codebase-index 1.9.0__tar.gz → 2.1.0__tar.gz

codebase_index-2.1.0/.claude/skills/codebase-index/.skill_version

@@ -0,0 +1 @@
+2.1.0

codebase_index-2.1.0/.claude/skills/codebase-index/SKILL.md

@@ -0,0 +1,65 @@
+---
+name: codebase-index
+description: Use before answering repository questions about architecture, implementation, symbols, references, dependencies, refactoring impact, data flow, or bugs. Query the local hybrid index first so the agent reads only evidence-bearing file:line ranges instead of scanning the repository, and verify evidence gathered earlier before relying on it.
+allowed-tools: Bash(codebase-index search *), Bash(codebase-index explain *), Bash(codebase-index architecture *), Bash(codebase-index symbol *), Bash(codebase-index refs *), Bash(codebase-index impact *), Bash(codebase-index diff-impact *), Bash(codebase-index path *), Bash(codebase-index describe *), Bash(codebase-index verify *), Bash(codebase-index graph *), Bash(codebase-index stats *), Bash(codebase-index doctor *), Bash(codebase-index update *), Bash(codebase-index index *), Bash(cbx *), Read, Grep, Glob
+---
+
+# Codebase Index
+
+Use the local index before reading repository files. It answers with ranked,
+numbered lines, so most answers need no Read and no Grep at all.
+
+## Route the question — always `--compact`
+
+| Intent | Command |
+|---|---|
+| Where / how does X work? | `codebase-index search "X" --compact --session <tag>` |
+| Overview of a feature | `codebase-index explain "X" --compact --session <tag>` |
+| Every caller / call site of X | `codebase-index refs "Owner.member" --compact` |
+| What breaks if X changes (incl. other modules) | `codebase-index impact "Owner.member" --compact` |
+| Find a definition | `codebase-index symbol "X"` |
+| A class: members, who uses it | `codebase-index describe "Class" --json` |
+| What does my diff affect? | `codebase-index diff-impact --json` |
+| Is what I read earlier still true? | `codebase-index verify --session <tag> --json` |
+
+`--compact` prints `path:start-end symbol` per result with the matching lines
+numbered underneath (`  24| public static final String FILE_ID = ...`). Cite
+those lines as `path:24` directly. Read a range only when the lines shown do not
+answer the question — and then only that range, never the whole file.
+
+Name members as `Owner.member` (`TownService.refresh`, `activation::place`,
+`CoreError::ObjectDamaged`) so same-named methods of other types are excluded.
+`refs --compact` lines are `path:line kind caller -> target`: the list of call
+sites with the calling function is usually the whole answer. Add
+`--exclude-tests` for production-only lists and `--path <prefix>` for one module.
+`kind reference` is a non-call use, e.g. an enum variant matched in a `match` arm.
+
+`impact --compact` starts with `# module <m>: build files depending on it: ...`
+— the answer to "does another module depend on this", with no build-file grep.
+
+## Protocol
+
+1. Pick one session tag per conversation (e.g. `auth-fix-1`); pass it to
+   `search`/`explain`. Results already sent in this session print as
+   `(already sent)` — use your earlier copy.
+2. A header saying `index stale` → run `codebase-index update` once; `NO INDEX`
+   → `codebase-index index`.
+3. Batch independent questions into one Bash call (`cmd1; echo ---; cmd2`).
+4. `# partial:` on refs/impact means the list may be incomplete. For
+   `Owner.member` it lists `possible_call` sites (calls on a variable the index
+   cannot type), nearest first: check those few lines, do not grep the repo.
+5. Before relying on evidence from earlier in a long task, run
+   `codebase-index verify --session <tag> --json`.
+6. Grep only when the index returns nothing relevant or for non-code text.
+
+Edge confidence: `extracted` exact, `inferred` heuristic (receiver matched a
+type), `ambiguous` unresolved. Never present an inferred chain as certain.
+
+## Answer
+
+Lead with the answer, then the minimum `file:line` evidence. State uncertainty
+only when evidence is partial, inferred or stale.
+
+Options and JSON fields: [references/commands.md](references/commands.md),
+[references/response-contract.md](references/response-contract.md),
+session memory: [references/memory.md](references/memory.md).

