptom "NullPointerException in checkout"
+ask fix-bug /path/to/repo --symptom "NullPointerException in checkout"
 ```
 
 Risk-ranked file list correlated to the symptom: keyword extraction, path matching, content matching, git commit correlation.
@@ -586,7 +601,7 @@ Risk-ranked file list correlated to the symptom: keyword extraction, path matchi
 ### `modernize` — Modernization planning  [free ≤500 Java files · Pro above]
 
 ```bash
-sourcecode modernize /path/to/repo
+ask modernize /path/to/repo
 ```
 
 High-coupling nodes (high fan-in = risky to change), dead zone candidates (isolated symbols), subsystem tangles.
@@ -594,10 +609,10 @@ High-coupling nodes (high fan-in = risky to change), dead zone candidates (isola
 ### `migrate-check` — Spring Boot 2→3 migration readiness
 
 ```bash
-sourcecode migrate-check /path/to/repo
-sourcecode migrate-check . --min-severity high
-sourcecode migrate-check . --format text
-sourcecode migrate-check . --output migration.json
+ask migrate-check /path/to/repo
+ask migrate-check . --min-severity high
+ask migrate-check . --format text
+ask migrate-check . --output migration.json
 ```
 
 Detects migration blockers across Java source files, Spring XML config files, and Maven/Gradle build files. 27 rules organized by target:
@@ -774,19 +789,19 @@ evidence. `migrate-check` enforces:
 
 ```bash
 # inspect only the Hibernate rewrite targets
-sourcecode migrate-check . --format json | jq '.hibernate.rewrite_targets[]'
+ask migrate-check . --format json | jq '.hibernate.rewrite_targets[]'
 
 # product blockers only (excludes test/fixtures + hygiene)
-sourcecode migrate-check . --format json | jq '.blocking_count, .non_blocking, .hygiene_findings'
+ask migrate-check . --format json | jq '.blocking_count, .non_blocking, .hygiene_findings'
 ```
 
 ### `rename-class` — Java class rename
 
 ```bash
-sourcecode rename-class . --from ServiceA --to ServiceB
-sourcecode rename-class /path/to/repo --from OrderManager --to OrderService
-sourcecode rename-class . --from OldName --to NewName --dry-run
-sourcecode rename-class . --from OldName --to NewName --no-tests   # src/main only
+ask rename-class . --from ServiceA --to ServiceB
+ask rename-class /path/to/repo --from OrderManager --to OrderService
+ask rename-class . --from OldName --to NewName --dry-run
+ask rename-class . --from OldName --to NewName --no-tests   # src/main only
 ```
 
 Renames a Java class safely throughout the repository: declaration, constructor, all import statements, type references (fields, params, return types), `extends`/`implements`, generics, casts, and Spring `@Qualifier` names. Renames the physical `.java` file. Emits a structured change audit trail (`file`, `before_lines`, `after_lines`, `intent`, `diff`).
@@ -796,10 +811,10 @@ Use `--dry-run` to preview changes without writing to disk.
 ### `chunk-file` — split large Java files for agent consumption
 
 ```bash
-sourcecode chunk-file BigService.java
-sourcecode chunk-file BigService.java --max-lines 300
-sourcecode chunk-file BigService.java --chunk 5          # read chunk 5 only
-sourcecode chunk-file BigService.java --metadata-only    # boundaries only, no content
+ask chunk-file BigService.java
+ask chunk-file BigService.java --max-lines 300
+ask chunk-file BigService.java --chunk 5          # read chunk 5 only
+ask chunk-file BigService.java --metadata-only    # boundaries only, no content
 ```
 
 Splits a large Java file at method/class boundaries so AI agents can read files with 10K–25K+ lines in context-sized pieces. Each chunk includes `chunk_id`, `start_line`, `end_line`, `chunk_type`, symbol name, a `context_header` (package + class + imports summary), and `content`. A `size_warning` flag marks methods that exceed `--max-lines` and cannot be split further.
@@ -809,7 +824,7 @@ Splits a large Java file at method/class boundaries so AI agents can read files
 Low-level access to all tasks with full options:
 
 ```bash
-sourcecode prepare-context TASK [PATH] [OPTIONS]
+ask prepare-context TASK [PATH] [OPTIONS]
 ```
 
 | Task | What it surfaces |
@@ -868,9 +883,9 @@ All outputs include:
 Anonymous, **on by default (opt-out)**. Collects: version, OS, commands, flags, duration, repo size range, errors. No source code, paths, secrets, or output content. A one-time notice is shown on first interactive run.
 
 ```bash
-sourcecode telemetry status
-sourcecode telemetry enable
-sourcecode telemetry disable
+ask telemetry status
+ask telemetry enable
+ask telemetry disable
 ```
 
 Disable any time: `export SOURCECODE_TELEMETRY=0` (or `DO_NOT_TRACK=1`)
@@ -880,7 +895,7 @@ Disable any time: `export SOURCECODE_TELEMETRY=0` (or `DO_NOT_TRACK=1`)
 ## Configuration
 
 ```bash
-sourcecode config    # show version, config file path, telemetry status
+ask config    # show version, config file path, telemetry status
 ```
 
 ### `sourcecode.config.json` (repo root)