Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Python aicode-complexitycode-healthcode-intelligencecode-qualitydead-codedeveloper-toolsdocumentationgit-analyticsmcpopen-sourcepythonrefactoringstatic-analysistechnical-debt
release: v0.52.0 — documentation drift, honest savings, and test quality in code health (#2474)
Raghav Chamadiyad12892606055
diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.jsonindex e56ae2c6c..6f3b3d8de 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": "0.51.0",+ "version": "0.52.0","category": "productivity","keywords": ["codebase",diff --git a/docs/CHANGELOG.md b/docs/CHANGELOG.mdindex c872307a2..f30df82f1 100644--- a/docs/CHANGELOG.md+++ b/docs/CHANGELOG.md@@ -9,6 +9,74 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0---+## [0.52.0] - 2026-09-20++A wide cycle. Documentation makes assertions about code, and this repository has the graph to check them, so a fourth deterministic analysis joins the pipeline: it reads the repository's own markdown, extracts the claims each document makes, resolves them against the real tree, and reports the ones the tree refutes. No model is involved, findings refresh on every update, and the reverse view answers which documents name a given file.++Savings accounting was badly wrong, and wrong in the direction of reporting far less than was actually saved. Nothing wrote pricing onto a canonical event, so a report over that ledger valued real savings at $0.00, and the readers that avoided it repriced all of history at whatever model the newest session used. Two counterfactual estimators still described a tool that no longer exists, so the tools they covered recorded themselves as a net cost on nearly every call. Each event is priced from its own evidence now, and the API, the overview and the CLI agree. The figure remains a deliberate floor: where the evidence is ambiguous it declines to claim a saving rather than estimating one, so the real number is very likely higher than the one shown.++The pages that tell you where to look were rebuilt. The overview's attention list read three detectors because those were the three that existed when it was written, while code-health findings, security, documentation drift and refactoring plans sat on a tab; they are one list now. The costs page stopped being a stack of nested cards at one visual weight. A commit sheet that could say how big a change was, but not whether it made anything worse, reports the health delta and leads with where the change lands rather than with a percentile it then explains.++Code health can see test quality for the first time — a test that checks nothing, a test that is mostly mock setup — with a per-language assertion vocabulary underneath, since the old rule counted 87 assertions across a 502-test-file Go repository. Decisions stop claiming what they cannot support: a ruling from a record nobody accepted, governance over every file in the commit a decision was mined from, transcript working agreements stored as though the codebase had decided them. And a long precision pass lands on Rust, C#, Go, Objective-C, Swift, Java and TypeScript extraction.++### Added++- **Documentation drift, a fourth deterministic analysis** (#2290, #2307, #2313, #2356, #2370, #2378). The pass reads the repository's markdown, extracts the claims each document makes about the tree, resolves them against the graph, and files a finding for each claim the tree refutes. Findings are refreshed on every `update`, not only on a clean index. They surface in the CLI, in `get_health`, and on a Code Health tab backed by a router, a canonical wire contract and shared view components. `get_context(include=["doc_drift"])` answers the reverse question — which documents name this file, where in each, and whether those documents carry drift of their own — from the references that resolved. A finding opens its own evidence: the line as the document wrote it, the heading trail locating the passage, and what the resolver checked, all of which previously arrived with the finding and was discarded.+- **An agent can be asked to record the choice it just committed** (#2465). The layer's first write-side hook. After a successful `git commit`, a PostToolUse hook offers the `decision add` line and says what to put in it. Off unless the repository turns it on (`decisions.capture_prompt`; no preset sets it); at most once per session; only on `git commit`, never a merge or a rebase; only on a message carrying two or more decision signals — measured over 137 commits, one keyword admits 58% of them and two admits 25%; and never for a commit a record already cites, with an unreadable store counting as cited so the failure mode is silence. It proposes only: nothing is recorded unless the agent runs the command, and what it records lands as a candidate for review, never as a rule.+- **A working agreement is told apart from a decision about the code** (#2405, #2451). "Never commit to main" is a rule about how work is conducted; "`get_why` never calls an LLM" is a claim about the code that a diff can violate. Only the second can be checked against files, and the first could not be accepted at all, because acceptance requires a scope and a repo-wide rule names none. They are separate kinds now, and a measured capture tier can deliver an agreement without an acceptance.+- **A commit says what it did to code health** (#2459, #2463). `GitCommit` stores which files each commit touched, so a per-commit surface no longer shells out to git and a server with no checkout can answer at all. On top of that, the commit sheet reports the health delta a change produced — the base-versus-head comparison that previously needed both sides of every changed file and a working tree.+- **Test quality is measured** (#2317, #2358, #2371, #2393, #2399, #2419, #2436). `assertion_free_test` flags a test case whose assertion and verification counts are both zero — Meszaros's Unknown Test, and the one test-quality marker with a yes-or-no answer rather than a threshold. `mock_saturated_test` measures how much of a test is mock setup, advisory and unweighted on purpose: no defect corpus labels mock density, so weighting it would move a number that claims to predict bugs using evidence that says nothing about bugs. Java is recorded as blocked after measurement rather than guessed at. Underneath both, assertions are counted with a per-language vocabulary instead of the `assert`/`expect` prefix pair, a called helper's assertions reach the caller that delegates to it, and a test's oracle is found wherever it sits in a multi-item `with` header.+- **One attention list on the overview** (#2429). "Needs attention" read decision health, knowledge silos and dead code, because those were the three detectors that existed when it was written. Code-health findings, security, documentation drift and refactoring plans lived on a tab and never reached the page whose job is to say where to look.+- **One composed change review** (#2273, #2274, #2281). Risk scoring, the health delta, contract impact, test impact, independent grouping and branch overlap each had one owner, and every surface composed them itself and reached its own conclusions from the same facts. A versioned `ChangeReviewBundle` and one `ChangeReviewService` compose them once, so a second surface cannot disagree with the first, and the expensive comparison can be handed in already computed rather than forcing a caller to choose between the shared composition and its own concurrency. It is documented for programs that want the whole review as one object, without a checkout.