{codebase_index-1.9.0 → codebase_index-2.1.0}/.claude/skills/codebase-index/references/commands.md

@@ -17,6 +17,9 @@ Useful search options:
 - `--offset <pagination offset>`
 - `--raw` to disable snippet skeletonization
 - `--no-fallback` to suppress fallback suggestions
+- `--session <tag>` to name this conversation's context: unchanged evidence it
+  already received comes back as `reused: true` without the snippet, and
+  evidence that changed is listed under `memory.invalidated`
 
 `explain` uses the HOW_IT_WORKS intent and a larger default token budget. Prefer
 it over repeatedly rewording a broad search.
@@ -34,6 +37,24 @@ codebase-index describe "<file-or-symbol>" --json
 
 - `architecture` reads module analysis cached at index time.
 - `refs` finds definitions, calls, and graph-backed references.
+  For a method whose name several types share, pass `Owner.member`
+  (`TownService.refresh`, or `module::fn` for a top-level function); each site
+  names its `caller` and the `target` it resolved to. Calls the index cannot type
+  (`chest.holdings().take(..)`) come back as `possible_call`, nearest first, with
+  `coverage.partial: true`: read those before claiming a complete list.
+  `impact` and `symbol` accept the same form.
+  Filters: `--exclude-tests`, `--path <prefix>` (repeatable). `--compact` prints
+  `path:line kind caller -> target [confidence]`, one site per line.
+- `search`, `explain` and `impact` also take `--compact`: agent text instead of
+  JSON. For search/explain, each result is `path:start-end symbols` followed by up
+  to eight numbered lines that carry the match (rarer query words first);
+  evidence already sent to the session prints as `(already sent)`. For impact,
+  one `d<hops> path:line name via edge` line per node, after a
+  `# module ...` line naming the build files that depend on the target's module.
+- `symbol` returns exact matches alone when there are any and reports how many
+  prefix matches it left out (`more_prefix_matches`); `--exact` drops them.
+- `describe` on a class, enum, struct or trait also lists its `members` and
+  folds their edges into `used_by` / `uses` (code outside the type).
 - `impact` walks dependents (`up`), dependencies (`down`), or both.
 - `diff-impact` aggregates impact for tracked changes relative to a verified
   Git commit; new or excluded files are reported as unresolved.
@@ -49,6 +70,18 @@ codebase-index graph "<target>" --direction both --depth 2 --output graph.html
 For headless work, use `--output`; do not use `--open`. Exports also support
 `--format graphml|dot|neo4j`.
 
