Skip to content

Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.

release: v0.45.0 (#1823)

Raghav Chamadiyae2bb8a2e4eff
diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
index 807b922d6..b11313243 100644
--- a/.claude-plugin/marketplace.json
+++ b/.claude-plugin/marketplace.json
@@ -14,7 +14,7 @@
"name": "repowise",
"source": "./plugins/claude-code",
"description": "Codebase intelligence for Claude Code. Indexes your repo into five layers (Graph, Git, Docs, Decisions, Code Health) and gives Claude deep understanding of architecture, ownership, hotspots, decisions, and defect risk — fewer greps, fewer file reads, lower cost per query.",
- "version": "0.44.0",
+ "version": "0.45.0",
"category": "productivity",
"keywords": [
"codebase",
diff --git a/docs/CHANGELOG.md b/docs/CHANGELOG.md
index 06c889e4c..07bec013e 100644
--- a/docs/CHANGELOG.md
+++ b/docs/CHANGELOG.md
@@ -9,21 +9,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
---
-## [Unreleased]
+## [0.45.0] — 2026-08-21
-### Added
+The headline this cycle is test intelligence that needs no coverage report. 0.44.0 made the call graph good enough to lead with; this release walks it to answer which tests reach a file, serves that through the API, and turns the Coverage tab into a Tests tab that says something useful on a repository that has never ingested a report. Around it, Code Health's performance findings become bounded opportunities that open the matching refactoring plan, Eden AI joins as an EU-hosted provider and embedder, and pinning BLAS threads before numpy loads halves peak memory on a cold index.
-- **Code Health performance opportunities now lead into the existing
- Refactoring workflow.** A dedicated Performance tab groups raw findings into
- bounded causal opportunities with production/tooling versus test context,
- affected-call-site totals, confidence, provenance paths, and raw-evidence
- paging. Exact stable opportunity ids open matching `performance_fix` plans;
- opportunities without a safe plan say so instead of selecting a nearby one.
- The Refactoring page adds a Performance filter and shared priority,
- validation, path, and pagination renderers. Its new server-owned page endpoint
- bounds initial payloads while preserving the legacy unpaged route. VS Code
- consumes the same contracts and renders priority and validation without web
- dependencies; older missing optional fields remain supported.
+### Added
- **A test-to-code map that needs no coverage report.** The per-test map only
ever existed if you ingested a coverage report with contexts, so on most
@@ -51,8 +41,45 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
`get_change_risk`'s `impacted_tests`, and a `via` marker on every
`repowise impacted-tests` candidate saying which tier answered.
+- **Code Health performance opportunities now lead into the existing
+ Refactoring workflow.** A dedicated Performance tab groups raw findings into
+ bounded causal opportunities with production/tooling versus test context,
+ affected-call-site totals, confidence, provenance paths, and raw-evidence
+ paging. Exact stable opportunity ids open matching `performance_fix` plans;
+ opportunities without a safe plan say so instead of selecting a nearby one.
+ The Refactoring page adds a Performance filter and shared priority,
+ validation, path, and pagination renderers. Its new server-owned page endpoint
+ bounds initial payloads while preserving the legacy unpaged route. VS Code
+ consumes the same contracts and renders priority and validation without web
+ dependencies; older missing optional fields remain supported.
+
+- **`/health/tests-reaching?file_path=`** answers which tests reach one file,
+ with `via` separating a test whose calls run into it from one that only imports
+ it, and `/health/coverage` falls back to the inferred map under
+ `basis: "inferred"` when no report was ingested. The two bases never share a
+ field, so a consumer cannot render derived data through the measured code path
+ by accident. `include_inferred=false` declines the fallback for a caller that
+ only wants the cheap badge number. (#1757)
+
+- **Eden AI is a first-class LLM provider and embedder.** An EU-headquartered
+ gateway exposing 700+ models behind an OpenAI-compatible endpoint, so it reuses
+ the existing `openai` dependency with a custom base URL and adds no new one.
+ `EDENAI_API_KEY`, `EDENAI_BASE_URL` for the EU endpoint, and an embedder
+ defaulting to a 1024-dimension EU model. It is appended to the autodetect order
+ rather than inserted, so an unrelated key in the environment cannot move anyone
+ off the provider they were already resolving to. (#705)
+
### Changed
+- **The Coverage tab is now a Tests tab, and it answers without a report.** The
+ URL stays `/coverage` and "coverage" keeps meaning the measured thing inside
+ the tab; what changed is that the empty state no longer tells you to go
+ ingest a report while claiming nothing is inferred. On the inferred basis the
+ chart collapses to two positions rather than a 0-100 continuum, which is the
+ honest statement about the evidence, and nothing is rendered as a percentage
+ or a bar. The file page names the tests that reach it, with `via` separating a
+ test whose calls run into the file from one that only imports it. (#1758)
+
- **`untested_hotspot` stops accusing files that the tests run.** With no
coverage ingested it fired on any hotspot without a *paired test file*, which
is a filename convention, so a suite that names its tests for behaviour
@@ -78,6 +105,124 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
old name described the wrong thing; each entry carries `via` (`call-graph`,
`import-graph` or `filename-pattern`) to say which tier answered.