+- **Canonical savings accounting** (#2248, #2401, #2440). Three surfaces recorded savings and each answered the same three questions its own way — which database to open, whether to create one that is missing, and what to do when the write fails. One canonical event per logical interaction replaces agreement by hand.+- **Rust bodiless function declarations are symbols** (#2382). `fn foo();` parses as `function_signature_item`, and `rust.scm` had no pattern for that node anywhere. Two shapes were invisible to the symbol graph: a trait's undefaulted methods — the trait's entire contract, everything an implementor must supply — and every `extern "C"` declaration.+- **An embedding model's width can be declared without sending dimensions** (#1857), and local-endpoint MCP budgets are configurable (#1856).++### Changed++- **A decision record is keyed, scoped and promoted on evidence** (#2425, #2426, #2434, #2439, #2441). Identity keys on the record's body, file set and quote rather than on a model-generated title. A commit's file list stops doubling as the governance binding: for a record mined from a commit it is the provenance of the change, which is true, but as scope it was mostly false, since the `pr` and `git_archaeology` miners read one decision out of one commit body and then took that commit's entire file list. The miner is asked which files a commit's decision is actually about. The governing-scope cutoff drops from ten files to five: ten was chosen by looking at a labelled sample and then scored on that same sample, and the first out-of-sample measurement put it at 49% on topic with 26% outright noise, against the 54% baseline the scope work set out to fix. A candidate is promoted for stating a reason rather than for being seen twice.+- **Acceptance requires a reason, and records what signed it** (#2279, #2445, #2457, #2458). The contract read the reason as `rationale` and fell through to `decision`, so a record whose only content restated its own title passed the "no rationale" check — the what stood in for the why. Separately, the identity check was satisfied by any non-blank string and the accepter resolver fell through to `git config user.name`, so an agent accepting a decision signed the maintainer's name into the audit log and nothing downstream could tell the two apart. `CLAUDE.md` and `AGENTS.md` now say when a standing decision was not signed by a person, since an agent reads that block as instructions.+- **Session transcript mining is off unless asked for** (#2286, #2387, #2395). A decision mined from a transcript took its scope from whatever files the surrounding tool calls named, and a transcript names plenty that is not this codebase — scratch scripts, plan documents, files belonging to a checkout sitting beside this one. Over staged candidates on a real machine only 24.7% of the bound paths were files the index holds, and 64.5% of rows carried a list in which nothing resolved at all. Codex transcripts are scoped to the repository that owns them; both raw-line gates had dropped the `session_meta` line carrying the working directory, so every Codex event read as having no opinion rather than as a miss.+- **Decision confidence accounts for what a record states** (#2328). Confidence read source rank, corroboration and verification but never whether the record said anything, so the ranking ran backwards: records filling one body field averaged 0.845 against 0.776 for records filling five, with 65.2% of ordered pairs inverted. Scaling the rank-earned credit by how much an extracted record states takes the inversion rate to 12.9% and makes the table monotonic.+- **`get_change_risk` reports what a change wrote, not what it weighs** (#2452). A census of 135 recorded calls from Claude Code and Codex, 118 of them real engineering use, found the tool spending its payload on signals no agent acted on and burying the ones they did.+- **The commit sheet leads with where a change lands** (#2453, #2455). It opened on a percentile and then spent its body explaining the number it had just printed — three of its four blocks were commentary about the model, and it never named a file. The queue's chips filter the repository now instead of the loaded page: risk order returns the top tercile first, so all 50 loaded rows were already "high", the chips read "All (50), High priority (50)", and clicking High priority removed nothing. On this repository the real figures are 911 / 302 / 458.+- **The costs page is an evidence-led scan surface** (#2432). It was a stack of nested cards at one visual weight throughout. A card should mean "an object you can act on", and a savings total is not that, so the boxes carried no information while removing the page's hierarchy.+- **MCP responses stop repeating themselves** (#2272, #2284, #2456). The canonical index scope is about 900 characters and rode on every response — roughly a third of a small `get_symbol` reply, spent answering a question almost no call asks. A diagnostic that ships with every answer is a tax rather than a disclosure, so a digest rides instead and the full scope is one call away. It is also parsed once per index state rather than re-reading `state.json` and re-parsing `config.yaml` on every call. Four further fields, each rebuildable from the row it shipped beside or from the key it sat under, are gone.+- **`timing_ms` is reported for every tool** (#2271), rather than for the ones someone had remembered to thread it through.+- **History-based health gates are ranked against the repository** (#2437, #2438). Six months is a fixed window, so a repository landing many commits a day accumulates more fix commits per file inside it than a quiet one; with an entry gate of one fix, `prior_defect` fired on 43.5% of the files here, and a signal that flags nearly half a tree is not locating anything. Co-change breadth is measured before truncation rather than by counting a list capped at 25 partners, where above the cap every file looks identical.+- **An agent is defined once** (#2394). The same agent was spelled four ways across four hand-maintained namespaces, and the savings domain had added a fifth and a sixth that agreed with the target registry only by hand.++### Fixed++- **`get_why` stops claiming a ruling the store does not hold** (#2280, #2282, #2322). A record is a candidate until a `DecisionAcceptance` row exists, and accepting is a deliberate manual step, so a store of nothing but candidates is the state of every repository whose maintainer has not worked through the acceptance UI. Separately, neither path-mode call shape declared its lanes as requested, so the shared response budget shed them first and a path query dropped its origin story whole. The health mode names the active, deprecated, superseded, dismissed and unscoped lanes it previously reported as a bare count.+- **A hand-authored decision reaches the surfaces that deliver it** (#2464). `decision add` and the HTTP create route wrote `affected_files_json` and stopped, while the edit-time injection hook, `get_governing_decisions` and the `get_risk` directives all read `decision_node_links`, which only the mining pipeline ever wrote. A record added by hand had files and no links, so nothing could deliver it.+- **`get_risk` stops answering an unresolved target with a confident zero** (#2321). A `module:` id, a bare directory, an unindexed path and a typo all fell through to the same card, every numeric field of which was a structural zero. Measured here, a subsystem directory returned `dependents_count: 0` while a single file inside it returned 59, so a subsystem nothing could safely be changed in read as safe to change. The directory is the dangerous form, because it looks like an ordinary target.