+## Evidence
+
+```bash
+codebase-index verify --session <tag> --json
+codebase-index verify "<path:start-end@hash>" ... --json
+```
+
+- `verify` is read-only and needs no index: it checks evidence against the
+  working tree. `all_valid` is true only when every checked span still holds.
+- `--strict` exits 1 when anything is invalid (useful in scripts).
+- See [memory.md](memory.md) for verdict states and when to reread.
+
 ## Index health
 
 ```bash

codebase_index-2.1.0/.claude/skills/codebase-index/references/memory.md

@@ -0,0 +1,49 @@
+# Evidence Memory
+
+Load this when you use `--session`, when a packet contains `reused`, `stale` or
+`memory`, or when you want to cite evidence for later.
+
+## What is guaranteed
+
+Evidence is identified by the exact bytes of a file span. `reused: true` is set
+only when this session already received the same text — or the whole span —
+and those bytes are unchanged now. Nothing is decided by query similarity, and
+memory stores no source text.
+
+## Verdict states
+
+| state | still true? | do this |
+|---|---|---|
+| `valid` | yes | use it |
+| `relocated` | yes — identical content moved inside the file | use it; cite the new lines |
+| `changed` | no | reread the range before relying on it |
+| `ambiguous` | no — identical content now occurs more than once | reread |
+| `deleted` | no — file gone; a rename or move counts as deleted | search again |
+| `excluded` | no — now ignored or secret-like | do not read it |
+| `unreadable` | no | search again |
+
+## Reread even when evidence is valid
+
+- You are about to edit and need the exact current text.
+- The earlier snippet was a skeleton or a signature and you need the body.
+- Your context was cleared or compacted, or you cannot see the earlier snippet.
+- A tool output was truncated.
+
+## Citing evidence across conversations
+
+`codebase-index verify --session <tag> --json` lists everything the session
+received as `path:start-end@hash` references. Keep the references next to the
+conclusions they support in notes or handoffs:
+
+```text
+Refunds are capped at the invoice total [billing/refund.py:3-4@3f9a2c1b7d4e8a90]
+```
+
+Later, from any agent, check them before trusting the note:
+
+```bash
+codebase-index verify "billing/refund.py:3-4@3f9a2c1b7d4e8a90" --json
+```
+
+`all_valid: true` means every cited span still holds exactly. Otherwise reread
+the invalid spans and re-derive the conclusion; do not patch the old one.

{codebase_index-1.9.0/.opencode → codebase_index-2.1.0/.claude}/skills/codebase-index/references/response-contract.md

@@ -16,9 +16,20 @@ Each result can contain:
 - `snippet`
 - `skeletonized`
 - `elided_lines`
+- `stale` — only when the index text no longer matches the file
+- `reused` — only with `--session`, when `snippet` was withheld because this
+  session already received that exact text from unchanged source
 
 `recommended_reads` is the read plan. Start with its first one to three entries
-and use exact line ranges.
+and use exact line ranges. An entry with `truncated: true` was capped at the
+definition head (`max_read_lines`, default 120); `line_end_full` gives the real
+extent. Read the capped range first and continue only when the head is not
+enough.
+
+With `--session`, the packet also carries `memory`: `session`, `reused`,
+`tokens_saved`, and `invalidated` — references to evidence the session received
+that has since changed. `available: false` means nothing was withheld. See
+[memory.md](memory.md).
 
 `pagination.has_more` and `pagination.next_offset` indicate additional results.
 Prefer a more specific command or a larger token budget before paging.

{codebase_index-1.9.0 → codebase_index-2.1.0}/.claude/skills/codebase-index/scripts/cbx

@@ -4,7 +4,7 @@
 # - Whitelists subcommands so the skill can never invoke destructive ones (clean/init/watch).
 set -euo pipefail
 
-ALLOWED="search explain architecture symbol refs impact diff-impact path describe graph stats doctor update index"
+ALLOWED="search explain architecture symbol refs impact diff-impact path describe verify graph stats doctor update index"
 
 sub="${1:-}"
 case " $ALLOWED " in

{codebase_index-1.9.0/.opencode → codebase_index-2.1.0/.claude}/skills/codebase-index/scripts/cbx.ps1

@@ -10,7 +10,7 @@ param(
 $ErrorActionPreference = "Stop"
 $allowed = @(
     "search", "explain", "architecture", "symbol", "refs", "impact", "diff-impact",
-    "path", "describe", "graph", "stats", "doctor", "update", "index"
+    "path", "describe", "verify", "graph", "stats", "doctor", "update", "index"
 )
 
 if ($allowed -notcontains $Subcommand) {

{codebase_index-1.9.0 → codebase_index-2.1.0}/.claude-plugin/plugin.json

@@ -3,7 +3,7 @@
   "name": "codebase-index",
   "displayName": "Codebase Index",
   "description": "Give Claude a precise local map of your codebase: find implementations, trace behavior, and predict change impact with file-line evidence.",
-  "version": "1.9.0",
+  "version": "2.1.0",
   "author": {
     "name": "codebase-index contributors"
   },

codebase_index-2.1.0/.codex/skills/codebase-index/.skill_version

@@ -0,0 +1 @@
+2.1.0

codebase_index-2.1.0/.codex/skills/codebase-index/SKILL.md

@@ -0,0 +1,65 @@
+---
+name: codebase-index
+description: Use before answering repository questions about architecture, implementation, symbols, references, dependencies, refactoring impact, data flow, or bugs. Query the local hybrid index first so the agent reads only evidence-bearing file:line ranges instead of scanning the repository, and verify evidence gathered earlier before relying on it.