+- **Refactoring recommendations have one contract.** REST, MCP and the CLI each
+ rebuilt their own ranking and payload shape, and the TypeScript contract was
+ duplicated in the UI package. The wire contract moves to
+ `@repowise-dev/types` and the Python side gets a single read model owning
+ rehydration, enrichment, ranking, validation and serialization for every
+ surface. Blast radius now raises cost and risk rather than benefit, so a wide
+ change ranks as expensive instead of valuable. (#1784)
+
+- **The semantic leg of search gets a budget the cold path can clear.** The first
+ vector query in a process pays for the store open, the first embed and the
+ first ANN probe. That was measured at 6.3s and 13.4s on a cold Windows index
+ where a warm query takes 0.19s, against a hardcoded 8s bound inside a
+ suppressed exception. The budget is now one shared 30s default, capped at 120s and
+ overridable with `REPOWISE_VECTOR_SEARCH_TIMEOUT_S`, and a timeout logs a
+ warning naming the knob instead of silently degrading to full-text with
+ nothing said. (#1678, #1685)
+
+- **Plugin**: `/repowise:impacted-tests` and the `change-review` skill describe
+ the inferred map as the call graph with an import-graph fallback, and `init` /
+ `reindex` list the embedders the CLI actually accepts.
+
+- **Execution-graph analysis is unified** behind one code path in health, with
+ the legacy call fallback restricted rather than left answering alongside it.
+ (#1773)
+
+### Fixed
+
+- **An incremental update stopped erasing ingested coverage.** The incremental
+ pipeline built its analyzer without a coverage map, so every changed file was
+ re-scored as if no report had ever been ingested and the partial-health writer
+ upserted `line_coverage_pct` back to NULL, eroding coverage one file per
+ update, starting with the files under active development. Both callers now load
+ and supply the persisted map. (#1739, #1806)
+- **`repowise init` no longer crashes in a git worktree.** `.git` is a file
+ there, not a directory, so building `.git/hooks` by hand raised
+ `NotADirectoryError` and took the whole command down. The hooks directory is
+ resolved with `git rev-parse --git-path hooks`, which answers correctly for a
+ worktree and a normal clone alike. (#1609, #1808)
+- **The CLI and the MCP server resolve the same embedder key.** The server never
+ consulted the process environment, so on a machine with an exported provider
+ key different from the repository's `.repowise/.env`, semantic search degraded
+ through the CLI while the MCP tool answered. The server now reads the env tier
+ first, matching the CLI's "an exported key is an explicit override" contract.
+ (#1711, #1810)
+- **`edenai` is selectable everywhere it is documented**: `init --embedder`,
+ `reindex --embedder`, both interactive prompts, `EDENAI_API_KEY` autodetection
+ and the server's embedder build, four lists that were left on the older
+ five-backend set. (#1815, #1820)
+- **`repowise reindex` exits non-zero when every embed failed**, so an automated
+ pipeline cannot treat an empty vector index as a successful build. An empty
+ wiki still exits 0. (#1495, #1732)
+- **The file page states how many tests reach a file, not how many it listed.**
+ The list is capped at 50 and the page rendered that cap as the measurement; it
+ now leads with the true count and says what it is showing. (#1764)
+- **A generated-file banner has to be a banner.** The marker is required within
+ the first two lines instead of substring-matched across the whole header, which
+ fixes the class of prose false positives across all six markers. (#1519, #1731)
+- **Python resolution**: `from pkg import submodule` pinned the binding at the
+ package `__init__.py`, so a later `submodule.symbol()` call resolved against a
+ file declaring nothing and dead code called the symbol safe to delete (#1193,
+ #1733); aliased submodule bindings are pinned properly (#1255, #1785).
+- **Go**: a call through a field (`a.b.Method()`) matched no pattern and was
+ missing from the graph entirely rather than present and unresolved (#1727), and
+ an embed of `io.Reader` keeps its package qualifier instead of binding to
+ whatever repo-local `Reader` shares the short name, which made the type
+ inherit from itself when the enclosing type had that name (#1726).
+- **TypeScript**: `#private` class members produce a symbol and a call site
+ (#1715, #1721), a return type no longer renders with a stray colon
+ (`-> : string`) (#1695, #1719), and a relative import probes `index.tsx` and
+ `index.jsx` (#1725).
+- **Java and C# method return types are preserved** in signatures (#1713).
+- **The bare-name tier stops answering for the standard library** (#1708), and
+ barrel-file definitions are aligned with `file_reachability` (#1491, #1557).
+- **The paired-test filename heuristic is shared** rather than reimplemented per
+ surface (#1750).