+- **`get_context`'s `used_by` keys on the symbol, not on its file** (#2329). The query joined the edge target against the symbol's file path, but every symbol-level edge is emitted symbol-to-symbol with a `path::Name` target, so calls, references, extends, implements, method_implements, dispatches_to, framework_binds and reads could none of them ever match. The field answered "who imports this symbol's file" under a name that promises otherwise.+- **`get_symbol(depth=3)` serves the hops it found** (#2285), and a requested projection is kept ahead of the ones a caller did not ask for (#2270) — `get_overview(include=["outline"])` returned 0 of 40 outline sections while leaving 73% of its budget unspent.+- **A `.tsx` file is read with the JSX grammar** (#2398). It arrives tagged `typescript`, and that grammar fails on the first `<Component />`; everything after it landed in error recovery, so the health pass was reading a tree that does not describe the file. Assertions after the first element were never counted, the clone detector hashed a token stream recovery had partly invented, and the dataflow CFG was built over the same wreckage.+- **A file's same-named functions survive to the markers that score them** (#2408). Eleven scoring markers read a per-file map keyed by function name, and a function name is not unique inside a file — every `it(...)` callback in a spec file walks under the name `it callback`, and `__init__` walks under one name on each class in a module.+- **Rust graph precision** (#1568, #2362, #2376, #2386, #2409, #2412, #2415, #2418, #2423). Field and type-argument types are recorded as type references, so a struct used only as a field type or nested in `Option<T>` no longer reads as an unused export; Rust reaches an intra-crate field type without a `use` statement, so nothing else recorded the reference. A `pub trait`'s items take the visibility the trait declares instead of `private`, which had left downstream-callable API sitting in the narrow dead-code pool. A trait's defaulted methods are parented to the trait rather than emitted parentless as plain functions. `type_use` captures widen to wrapper shapes, a scoped call binds to its own type rather than the file's last, a re-export through a crate root carries the rest of the path, a trait bound is no longer read as inheritance, a std-library name is refused on the `import_merged` tier, and impl blocks are treated as uncallable and non-importable.+- **C#, Go, Objective-C, Swift, Java, GDScript and TypeScript extraction** (#2309, #2312, #2316, #2318, #2323, #2324, #2330, #2336, #2361, #2363, #2364, #2402, #2414, #2428). C# null-conditional call sites (`a?.Foo()`) are captured — they were not resolved-and-wrong and not unresolved either, but never captured, so nothing downstream knew they existed — and an extension-method call binds to the type it extends, with `builtin_parents` aligned to the shared .NET BCL set. Go functions in composite literals mint reference edges. Objective-C `.h` and `.m` files are paired, and a call-shaped attribute macro trailing a declaration is blanked rather than left to wreck error recovery past the terminating semicolon. A Swift qualified extension no longer names its qualifier as a conformer in its own right. A bare `@Immutable` stops fabricating a generated Java class. TypeScript class fields holding a function are indexed. GDScript `uid://` references resolve through the `.uid` sidecar, and a Godot scene connection resolves to a C# script method. A nested sub-package resolves from its own manifest, an inheritance edge anchors to the child's real symbol id, and inert `reads` membership is retired from `SYMBOL_USE_EDGE_TYPES`.+- **Savings are priced from their own evidence** (#2413, #2461, #2468). Nothing wrote pricing onto a canonical event, so any report over the canonical ledger would have valued real savings at $0.00; the legacy readers avoided that by resolving the coding agent's model at read time and repricing all of history at it, which moved past figures whenever the newest session changed model. Rates are no longer fabricated and stamped as measured, evidence on disk is no longer thrown away, and two counterfactual estimators describing a tool that no longer exists had been recording the tools they cover as a net cost on nearly every call. The API, the overview and the CLI report the same numbers. The reported figure stays a deliberate floor: where the evidence is ambiguous the ledger declines to claim a saving rather than estimating one, so the real figure is very likely higher than the one shown.+- **`distill` runs a wrapped command in the shell it was written for** (#2448). `_POSIX_HOST = os.name == "posix"` gated both the metacharacter bail and safe-chain recognition, so on a Windows host `cd X && git diff` from an agent's Bash tool was refused before classification ever ran. Measured over 30 days on one machine: 2,203 commands bypassed distillation, worth 738,123 tokens, and that one gate explains 97.5% of them.+- **Secret values are masked in security finding snippets** (#2375), `provider_config` is stored `0600`, and keys are redacted in the validate response (#1798).+- **CORS is browser-compliant and configurable by environment** (#1793), and repository paths are passed to local CLI providers (#2242).+- **A configured database is treated as a store** by `update` (#2404) and `delete` (#2338). Both guarded on the repo-local `wiki.db` file before building an engine from `resolve_db_url`; under a shared database that file is absent by design, so the guard returned before the engine was ever built.+- **`init --force` in a worktree is no longer a paid upgrade** (#2339), MCP tool updates route to the workspace repository database (#2241), and a missing workspace repository can be removed from the UI (#2253).+- **A whole prompt is recorded as input tokens** (#2337). Claude Code splits one prompt across three disjoint usage fields, and only `input_tokens` — the uncached remainder — was persisted, so a roughly 20k-token module page recorded `input_tokens=2` and `status` summed a whole wiki to almost nothing.+- **DeepSeek and Kimi are priced** (#1790) rather than $0 in both the estimator and the live tracker, and `codex_cli` subprocess concurrency is configurable (#2334).+- **The root layout's repository list is not prerendered** (#2260, #2261). `/settings` and `not-found` are static routes, so `next build` prerendered them where no API answers and baked "can't reach the API" into their payloads; since layouts do not re-render on soft navigation, the sidebar then stayed wrong on a healthy server.+- **`total_pages` is zero when a phase reports no total** (#2308), a formatter comment stops prescribing `ruff format` (#2444), the no-index MCP guidance names the capability rather than one host's tool names (#2326), and chat stops suggesting questions no tool can answer (#2315).+- **Decision plumbing** (#2310, #2314, #2357, #2421, #2422, #2447, #2450). Paraphrases are deduplicated at the pass that creates the record, and stored duplicates are folded in one sweep. `last_code_change` is filled from the dates staleness already reads, having held a value on 0 of 357 records. Staged decision paths are stored in a form the index can resolve. A bundled claim is flagged on every capture path rather than on one lane. A starved token budget no longer silently loses whole batches, and one wordy candidate no longer silences its whole lane.