+- **Security scanning**: `replace_findings` no longer loses rows on a duplicate
+ key (#1523), and a multi-line `subprocess.*(... shell=True)` call is flagged
+ (#1522).
+- **Agent CLIs no longer load the target repository's instruction files** when
+ invoked for generation (#1100).
+- **`workspace init --dry-run` writes nothing** (#1526), and `init --test-run`
+ actually limits generation to the top 10 files (#1525).
+- **`share_of_repo_gap_pct` uses the gross gap as its denominator** (#1452), and
+ history fetches avoid the partial-clone path (#1608).
+- **The `get_risk` artifact renders in chat.** The renderer mapped over a list
+ and read `path` / `churn_percentile`, but the tool returns a path-keyed dict of
+ `hotspot_score` / `file_path`, so opening the artifact threw or showed blank
+ rows. Both shapes are normalized, and the 0-1 score is scaled for display
+ rather than printed as though it were already a percentage. (#1480)
+
+### Performance
+
+- **Peak memory on a cold index is roughly halved.** Importing numpy brings up a
+ BLAS runtime that commits a private per-thread workspace sized to the host's
+ core count: 746 MB on a 32-core machine for the import alone, committed once,
+ never returned, and invisible to `tracemalloc` because no Python object owns
+ it. The pipeline's only numpy work is PageRank over a sparse graph, which runs
+ single-threaded in well under a second, so the thread count is pinned before
+ numpy is imported. A cold `init --no-prose` on an 876-file repository went from
+ 1,547 MB to 818 MB at no wall-clock cost. `OMP_NUM_THREADS` is deliberately
+ left alone: igraph community detection really is OpenMP-parallel, and pinning
+ it cost 18% wall clock for no further saving. (#1394, #1776)
+
+### Documentation
+
+- **A roadmap, an enterprise section, and a benchmarks page that leads with its
+ results.** `ROADMAP.md` is new and states plainly that language support is
+ never gated behind the licence; the README gains a real enterprise section
+ covering deployment, data boundary, compliance and contract; `BENCHMARKS.md`
+ goes from 777 visible lines to 456 with every caveat and every losing row
+ preserved behind folds. Language support is now stated the same way in every
+ document: 19 parsed to a full AST, 35 on the ladder. Source control beyond git
+ (Perforce, Subversion, and the mainframe promotion hierarchies) is scoped to
+ the one history-derived layer that actually needs it. (#1766)
+- **The graph precision result is published**, judged by a compiler across five
+ tools (#1738), and `COMMERCIAL.md`'s tool count matches the way the document
+ counts (#1771).
+
---
## [0.44.0] — 2026-08-18
diff --git a/packages/cli/src/repowise/cli/__init__.py b/packages/cli/src/repowise/cli/__init__.py
index 73c2feff4..bb3cd822a 100644
--- a/packages/cli/src/repowise/cli/__init__.py
+++ b/packages/cli/src/repowise/cli/__init__.py
@@ -16,4 +16,4 @@ from repowise.cli._stdio import _ensure_utf8_stdio
# is already UTF-8.
_ensure_utf8_stdio()
-__version__ = "0.44.0"
+__version__ = "0.45.0"
diff --git a/packages/cli/src/repowise/cli/agent_targets/_data/codex_prompts/repowise-init.md b/packages/cli/src/repowise/cli/agent_targets/_data/codex_prompts/repowise-init.md
index 0af30b418..1461b0951 100644
--- a/packages/cli/src/repowise/cli/agent_targets/_data/codex_prompts/repowise-init.md
+++ b/packages/cli/src/repowise/cli/agent_targets/_data/codex_prompts/repowise-init.md
@@ -79,7 +79,8 @@ Core flags:
--mode fast Quick first pass on very large repos: no wiki at all.
Embeddings:
- --embedder NAME Embedding provider: gemini, openai, mock (default: auto-detect)
+ --embedder NAME Embedding provider: gemini, openai, openrouter, ollama,
+ edenai, mock (default: auto-detect)
Cost control:
--concurrency N Max parallel LLM calls (default: 10)
diff --git a/packages/cli/src/repowise/cli/agent_targets/_data/codex_prompts/repowise-reindex.md b/packages/cli/src/repowise/cli/agent_targets/_data/codex_prompts/repowise-reindex.md
index 829f30169..57496e788 100644
--- a/packages/cli/src/repowise/cli/agent_targets/_data/codex_prompts/repowise-reindex.md
+++ b/packages/cli/src/repowise/cli/agent_targets/_data/codex_prompts/repowise-reindex.md
@@ -21,12 +21,12 @@ This is useful when:
## Available flags
-- `--embedder gemini|openai|auto` — embedding provider (default: auto-detect from env vars)
+- `--embedder gemini|openai|openrouter|ollama|edenai|auto` — embedding provider (default: auto-detect from env vars)
- `--batch-size N` — pages per embedding batch (default: 20)
## Requirements
-Requires either `GEMINI_API_KEY`/`GOOGLE_API_KEY` or `OPENAI_API_KEY` to be set. The mock embedder is not accepted for reindexing. If neither key is available, ask the user to set one before proceeding.