+- **The contradiction rate counts rows, not decisions** (#2479). `hook stats` reported 181 followed against 20 contradicted, a 10.0% rate, where all 20 rows were one decision: the verdict was computed per decision and stored per row, so a single match settled every row that decision had ever been shown in. The true rate on that corpus is 0 of 201. Alongside it, a contradiction now requires two-sided evidence rather than a reversal keyword found in either text alone, opposing verbs match as whole words rather than inside longer ones (`use` was matching inside `user`), and injection rows resolve through `decision_aliases` so a re-keyed record no longer reads as gone and drains its rows.+- **A failed HEAD read no longer strands a store's sync pointer** (#2446), a churn rank is published beside the raw churn sum on direct risks (#2443), a zero-impact finding is visible to a surface that ranks nothing (#2430), a shared `warn()` helper unifies the warning stream (#1843), and the credential-masking migration has its own revision (#2462).+- **An MCP session's end is named** (#2283) instead of arriving as EOF, a broken pipe or a cancelled task that were all indistinguishable from a crash — the hang-up escaped as a traceback the host would respawn on, and a clean end produced no line at all.++### Documentation++- The change-review engine is documented for programs that compose it directly (#2281). Contributor guidance makes a claim binding from the moment the comment is posted rather than from assignment, which can lag it by days (#2377), and corrects stale setup steps. The Rust `unused_internal` skip is given its real reason (#2390): the stated one was that the graph emits no intra-file Rust call edges, and it does — same-file calls are the largest single resolution origin in every Rust repository measured, and bare same-file call sites resolve at 97.5% or better.++---## [0.51.0] - 2026-09-16An index makes claims about a repository, and several of them were not being checked. A fast index and a full one described their scope differently in every place that reported it, and a configured cap could be read as achieved coverage. Git history sampling let a file's retained history depend on which of two internal lanes happened to serve it. Pages that fell outside a generation selection could be marked stale and stay stale through every later update, while `doctor` blamed the wrong cause and named a command that could not clear it. An update could call a repository current because its commit had not moved, even when the configuration deciding what to index had changed underneath it. This release makes each of those say what is actually true, and records the coverage a run achieved rather than the coverage it was allowed. Next to that, contract evidence stops depending on whether a handler signature can be recovered from code: a checked-in OpenAPI document is now a provider schema, compared directionally, and local Maven coordinates resolve across a workspace. COBOL is a parsed language.diff --git a/packages/cli/src/repowise/cli/__init__.py b/packages/cli/src/repowise/cli/__init__.pyindex 75508b73f..e63fdf504 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__ = "0.51.0"+__version__ = "0.52.0"diff --git a/packages/cli/src/repowise/cli/agent_targets/_data/codex_prompts/repowise-decision.md b/packages/cli/src/repowise/cli/agent_targets/_data/codex_prompts/repowise-decision.mdindex 60342175b..67ed73f44 100644--- a/packages/cli/src/repowise/cli/agent_targets/_data/codex_prompts/repowise-decision.md+++ b/packages/cli/src/repowise/cli/agent_targets/_data/codex_prompts/repowise-decision.md@@ -4,9 +4,11 @@ description: Work with architectural decisions — list, inspect health, add, or# Repowise Decisions-Repowise captures architectural decisions (the *why* behind the code) from eight-sources and tracks them for staleness and conflicts. This command drives the-`repowise decision` group.+Repowise captures architectural decisions (the *why* behind the code) from+several sources and tracks them for staleness and conflicts. This command drives+the `repowise decision` group. Sources are individually switchable — run+`repowise decision source list` to see which are on; transcript mining is off+unless the repository turns it on.## Steps@@ -28,8 +30,13 @@ sources and tracks them for staleness and conflicts. This command drives the`--title` and `--decision` it records without prompting and prints the id(`--format json` to parse it back), which is the form to use with no terminal.The rest are optional: `--context`, `--rationale`, `--alternative`,- `--consequence`, `--affects`, `--tag`, the last four repeatable. A flag-driven- record lands `proposed` for a person to `confirm`.+ `--consequence`, `--affects`, `--tag`, `--evidence-commit`, the last five+ repeatable. A flag-driven record lands `proposed` for a person to `confirm`.+ **Always state a reason** — pass `--rationale` (or `--context`); a record whose+ body only restates its own title cannot be accepted. `--kind agreement` records+ a working agreement: a rule about how the work is conducted, which names no+ file and is not checked against the code. `--evidence-commit <sha>` ties the+ record to the commit the choice was made in.- **confirm** — `repowise decision confirm` — review decisions auto-proposed fromgit history and accept or reject them.- **deprecate / dismiss** — `repowise decision deprecate <id>` (optionallydiff --git a/packages/core/src/repowise/core/__init__.py b/packages/core/src/repowise/core/__init__.pyindex 7795566a4..789aa60f7 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 oNamespace package: repowise.core is part of the repowise namespace."""-__version__ = "0.51.0"+__version__ = "0.52.0"diff --git a/packages/core/src/repowise/core/upgrade/_data/CHANGELOG.md b/packages/core/src/repowise/core/upgrade/_data/CHANGELOG.mdindex c872307a2..f30df82f1 100644--- a/packages/core/src/repowise/core/upgrade/_data/CHANGELOG.md+++ b/packages/core/src/repowise/core/upgrade/_data/CHANGELOG.md@@ -9,6 +9,74 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0---+## [0.52.0] - 2026-09-20++A wide cycle. Documentation makes assertions about code, and this repository has the graph to check them, so a fourth deterministic analysis joins the pipeline: it reads the repository's own markdown, extracts the claims each document makes, resolves them against the real tree, and reports the ones the tree refutes. No model is involved, findings refresh on every update, and the reverse view answers which documents name a given file.++Savings accounting was badly wrong, and wrong in the direction of reporting far less than was actually saved. Nothing wrote pricing onto a canonical event, so a report over that ledger valued real savings at $0.00, and the readers that avoided it repriced all of history at whatever model the newest session used. Two counterfactual estimators still described a tool that no longer exists, so the tools they covered recorded themselves as a net cost on nearly every call. Each event is priced from its own evidence now, and the API, the overview and the CLI agree. The figure remains a deliberate floor: where the evidence is ambiguous it declines to claim a saving rather than estimating one, so the real number is very likely higher than the one shown.