+Requires a key for one of the real embedders — `GEMINI_API_KEY`/`GOOGLE_API_KEY`, `OPENAI_API_KEY`, `OPENROUTER_API_KEY` or `EDENAI_API_KEY` — or a running Ollama. The mock embedder is not accepted for reindexing. If none is available, ask the user to set one before proceeding.
## Handling $ARGUMENTS
diff --git a/packages/core/src/repowise/core/__init__.py b/packages/core/src/repowise/core/__init__.py
index 9550a972e..d84206c4e 100644
--- a/packages/core/src/repowise/core/__init__.py
+++ b/packages/core/src/repowise/core/__init__.py
@@ -6,4 +6,4 @@ generation engine. This is the heart of repowise — all other packages depend o
Namespace package: repowise.core is part of the repowise namespace.
"""
-__version__ = "0.44.0"
+__version__ = "0.45.0"
diff --git a/packages/core/src/repowise/core/upgrade/_data/CHANGELOG.md b/packages/core/src/repowise/core/upgrade/_data/CHANGELOG.md
index 06c889e4c..07bec013e 100644
--- a/packages/core/src/repowise/core/upgrade/_data/CHANGELOG.md
+++ b/packages/core/src/repowise/core/upgrade/_data/CHANGELOG.md
@@ -9,21 +9,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
---
-## [Unreleased]
+## [0.45.0] — 2026-08-21
-### Added
+The headline this cycle is test intelligence that needs no coverage report. 0.44.0 made the call graph good enough to lead with; this release walks it to answer which tests reach a file, serves that through the API, and turns the Coverage tab into a Tests tab that says something useful on a repository that has never ingested a report. Around it, Code Health's performance findings become bounded opportunities that open the matching refactoring plan, Eden AI joins as an EU-hosted provider and embedder, and pinning BLAS threads before numpy loads halves peak memory on a cold index.
-- **Code Health performance opportunities now lead into the existing
- Refactoring workflow.** A dedicated Performance tab groups raw findings into
- bounded causal opportunities with production/tooling versus test context,
- affected-call-site totals, confidence, provenance paths, and raw-evidence
- paging. Exact stable opportunity ids open matching `performance_fix` plans;
- opportunities without a safe plan say so instead of selecting a nearby one.
- The Refactoring page adds a Performance filter and shared priority,
- validation, path, and pagination renderers. Its new server-owned page endpoint
- bounds initial payloads while preserving the legacy unpaged route. VS Code
- consumes the same contracts and renders priority and validation without web
- dependencies; older missing optional fields remain supported.
+### Added
- **A test-to-code map that needs no coverage report.** The per-test map only
ever existed if you ingested a coverage report with contexts, so on most
@@ -51,8 +41,45 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
`get_change_risk`'s `impacted_tests`, and a `via` marker on every
`repowise impacted-tests` candidate saying which tier answered.
+- **Code Health performance opportunities now lead into the existing
+ Refactoring workflow.** A dedicated Performance tab groups raw findings into
+ bounded causal opportunities with production/tooling versus test context,
+ affected-call-site totals, confidence, provenance paths, and raw-evidence
+ paging. Exact stable opportunity ids open matching `performance_fix` plans;
+ opportunities without a safe plan say so instead of selecting a nearby one.
+ The Refactoring page adds a Performance filter and shared priority,
+ validation, path, and pagination renderers. Its new server-owned page endpoint
+ bounds initial payloads while preserving the legacy unpaged route. VS Code
+ consumes the same contracts and renders priority and validation without web
+ dependencies; older missing optional fields remain supported.
+
+- **`/health/tests-reaching?file_path=`** answers which tests reach one file,
+ with `via` separating a test whose calls run into it from one that only imports
+ it, and `/health/coverage` falls back to the inferred map under
+ `basis: "inferred"` when no report was ingested. The two bases never share a
+ field, so a consumer cannot render derived data through the measured code path
+ by accident. `include_inferred=false` declines the fallback for a caller that
+ only wants the cheap badge number. (#1757)
+
+- **Eden AI is a first-class LLM provider and embedder.** An EU-headquartered
+ gateway exposing 700+ models behind an OpenAI-compatible endpoint, so it reuses
+ the existing `openai` dependency with a custom base URL and adds no new one.
+ `EDENAI_API_KEY`, `EDENAI_BASE_URL` for the EU endpoint, and an embedder
+ defaulting to a 1024-dimension EU model. It is appended to the autodetect order
+ rather than inserted, so an unrelated key in the environment cannot move anyone
+ off the provider they were already resolving to. (#705)
+
### Changed
+- **The Coverage tab is now a Tests tab, and it answers without a report.** The
+ URL stays `/coverage` and "coverage" keeps meaning the measured thing inside
+ the tab; what changed is that the empty state no longer tells you to go
+ ingest a report while claiming nothing is inferred. On the inferred basis the
+ chart collapses to two positions rather than a 0-100 continuum, which is the
+ honest statement about the evidence, and nothing is rendered as a percentage
+ or a bar. The file page names the tests that reach it, with `via` separating a
+ test whose calls run into the file from one that only imports it. (#1758)
+
- **`untested_hotspot` stops accusing files that the tests run.** With no
coverage ingested it fired on any hotspot without a *paired test file*, which
is a filename convention, so a suite that names its tests for behaviour
@@ -78,6 +105,124 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
old name described the wrong thing; each entry carries `via` (`call-graph`,
`import-graph` or `filename-pattern`) to say which tier answered.
+- **Refactoring recommendations have one contract.** REST, MCP and the CLI each
+ rebuilt their own ranking and payload shape, and the TypeScript contract was
+ duplicated in the UI package. The wire contract moves to
+ `@repowise-dev/types` and the Python side gets a single read model owning
+ rehydration, enrichment, ranking, validation and serialization for every
+ surface. Blast radius now raises cost and risk rather than benefit, so a wide
+ change ranks as expensive instead of valuable. (#1784)
+
+- **The semantic leg of search gets a budget the cold path can clear.** The first
+ vector query in a process pays for the store open, the first embed and the
+ first ANN probe. That was measured at 6.3s and 13.4s on a cold Windows index
+ where a warm query takes 0.19s, against a hardcoded 8s bound inside a
+ suppressed exception. The budget is now one shared 30s default, capped at 120s and
+ overridable with `REPOWISE_VECTOR_SEARCH_TIMEOUT_S`, and a timeout logs a
+ warning naming the knob instead of silently degrading to full-text with
+ nothing said. (#1678, #1685)
+
+- **Plugin**: `/repowise:impacted-tests` and the `change-review` skill describe
+ the inferred map as the call graph with an import-graph fallback, and `init` /
+ `reindex` list the embedders the CLI actually accepts.
+
+- **Execution-graph analysis is unified** behind one code path in health, with
+ the legacy call fallback restricted rather than left answering alongside it.
+ (#1773)
+
+### Fixed
+
+- **An incremental update stopped erasing ingested coverage.** The incremental
+ pipeline built its analyzer without a coverage map, so every changed file was
+ re-scored as if no report had ever been ingested and the partial-health writer
+ upserted `line_coverage_pct` back to NULL, eroding coverage one file per
+ update, starting with the files under active development. Both callers now load
+ and supply the persisted map. (#1739, #1806)
+- **`repowise init` no longer crashes in a git worktree.** `.git` is a file
+ there, not a directory, so building `.git/hooks` by hand raised
+ `NotADirectoryError` and took the whole command down. The hooks directory is
+ resolved with `git rev-parse --git-path hooks`, which answers correctly for a
+ worktree and a normal clone alike. (#1609, #1808)
+- **The CLI and the MCP server resolve the same embedder key.** The server never
+ consulted the process environment, so on a machine with an exported provider
+ key different from the repository's `.repowise/.env`, semantic search degraded
+ through the CLI while the MCP tool answered. The server now reads the env tier
+ first, matching the CLI's "an exported key is an explicit override" contract.
+ (#1711, #1810)
+- **`edenai` is selectable everywhere it is documented**: `init --embedder`,
+ `reindex --embedder`, both interactive prompts, `EDENAI_API_KEY` autodetection
+ and the server's embedder build, four lists that were left on the older
+ five-backend set. (#1815, #1820)
+- **`repowise reindex` exits non-zero when every embed failed**, so an automated
+ pipeline cannot treat an empty vector index as a successful build. An empty
+ wiki still exits 0. (#1495, #1732)
+- **The file page states how many tests reach a file, not how many it listed.**
+ The list is capped at 50 and the page rendered that cap as the measurement; it
+ now leads with the true count and says what it is showing. (#1764)
+- **A generated-file banner has to be a banner.** The marker is required within
+ the first two lines instead of substring-matched across the whole header, which
+ fixes the class of prose false positives across all six markers. (#1519, #1731)
+- **Python resolution**: `from pkg import submodule` pinned the binding at the
+ package `__init__.py`, so a later `submodule.symbol()` call resolved against a
+ file declaring nothing and dead code called the symbol safe to delete (#1193,
+ #1733); aliased submodule bindings are pinned properly (#1255, #1785).
+- **Go**: a call through a field (`a.b.Method()`) matched no pattern and was
+ missing from the graph entirely rather than present and unresolved (#1727), and
+ an embed of `io.Reader` keeps its package qualifier instead of binding to
+ whatever repo-local `Reader` shares the short name, which made the type
+ inherit from itself when the enclosing type had that name (#1726).