++The pages that tell you where to look were rebuilt. The overview's attention list read three detectors because those were the three that existed when it was written, while code-health findings, security, documentation drift and refactoring plans sat on a tab; they are one list now. The costs page stopped being a stack of nested cards at one visual weight. A commit sheet that could say how big a change was, but not whether it made anything worse, reports the health delta and leads with where the change lands rather than with a percentile it then explains.++Code health can see test quality for the first time — a test that checks nothing, a test that is mostly mock setup — with a per-language assertion vocabulary underneath, since the old rule counted 87 assertions across a 502-test-file Go repository. Decisions stop claiming what they cannot support: a ruling from a record nobody accepted, governance over every file in the commit a decision was mined from, transcript working agreements stored as though the codebase had decided them. And a long precision pass lands on Rust, C#, Go, Objective-C, Swift, Java and TypeScript extraction.++### Added++- **Documentation drift, a fourth deterministic analysis** (#2290, #2307, #2313, #2356, #2370, #2378). The pass reads the repository's markdown, extracts the claims each document makes about the tree, resolves them against the graph, and files a finding for each claim the tree refutes. Findings are refreshed on every `update`, not only on a clean index. They surface in the CLI, in `get_health`, and on a Code Health tab backed by a router, a canonical wire contract and shared view components. `get_context(include=["doc_drift"])` answers the reverse question — which documents name this file, where in each, and whether those documents carry drift of their own — from the references that resolved. A finding opens its own evidence: the line as the document wrote it, the heading trail locating the passage, and what the resolver checked, all of which previously arrived with the finding and was discarded.+- **An agent can be asked to record the choice it just committed** (#2465). The layer's first write-side hook. After a successful `git commit`, a PostToolUse hook offers the `decision add` line and says what to put in it. Off unless the repository turns it on (`decisions.capture_prompt`; no preset sets it); at most once per session; only on `git commit`, never a merge or a rebase; only on a message carrying two or more decision signals — measured over 137 commits, one keyword admits 58% of them and two admits 25%; and never for a commit a record already cites, with an unreadable store counting as cited so the failure mode is silence. It proposes only: nothing is recorded unless the agent runs the command, and what it records lands as a candidate for review, never as a rule.+- **A working agreement is told apart from a decision about the code** (#2405, #2451). "Never commit to main" is a rule about how work is conducted; "`get_why` never calls an LLM" is a claim about the code that a diff can violate. Only the second can be checked against files, and the first could not be accepted at all, because acceptance requires a scope and a repo-wide rule names none. They are separate kinds now, and a measured capture tier can deliver an agreement without an acceptance.+- **A commit says what it did to code health** (#2459, #2463). `GitCommit` stores which files each commit touched, so a per-commit surface no longer shells out to git and a server with no checkout can answer at all. On top of that, the commit sheet reports the health delta a change produced — the base-versus-head comparison that previously needed both sides of every changed file and a working tree.+- **Test quality is measured** (#2317, #2358, #2371, #2393, #2399, #2419, #2436). `assertion_free_test` flags a test case whose assertion and verification counts are both zero — Meszaros's Unknown Test, and the one test-quality marker with a yes-or-no answer rather than a threshold. `mock_saturated_test` measures how much of a test is mock setup, advisory and unweighted on purpose: no defect corpus labels mock density, so weighting it would move a number that claims to predict bugs using evidence that says nothing about bugs. Java is recorded as blocked after measurement rather than guessed at. Underneath both, assertions are counted with a per-language vocabulary instead of the `assert`/`expect` prefix pair, a called helper's assertions reach the caller that delegates to it, and a test's oracle is found wherever it sits in a multi-item `with` header.+- **One attention list on the overview** (#2429). "Needs attention" read decision health, knowledge silos and dead code, because those were the three detectors that existed when it was written. Code-health findings, security, documentation drift and refactoring plans lived on a tab and never reached the page whose job is to say where to look.+- **One composed change review** (#2273, #2274, #2281). Risk scoring, the health delta, contract impact, test impact, independent grouping and branch overlap each had one owner, and every surface composed them itself and reached its own conclusions from the same facts. A versioned `ChangeReviewBundle` and one `ChangeReviewService` compose them once, so a second surface cannot disagree with the first, and the expensive comparison can be handed in already computed rather than forcing a caller to choose between the shared composition and its own concurrency. It is documented for programs that want the whole review as one object, without a checkout.+- **Canonical savings accounting** (#2248, #2401, #2440). Three surfaces recorded savings and each answered the same three questions its own way — which database to open, whether to create one that is missing, and what to do when the write fails. One canonical event per logical interaction replaces agreement by hand.+- **Rust bodiless function declarations are symbols** (#2382). `fn foo();` parses as `function_signature_item`, and `rust.scm` had no pattern for that node anywhere. Two shapes were invisible to the symbol graph: a trait's undefaulted methods — the trait's entire contract, everything an implementor must supply — and every `extern "C"` declaration.+- **An embedding model's width can be declared without sending dimensions** (#1857), and local-endpoint MCP budgets are configurable (#1856).++### Changed++- **A decision record is keyed, scoped and promoted on evidence** (#2425, #2426, #2434, #2439, #2441). Identity keys on the record's body, file set and quote rather than on a model-generated title. A commit's file list stops doubling as the governance binding: for a record mined from a commit it is the provenance of the change, which is true, but as scope it was mostly false, since the `pr` and `git_archaeology` miners read one decision out of one commit body and then took that commit's entire file list. The miner is asked which files a commit's decision is actually about. The governing-scope cutoff drops from ten files to five: ten was chosen by looking at a labelled sample and then scored on that same sample, and the first out-of-sample measurement put it at 49% on topic with 26% outright noise, against the 54% baseline the scope work set out to fix. A candidate is promoted for stating a reason rather than for being seen twice.+- **Acceptance requires a reason, and records what signed it** (#2279, #2445, #2457, #2458). The contract read the reason as `rationale` and fell through to `decision`, so a record whose only content restated its own title passed the "no rationale" check — the what stood in for the why. Separately, the identity check was satisfied by any non-blank string and the accepter resolver fell through to `git config user.name`, so an agent accepting a decision signed the maintainer's name into the audit log and nothing downstream could tell the two apart. `CLAUDE.md` and `AGENTS.md` now say when a standing decision was not signed by a person, since an agent reads that block as instructions.