+- **TypeScript**: `#private` class members produce a symbol and a call site
+ (#1715, #1721), a return type no longer renders with a stray colon
+ (`-> : string`) (#1695, #1719), and a relative import probes `index.tsx` and
+ `index.jsx` (#1725).
+- **Java and C# method return types are preserved** in signatures (#1713).
+- **The bare-name tier stops answering for the standard library** (#1708), and
+ barrel-file definitions are aligned with `file_reachability` (#1491, #1557).
+- **The paired-test filename heuristic is shared** rather than reimplemented per
+ surface (#1750).
+- **Security scanning**: `replace_findings` no longer loses rows on a duplicate
+ key (#1523), and a multi-line `subprocess.*(... shell=True)` call is flagged
+ (#1522).
+- **Agent CLIs no longer load the target repository's instruction files** when
+ invoked for generation (#1100).
+- **`workspace init --dry-run` writes nothing** (#1526), and `init --test-run`
+ actually limits generation to the top 10 files (#1525).
+- **`share_of_repo_gap_pct` uses the gross gap as its denominator** (#1452), and
+ history fetches avoid the partial-clone path (#1608).
+- **The `get_risk` artifact renders in chat.** The renderer mapped over a list
+ and read `path` / `churn_percentile`, but the tool returns a path-keyed dict of
+ `hotspot_score` / `file_path`, so opening the artifact threw or showed blank
+ rows. Both shapes are normalized, and the 0-1 score is scaled for display
+ rather than printed as though it were already a percentage. (#1480)
+
+### Performance
+
+- **Peak memory on a cold index is roughly halved.** Importing numpy brings up a
+ BLAS runtime that commits a private per-thread workspace sized to the host's
+ core count: 746 MB on a 32-core machine for the import alone, committed once,
+ never returned, and invisible to `tracemalloc` because no Python object owns
+ it. The pipeline's only numpy work is PageRank over a sparse graph, which runs
+ single-threaded in well under a second, so the thread count is pinned before
+ numpy is imported. A cold `init --no-prose` on an 876-file repository went from
+ 1,547 MB to 818 MB at no wall-clock cost. `OMP_NUM_THREADS` is deliberately
+ left alone: igraph community detection really is OpenMP-parallel, and pinning
+ it cost 18% wall clock for no further saving. (#1394, #1776)
+
+### Documentation
+
+- **A roadmap, an enterprise section, and a benchmarks page that leads with its
+ results.** `ROADMAP.md` is new and states plainly that language support is
+ never gated behind the licence; the README gains a real enterprise section
+ covering deployment, data boundary, compliance and contract; `BENCHMARKS.md`
+ goes from 777 visible lines to 456 with every caveat and every losing row
+ preserved behind folds. Language support is now stated the same way in every
+ document: 19 parsed to a full AST, 35 on the ladder. Source control beyond git
+ (Perforce, Subversion, and the mainframe promotion hierarchies) is scoped to
+ the one history-derived layer that actually needs it. (#1766)
+- **The graph precision result is published**, judged by a compiler across five
+ tools (#1738), and `COMMERCIAL.md`'s tool count matches the way the document
+ counts (#1771).
+
---
## [0.44.0] — 2026-08-18
diff --git a/packages/server/src/repowise/server/__init__.py b/packages/server/src/repowise/server/__init__.py
index e7a2de1a0..b5ed6a21b 100644
--- a/packages/server/src/repowise/server/__init__.py
+++ b/packages/server/src/repowise/server/__init__.py
@@ -7,4 +7,4 @@ Provides:
- Background job scheduler (APScheduler)
"""
-__version__ = "0.44.0"
+__version__ = "0.45.0"
diff --git a/plugins/claude-code/.claude-plugin/plugin.json b/plugins/claude-code/.claude-plugin/plugin.json
index 51c12599a..d68b71666 100644
--- a/plugins/claude-code/.claude-plugin/plugin.json
+++ b/plugins/claude-code/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
{
"name": "repowise",
"description": "Codebase intelligence for Claude Code. Indexes your codebase into five layers (Graph, Git, Docs, Decisions, Code Health) and exposes them through eleven task-shaped MCP tools — so Claude understands architecture, ownership, hotspots, why code is built the way it is, and where the defect risk lives.",
- "version": "0.44.0",
+ "version": "0.45.0",
"author": {
"name": "Repowise",
"email": "[email protected]",
diff --git a/plugins/claude-code/CHANGELOG.md b/plugins/claude-code/CHANGELOG.md
index cfe2d03f1..2b4fb8e2d 100644
--- a/plugins/claude-code/CHANGELOG.md
+++ b/plugins/claude-code/CHANGELOG.md
@@ -2,6 +2,22 @@
All notable changes to the Repowise Claude Code plugin are documented here.
+## 0.45.0
+
+### Changed
+- `/repowise:impacted-tests` and the `change-review` skill describe the map as
+ it now works: with no coverage ingested the candidates come from the call
+ graph, with the import graph filling in only where it is silent, and every
+ candidate carries the `via` marker saying which tier answered. Only
+ `via: coverage` proves a test executed the change (#1749, #1755, #1757).
+- `/repowise:init` and `/repowise:reindex` list the embedders the CLI actually
+ accepts - `gemini`, `openai`, `openrouter`, `ollama`, `edenai` - rather than
+ the three-name set they had drifted to, and name the keys that resolve them
+ (#705, #1820).
+- No hook or MCP tool surface change this cycle: `hooks.json` still mirrors
+ `claude_config.py` and every tool named in a command or skill is one the
+ server lists.
+
## 0.44.0
### Changed
diff --git a/plugins/claude-code/commands/init.md b/plugins/claude-code/commands/init.md
index 3c0c339c6..c1d73e9ff 100644
--- a/plugins/claude-code/commands/init.md
+++ b/plugins/claude-code/commands/init.md
@@ -80,7 +80,8 @@ Core flags:
--mode fast Quick first pass on very large repos: no wiki at all.
Embeddings:
- --embedder NAME Embedding provider: gemini, openai, mock (default: auto-detect)
+ --embedder NAME Embedding provider: gemini, openai, openrouter, ollama,
+ edenai, mock (default: auto-detect)
Cost control:
--concurrency N Max parallel LLM calls (default: 10)
diff --git a/plugins/claude-code/commands/reindex.md b/plugins/claude-code/commands/reindex.md
index 0497d9dc0..1b93f1523 100644
--- a/plugins/claude-code/commands/reindex.md
+++ b/plugins/claude-code/commands/reindex.md
@@ -22,12 +22,12 @@ This is useful when:
## Available flags
-- `--embedder gemini|openai|auto` — embedding provider (default: auto-detect from env vars)
+- `--embedder gemini|openai|openrouter|ollama|edenai|auto` — embedding provider (default: auto-detect from env vars)
- `--batch-size N` — pages per embedding batch (default: 20)
## Requirements
-Requires either `GEMINI_API_KEY`/`GOOGLE_API_KEY` or `OPENAI_API_KEY` to be set. The mock embedder is not accepted for reindexing. If neither key is available, ask the user to set one before proceeding.
+Requires a key for one of the real embedders — `GEMINI_API_KEY`/`GOOGLE_API_KEY`, `OPENAI_API_KEY`, `OPENROUTER_API_KEY` or `EDENAI_API_KEY` — or a running Ollama. The mock embedder is not accepted for reindexing. If none is available, ask the user to set one before proceeding.
## Handling $ARGUMENTS
diff --git a/plugins/claude-code/skills/change-review/SKILL.md b/plugins/claude-code/skills/change-review/SKILL.md
index e4532a49d..848d28e64 100644
--- a/plugins/claude-code/skills/change-review/SKILL.md
+++ b/plugins/claude-code/skills/change-review/SKILL.md
@@ -65,9 +65,9 @@ The response carries a `directive` block — read it first, it's a few short lis
exercise the changed files. Recommend running these to validate the change.
Read **`tests_to_run_basis`** with it: `measured` means a coverage map proves
those tests execute the changed files (pytest-runnable ids); `inferred` means
- the import graph shows those test *files* reaching the change, which needs no
- coverage ingest but is a candidate list, so say so rather than presenting it as
- proof; `none` with an empty list is "unknown", never "no tests exist".
+ the call graph shows those test *files* reaching the change, with the import
+ graph filling in where it is silent, which needs no coverage ingest but is a
+ candidate list, so say so rather than presenting it as proof; `none` with an empty list is "unknown", never "no tests exist".
`pr_blast_radius` holds the fuller dossier behind those lists (including the
per-changed-file `guarding_tests` breakdown behind `tests_to_run`).
diff --git a/plugins/codex/.codex-plugin/plugin.json b/plugins/codex/.codex-plugin/plugin.json
index 3939b216f..0ecee1458 100644
--- a/plugins/codex/.codex-plugin/plugin.json
+++ b/plugins/codex/.codex-plugin/plugin.json
@@ -1,6 +1,6 @@
{
"name": "codex",
- "version": "0.6.0",
+ "version": "0.6.1",
"description": "Repowise codebase intelligence for Codex.",
"author": {
"name": "Repowise",
diff --git a/plugins/codex/skills/change-review/SKILL.md b/plugins/codex/skills/change-review/SKILL.md
index 191ca037b..1bd02dcdd 100644
--- a/plugins/codex/skills/change-review/SKILL.md
+++ b/plugins/codex/skills/change-review/SKILL.md
@@ -60,9 +60,9 @@ The response carries a `directive` block — read it first, it's a few short lis
exercise the changed files. Recommend running these to validate the change.