+- **Session transcript mining is off unless asked for** (#2286, #2387, #2395). A decision mined from a transcript took its scope from whatever files the surrounding tool calls named, and a transcript names plenty that is not this codebase — scratch scripts, plan documents, files belonging to a checkout sitting beside this one. Over staged candidates on a real machine only 24.7% of the bound paths were files the index holds, and 64.5% of rows carried a list in which nothing resolved at all. Codex transcripts are scoped to the repository that owns them; both raw-line gates had dropped the `session_meta` line carrying the working directory, so every Codex event read as having no opinion rather than as a miss.+- **Decision confidence accounts for what a record states** (#2328). Confidence read source rank, corroboration and verification but never whether the record said anything, so the ranking ran backwards: records filling one body field averaged 0.845 against 0.776 for records filling five, with 65.2% of ordered pairs inverted. Scaling the rank-earned credit by how much an extracted record states takes the inversion rate to 12.9% and makes the table monotonic.+- **`get_change_risk` reports what a change wrote, not what it weighs** (#2452). A census of 135 recorded calls from Claude Code and Codex, 118 of them real engineering use, found the tool spending its payload on signals no agent acted on and burying the ones they did.+- **The commit sheet leads with where a change lands** (#2453, #2455). It opened on a percentile and then spent its body explaining the number it had just printed — three of its four blocks were commentary about the model, and it never named a file. The queue's chips filter the repository now instead of the loaded page: risk order returns the top tercile first, so all 50 loaded rows were already "high", the chips read "All (50), High priority (50)", and clicking High priority removed nothing. On this repository the real figures are 911 / 302 / 458.+- **The costs page is an evidence-led scan surface** (#2432). It was a stack of nested cards at one visual weight throughout. A card should mean "an object you can act on", and a savings total is not that, so the boxes carried no information while removing the page's hierarchy.+- **MCP responses stop repeating themselves** (#2272, #2284, #2456). The canonical index scope is about 900 characters and rode on every response — roughly a third of a small `get_symbol` reply, spent answering a question almost no call asks. A diagnostic that ships with every answer is a tax rather than a disclosure, so a digest rides instead and the full scope is one call away. It is also parsed once per index state rather than re-reading `state.json` and re-parsing `config.yaml` on every call. Four further fields, each rebuildable from the row it shipped beside or from the key it sat under, are gone.+- **`timing_ms` is reported for every tool** (#2271), rather than for the ones someone had remembered to thread it through.+- **History-based health gates are ranked against the repository** (#2437, #2438). Six months is a fixed window, so a repository landing many commits a day accumulates more fix commits per file inside it than a quiet one; with an entry gate of one fix, `prior_defect` fired on 43.5% of the files here, and a signal that flags nearly half a tree is not locating anything. Co-change breadth is measured before truncation rather than by counting a list capped at 25 partners, where above the cap every file looks identical.+- **An agent is defined once** (#2394). The same agent was spelled four ways across four hand-maintained namespaces, and the savings domain had added a fifth and a sixth that agreed with the target registry only by hand.++### Fixed++- **`get_why` stops claiming a ruling the store does not hold** (#2280, #2282, #2322). A record is a candidate until a `DecisionAcceptance` row exists, and accepting is a deliberate manual step, so a store of nothing but candidates is the state of every repository whose maintainer has not worked through the acceptance UI. Separately, neither path-mode call shape declared its lanes as requested, so the shared response budget shed them first and a path query dropped its origin story whole. The health mode names the active, deprecated, superseded, dismissed and unscoped lanes it previously reported as a bare count.+- **A hand-authored decision reaches the surfaces that deliver it** (#2464). `decision add` and the HTTP create route wrote `affected_files_json` and stopped, while the edit-time injection hook, `get_governing_decisions` and the `get_risk` directives all read `decision_node_links`, which only the mining pipeline ever wrote. A record added by hand had files and no links, so nothing could deliver it.+- **`get_risk` stops answering an unresolved target with a confident zero** (#2321). A `module:` id, a bare directory, an unindexed path and a typo all fell through to the same card, every numeric field of which was a structural zero. Measured here, a subsystem directory returned `dependents_count: 0` while a single file inside it returned 59, so a subsystem nothing could safely be changed in read as safe to change. The directory is the dangerous form, because it looks like an ordinary target.+- **`get_context`'s `used_by` keys on the symbol, not on its file** (#2329). The query joined the edge target against the symbol's file path, but every symbol-level edge is emitted symbol-to-symbol with a `path::Name` target, so calls, references, extends, implements, method_implements, dispatches_to, framework_binds and reads could none of them ever match. The field answered "who imports this symbol's file" under a name that promises otherwise.+- **`get_symbol(depth=3)` serves the hops it found** (#2285), and a requested projection is kept ahead of the ones a caller did not ask for (#2270) — `get_overview(include=["outline"])` returned 0 of 40 outline sections while leaving 73% of its budget unspent.+- **A `.tsx` file is read with the JSX grammar** (#2398). It arrives tagged `typescript`, and that grammar fails on the first `<Component />`; everything after it landed in error recovery, so the health pass was reading a tree that does not describe the file. Assertions after the first element were never counted, the clone detector hashed a token stream recovery had partly invented, and the dataflow CFG was built over the same wreckage.+- **A file's same-named functions survive to the markers that score them** (#2408). Eleven scoring markers read a per-file map keyed by function name, and a function name is not unique inside a file — every `it(...)` callback in a spec file walks under the name `it callback`, and `__init__` walks under one name on each class in a module.+- **Rust graph precision** (#1568, #2362, #2376, #2386, #2409, #2412, #2415, #2418, #2423). Field and type-argument types are recorded as type references, so a struct used only as a field type or nested in `Option<T>` no longer reads as an unused export; Rust reaches an intra-crate field type without a `use` statement, so nothing else recorded the reference. A `pub trait`'s items take the visibility the trait declares instead of `private`, which had left downstream-callable API sitting in the narrow dead-code pool. A trait's defaulted methods are parented to the trait rather than emitted parentless as plain functions. `type_use` captures widen to wrapper shapes, a scoped call binds to its own type rather than the file's last, a re-export through a crate root carries the rest of the path, a trait bound is no longer read as inheritance, a std-library name is refused on the `import_merged` tier, and impl blocks are treated as uncallable and non-importable.