Read **`tests_to_run_basis`** with it: `measured` means a coverage map proves
those tests execute the changed files (pytest-runnable ids); `inferred` means
- the import graph shows those test *files* reaching the change, which needs no
- coverage ingest but is a candidate list, so say so rather than presenting it as
- proof; `none` with an empty list is "unknown", never "no tests exist".
+ the call graph shows those test *files* reaching the change, with the import
+ graph filling in where it is silent, which needs no coverage ingest but is a
+ candidate list, so say so rather than presenting it as proof; `none` with an empty list is "unknown", never "no tests exist".
`pr_blast_radius` holds the fuller dossier behind those lists (including the
per-changed-file `guarding_tests` breakdown behind `tests_to_run`).
diff --git a/plugins/shared/commands/init.md b/plugins/shared/commands/init.md
index ddb074188..1d3a8cb67 100644
--- a/plugins/shared/commands/init.md
+++ b/plugins/shared/commands/init.md
@@ -81,7 +81,8 @@ Core flags:
--mode fast Quick first pass on very large repos: no wiki at all.
Embeddings:
- --embedder NAME Embedding provider: gemini, openai, mock (default: auto-detect)
+ --embedder NAME Embedding provider: gemini, openai, openrouter, ollama,
+ edenai, mock (default: auto-detect)
Cost control:
--concurrency N Max parallel LLM calls (default: 10)
diff --git a/plugins/shared/commands/reindex.md b/plugins/shared/commands/reindex.md
index e7cb865f9..d1304a27c 100644
--- a/plugins/shared/commands/reindex.md
+++ b/plugins/shared/commands/reindex.md
@@ -23,12 +23,12 @@ This is useful when:
## Available flags
-- `--embedder gemini|openai|auto` — embedding provider (default: auto-detect from env vars)
+- `--embedder gemini|openai|openrouter|ollama|edenai|auto` — embedding provider (default: auto-detect from env vars)
- `--batch-size N` — pages per embedding batch (default: 20)
## Requirements
-Requires either `GEMINI_API_KEY`/`GOOGLE_API_KEY` or `OPENAI_API_KEY` to be set. The mock embedder is not accepted for reindexing. If neither key is available, ask the user to set one before proceeding.
+Requires a key for one of the real embedders — `GEMINI_API_KEY`/`GOOGLE_API_KEY`, `OPENAI_API_KEY`, `OPENROUTER_API_KEY` or `EDENAI_API_KEY` — or a running Ollama. The mock embedder is not accepted for reindexing. If none is available, ask the user to set one before proceeding.
## Handling $ARGUMENTS
diff --git a/plugins/shared/skills/change-review.md b/plugins/shared/skills/change-review.md
index de7adbb14..4af5b0032 100644
--- a/plugins/shared/skills/change-review.md
+++ b/plugins/shared/skills/change-review.md
@@ -73,9 +73,9 @@ The response carries a `directive` block — read it first, it's a few short lis
exercise the changed files. Recommend running these to validate the change.
Read **`tests_to_run_basis`** with it: `measured` means a coverage map proves
those tests execute the changed files (pytest-runnable ids); `inferred` means
- the import graph shows those test *files* reaching the change, which needs no
- coverage ingest but is a candidate list, so say so rather than presenting it as
- proof; `none` with an empty list is "unknown", never "no tests exist".
+ the call graph shows those test *files* reaching the change, with the import
+ graph filling in where it is silent, which needs no coverage ingest but is a
+ candidate list, so say so rather than presenting it as proof; `none` with an empty list is "unknown", never "no tests exist".
`pr_blast_radius` holds the fuller dossier behind those lists (including the
per-changed-file `guarding_tests` breakdown behind `tests_to_run`).
diff --git a/pyproject.toml b/pyproject.toml
index 2b6906f98..23ff15122 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
[project]
name = "repowise"
-version = "0.44.0"
+version = "0.45.0"
description = "The codebase intelligence layer for your AI coding agent — dependency graph, git history, dead code, decisions, and code health, exposed over MCP"
readme = "README.md"
requires-python = ">=3.11"
diff --git a/server.json b/server.json
index 9675d043d..0601658e6 100644
--- a/server.json
+++ b/server.json
@@ -8,12 +8,12 @@
"source": "github"
},
"websiteUrl": "https://www.repowise.dev",
- "version": "0.44.0",
+ "version": "0.45.0",
"packages": [
{
"registryType": "pypi",
"identifier": "repowise",
- "version": "0.44.0",
+ "version": "0.45.0",
"transport": {
"type": "stdio"
},
diff --git a/uv.lock b/uv.lock
index b06598cde..d8da74782 100644
--- a/uv.lock
+++ b/uv.lock
@@ -3051,7 +3051,7 @@ wheels = [
[[package]]
name = "repowise"
-version = "0.44.0"
+version = "0.45.0"
source = { editable = "." }
dependencies = [
{ name = "aiosqlite" },