+- **C#, Go, Objective-C, Swift, Java, GDScript and TypeScript extraction** (#2309, #2312, #2316, #2318, #2323, #2324, #2330, #2336, #2361, #2363, #2364, #2402, #2414, #2428). C# null-conditional call sites (`a?.Foo()`) are captured — they were not resolved-and-wrong and not unresolved either, but never captured, so nothing downstream knew they existed — and an extension-method call binds to the type it extends, with `builtin_parents` aligned to the shared .NET BCL set. Go functions in composite literals mint reference edges. Objective-C `.h` and `.m` files are paired, and a call-shaped attribute macro trailing a declaration is blanked rather than left to wreck error recovery past the terminating semicolon. A Swift qualified extension no longer names its qualifier as a conformer in its own right. A bare `@Immutable` stops fabricating a generated Java class. TypeScript class fields holding a function are indexed. GDScript `uid://` references resolve through the `.uid` sidecar, and a Godot scene connection resolves to a C# script method. A nested sub-package resolves from its own manifest, an inheritance edge anchors to the child's real symbol id, and inert `reads` membership is retired from `SYMBOL_USE_EDGE_TYPES`.+- **Savings are priced from their own evidence** (#2413, #2461, #2468). Nothing wrote pricing onto a canonical event, so any report over the canonical ledger would have valued real savings at $0.00; the legacy readers avoided that by resolving the coding agent's model at read time and repricing all of history at it, which moved past figures whenever the newest session changed model. Rates are no longer fabricated and stamped as measured, evidence on disk is no longer thrown away, and two counterfactual estimators describing a tool that no longer exists had been recording the tools they cover as a net cost on nearly every call. The API, the overview and the CLI report the same numbers. The reported figure stays a deliberate floor: where the evidence is ambiguous the ledger declines to claim a saving rather than estimating one, so the real figure is very likely higher than the one shown.+- **`distill` runs a wrapped command in the shell it was written for** (#2448). `_POSIX_HOST = os.name == "posix"` gated both the metacharacter bail and safe-chain recognition, so on a Windows host `cd X && git diff` from an agent's Bash tool was refused before classification ever ran. Measured over 30 days on one machine: 2,203 commands bypassed distillation, worth 738,123 tokens, and that one gate explains 97.5% of them.+- **Secret values are masked in security finding snippets** (#2375), `provider_config` is stored `0600`, and keys are redacted in the validate response (#1798).+- **CORS is browser-compliant and configurable by environment** (#1793), and repository paths are passed to local CLI providers (#2242).+- **A configured database is treated as a store** by `update` (#2404) and `delete` (#2338). Both guarded on the repo-local `wiki.db` file before building an engine from `resolve_db_url`; under a shared database that file is absent by design, so the guard returned before the engine was ever built.+- **`init --force` in a worktree is no longer a paid upgrade** (#2339), MCP tool updates route to the workspace repository database (#2241), and a missing workspace repository can be removed from the UI (#2253).+- **A whole prompt is recorded as input tokens** (#2337). Claude Code splits one prompt across three disjoint usage fields, and only `input_tokens` — the uncached remainder — was persisted, so a roughly 20k-token module page recorded `input_tokens=2` and `status` summed a whole wiki to almost nothing.+- **DeepSeek and Kimi are priced** (#1790) rather than $0 in both the estimator and the live tracker, and `codex_cli` subprocess concurrency is configurable (#2334).+- **The root layout's repository list is not prerendered** (#2260, #2261). `/settings` and `not-found` are static routes, so `next build` prerendered them where no API answers and baked "can't reach the API" into their payloads; since layouts do not re-render on soft navigation, the sidebar then stayed wrong on a healthy server.+- **`total_pages` is zero when a phase reports no total** (#2308), a formatter comment stops prescribing `ruff format` (#2444), the no-index MCP guidance names the capability rather than one host's tool names (#2326), and chat stops suggesting questions no tool can answer (#2315).+- **Decision plumbing** (#2310, #2314, #2357, #2421, #2422, #2447, #2450). Paraphrases are deduplicated at the pass that creates the record, and stored duplicates are folded in one sweep. `last_code_change` is filled from the dates staleness already reads, having held a value on 0 of 357 records. Staged decision paths are stored in a form the index can resolve. A bundled claim is flagged on every capture path rather than on one lane. A starved token budget no longer silently loses whole batches, and one wordy candidate no longer silences its whole lane.+- **The contradiction rate counts rows, not decisions** (#2479). `hook stats` reported 181 followed against 20 contradicted, a 10.0% rate, where all 20 rows were one decision: the verdict was computed per decision and stored per row, so a single match settled every row that decision had ever been shown in. The true rate on that corpus is 0 of 201. Alongside it, a contradiction now requires two-sided evidence rather than a reversal keyword found in either text alone, opposing verbs match as whole words rather than inside longer ones (`use` was matching inside `user`), and injection rows resolve through `decision_aliases` so a re-keyed record no longer reads as gone and drains its rows.+- **A failed HEAD read no longer strands a store's sync pointer** (#2446), a churn rank is published beside the raw churn sum on direct risks (#2443), a zero-impact finding is visible to a surface that ranks nothing (#2430), a shared `warn()` helper unifies the warning stream (#1843), and the credential-masking migration has its own revision (#2462).+- **An MCP session's end is named** (#2283) instead of arriving as EOF, a broken pipe or a cancelled task that were all indistinguishable from a crash — the hang-up escaped as a traceback the host would respawn on, and a clean end produced no line at all.++### Documentation++- The change-review engine is documented for programs that compose it directly (#2281). Contributor guidance makes a claim binding from the moment the comment is posted rather than from assignment, which can lag it by days (#2377), and corrects stale setup steps. The Rust `unused_internal` skip is given its real reason (#2390): the stated one was that the graph emits no intra-file Rust call edges, and it does — same-file calls are the largest single resolution origin in every Rust repository measured, and bare same-file call sites resolve at 97.5% or better.++---## [0.51.0] - 2026-09-16An index makes claims about a repository, and several of them were not being checked. A fast index and a full one described their scope differently in every place that reported it, and a configured cap could be read as achieved coverage. Git history sampling let a file's retained history depend on which of two internal lanes happened to serve it. Pages that fell outside a generation selection could be marked stale and stay stale through every later update, while `doctor` blamed the wrong cause and named a command that could not clear it. An update could call a repository current because its commit had not moved, even when the configuration deciding what to index had changed underneath it. This release makes each of those say what is actually true, and records the coverage a run achieved rather than the coverage it was allowed. Next to that, contract evidence stops depending on whether a handler signature can be recovered from code: a checked-in OpenAPI document is now a provider schema, compared directionally, and local Maven coordinates resolve across a workspace. COBOL is a parsed language.diff --git a/packages/server/src/repowise/server/__init__.py b/packages/server/src/repowise/server/__init__.pyindex 37d09d983..eb8da2008 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__ = "0.51.0"+__version__ = "0.52.0"diff --git a/plugins/claude-code/.claude-plugin/plugin.json b/plugins/claude-code/.claude-plugin/plugin.jsonindex bd7fcab81..ee1f9ce2e 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 ten 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": "0.51.0",+ "version": "0.52.0","author": {"name": "Repowise","email": "[email protected]",diff --git a/plugins/claude-code/CHANGELOG.md b/plugins/claude-code/CHANGELOG.mdindex d399854ca..1e1bdcf01 100644--- a/plugins/claude-code/CHANGELOG.md+++ b/plugins/claude-code/CHANGELOG.md@@ -2,6 +2,27 @@All notable changes to the Repowise Claude Code plugin are documented here.+## 0.52.0++### Changed+- The `decision` command reflects what acceptance now requires. A record whose+ body only restates its own title can no longer be confirmed, so the command+ tells the caller to state a reason rather than leaving it to be discovered at+ `confirm` time. It documents `--kind agreement` for a working agreement — a+ rule about how the work is conducted, which names no file and is not checked+ against the code — and `--evidence-commit`, which ties a record to the commit+ the choice was made in and is what stops the same commit being asked about+ twice.+- The command no longer claims a fixed source count. Capture sources are+ individually switchable and transcript mining is now off unless a repository+ turns it on, so it points at `repowise decision source list` instead.+- No tool-surface change this cycle: the server still lists the same 18 tools,+ every tool named in a command or skill is one of them, and `hooks.json` still+ mirrors the shared augment matcher in `claude_config.py`. The shell+ `PostToolUse` entry the new decision capture prompt needs is installed by+ `repowise decision config capture-prompt --on`, deliberately not by the+ plugin, so the measured narrowing of the shared matcher is not reversed.+## 0.51.0### Fixeddiff --git a/plugins/claude-code/commands/decision.md b/plugins/claude-code/commands/decision.mdindex 908bb6c07..33c34fff8 100644--- a/plugins/claude-code/commands/decision.md+++ b/plugins/claude-code/commands/decision.md@@ -5,9 +5,11 @@ allowed-tools: Bash, Read# Repowise Decisions-Repowise captures architectural decisions (the *why* behind the code) from eight-sources and tracks them for staleness and conflicts. This command drives the-`repowise decision` group.+Repowise captures architectural decisions (the *why* behind the code) from+several sources and tracks them for staleness and conflicts. This command drives+the `repowise decision` group. Sources are individually switchable — run+`repowise decision source list` to see which are on; transcript mining is off+unless the repository turns it on.## Steps@@ -29,8 +31,13 @@ sources and tracks them for staleness and conflicts. This command drives the`--title` and `--decision` it records without prompting and prints the id(`--format json` to parse it back), which is the form to use with no terminal.The rest are optional: `--context`, `--rationale`, `--alternative`,- `--consequence`, `--affects`, `--tag`, the last four repeatable. A flag-driven- record lands `proposed` for a person to `confirm`.+ `--consequence`, `--affects`, `--tag`, `--evidence-commit`, the last five+ repeatable. A flag-driven record lands `proposed` for a person to `confirm`.+ **Always state a reason** — pass `--rationale` (or `--context`); a record whose+ body only restates its own title cannot be accepted. `--kind agreement` records+ a working agreement: a rule about how the work is conducted, which names no+ file and is not checked against the code. `--evidence-commit <sha>` ties the+ record to the commit the choice was made in.- **confirm** — `repowise decision confirm` — review decisions auto-proposed fromgit history and accept or reject them.- **deprecate / dismiss** — `repowise decision deprecate <id>` (optionallydiff --git a/plugins/shared/commands/decision.md b/plugins/shared/commands/decision.mdindex f567915e5..8eb668aa4 100644--- a/plugins/shared/commands/decision.md+++ b/plugins/shared/commands/decision.md@@ -6,9 +6,11 @@ frontmatter: |# Repowise Decisions-Repowise captures architectural decisions (the *why* behind the code) from eight-sources and tracks them for staleness and conflicts. This command drives the-`repowise decision` group.+Repowise captures architectural decisions (the *why* behind the code) from+several sources and tracks them for staleness and conflicts. This command drives+the `repowise decision` group. Sources are individually switchable — run+`repowise decision source list` to see which are on; transcript mining is off+unless the repository turns it on.## Steps@@ -30,8 +32,13 @@ sources and tracks them for staleness and conflicts. This command drives the`--title` and `--decision` it records without prompting and prints the id(`--format json` to parse it back), which is the form to use with no terminal.The rest are optional: `--context`, `--rationale`, `--alternative`,- `--consequence`, `--affects`, `--tag`, the last four repeatable. A flag-driven- record lands `proposed` for a person to `confirm`.+ `--consequence`, `--affects`, `--tag`, `--evidence-commit`, the last five+ repeatable. A flag-driven record lands `proposed` for a person to `confirm`.+ **Always state a reason** — pass `--rationale` (or `--context`); a record whose+ body only restates its own title cannot be accepted. `--kind agreement` records+ a working agreement: a rule about how the work is conducted, which names no+ file and is not checked against the code. `--evidence-commit <sha>` ties the+ record to the commit the choice was made in.- **confirm** — `repowise decision confirm` — review decisions auto-proposed fromgit history and accept or reject them.- **deprecate / dismiss** — `repowise decision deprecate <id>` (optionallydiff --git a/pyproject.toml b/pyproject.tomlindex 08a25c60f..b1e79d5a4 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"[project]name = "repowise"-version = "0.51.0"+version = "0.52.0"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.jsonindex 878bb7713..279802658 100644--- a/server.json+++ b/server.json@@ -8,12 +8,12 @@"source": "github"},"websiteUrl": "https://www.repowise.dev",- "version": "0.51.0",+ "version": "0.52.0","packages": [{"registryType": "pypi","identifier": "repowise",- "version": "0.51.0",+ "version": "0.52.0","transport": {"type": "stdio"},diff --git a/uv.lock b/uv.lockindex f43b5ccf6..261f21f18 100644--- a/uv.lock+++ b/uv.lock@@ -3051,7 +3051,7 @@ wheels = [[[package]]name = "repowise"-version = "0.51.0"+version = "0.52.0"source = { editable = "." }dependencies = [{ name = "aiosqlite" },