+allowed-tools: Bash(codebase-index search *), Bash(codebase-index explain *), Bash(codebase-index architecture *), Bash(codebase-index symbol *), Bash(codebase-index refs *), Bash(codebase-index impact *), Bash(codebase-index diff-impact *), Bash(codebase-index path *), Bash(codebase-index describe *), Bash(codebase-index verify *), Bash(codebase-index graph *), Bash(codebase-index stats *), Bash(codebase-index doctor *), Bash(codebase-index update *), Bash(codebase-index index *), Bash(cbx *), Read, Grep, Glob
+---
+
+# Codebase Index
+
+Use the local index before reading repository files. It answers with ranked,
+numbered lines, so most answers need no Read and no Grep at all.
+
+## Route the question — always `--compact`
+
+| Intent | Command |
+|---|---|
+| Where / how does X work? | `codebase-index search "X" --compact --session <tag>` |
+| Overview of a feature | `codebase-index explain "X" --compact --session <tag>` |
+| Every caller / call site of X | `codebase-index refs "Owner.member" --compact` |
+| What breaks if X changes (incl. other modules) | `codebase-index impact "Owner.member" --compact` |
+| Find a definition | `codebase-index symbol "X"` |
+| A class: members, who uses it | `codebase-index describe "Class" --json` |
+| What does my diff affect? | `codebase-index diff-impact --json` |
+| Is what I read earlier still true? | `codebase-index verify --session <tag> --json` |
+
+`--compact` prints `path:start-end symbol` per result with the matching lines
+numbered underneath (`  24| public static final String FILE_ID = ...`). Cite
+those lines as `path:24` directly. Read a range only when the lines shown do not
+answer the question — and then only that range, never the whole file.
+
+Name members as `Owner.member` (`TownService.refresh`, `activation::place`,
+`CoreError::ObjectDamaged`) so same-named methods of other types are excluded.
+`refs --compact` lines are `path:line kind caller -> target`: the list of call
+sites with the calling function is usually the whole answer. Add
+`--exclude-tests` for production-only lists and `--path <prefix>` for one module.
+`kind reference` is a non-call use, e.g. an enum variant matched in a `match` arm.
+
+`impact --compact` starts with `# module <m>: build files depending on it: ...`
+— the answer to "does another module depend on this", with no build-file grep.
+
+## Protocol
+
+1. Pick one session tag per conversation (e.g. `auth-fix-1`); pass it to
+   `search`/`explain`. Results already sent in this session print as
+   `(already sent)` — use your earlier copy.
+2. A header saying `index stale` → run `codebase-index update` once; `NO INDEX`
+   → `codebase-index index`.
+3. Batch independent questions into one Bash call (`cmd1; echo ---; cmd2`).
+4. `# partial:` on refs/impact means the list may be incomplete. For
+   `Owner.member` it lists `possible_call` sites (calls on a variable the index
+   cannot type), nearest first: check those few lines, do not grep the repo.
+5. Before relying on evidence from earlier in a long task, run
+   `codebase-index verify --session <tag> --json`.
+6. Grep only when the index returns nothing relevant or for non-code text.
+
+Edge confidence: `extracted` exact, `inferred` heuristic (receiver matched a
+type), `ambiguous` unresolved. Never present an inferred chain as certain.
+
+## Answer
+
+Lead with the answer, then the minimum `file:line` evidence. State uncertainty
+only when evidence is partial, inferred or stale.
+
+Options and JSON fields: [references/commands.md](references/commands.md),
+[references/response-contract.md](references/response-contract.md),
+session memory: [references/memory.md](references/memory.md).

{codebase_index-1.9.0/skill → codebase_index-2.1.0/.codex/skills/codebase-index}/references/commands.md

@@ -17,6 +17,9 @@ Useful search options:
 - `--offset <pagination offset>`
 - `--raw` to disable snippet skeletonization
 - `--no-fallback` to suppress fallback suggestions
+- `--session <tag>` to name this conversation's context: unchanged evidence it
+  already received comes back as `reused: true` without the snippet, and
+  evidence that changed is listed under `memory.invalidated`
 
 `explain` uses the HOW_IT_WORKS intent and a larger default token budget. Prefer
 it over repeatedly rewording a broad search.
@@ -34,6 +37,24 @@ codebase-index describe "<file-or-symbol>" --json
 
 - `architecture` reads module analysis cached at index time.
 - `refs` finds definitions, calls, and graph-backed references.
+  For a method whose name several types share, pass `Owner.member`
+  (`TownService.refresh`, or `module::fn` for a top-level function); each site
+  names its `caller` and the `target` it resolved to. Calls the index cannot type
+  (`chest.holdings().take(..)`) come back as `possible_call`, nearest first, with
+  `coverage.partial: true`: read those before claiming a complete list.
+  `impact` and `symbol` accept the same form.
+  Filters: `--exclude-tests`, `--path <prefix>` (repeatable). `--compact` prints
+  `path:line kind caller -> target [confidence]`, one site per line.
+- `search`, `explain` and `impact` also take `--compact`: agent text instead of
+  JSON. For search/explain, each result is `path:start-end symbols` followed by up
+  to eight numbered lines that carry the match (rarer query words first);
+  evidence already sent to the session prints as `(already sent)`. For impact,
+  one `d<hops> path:line name via edge` line per node, after a
+  `# module ...` line naming the build files that depend on the target's module.
+- `symbol` returns exact matches alone when there are any and reports how many
+  prefix matches it left out (`more_prefix_matches`); `--exact` drops them.
+- `describe` on a class, enum, struct or trait also lists its `members` and
+  folds their edges into `used_by` / `uses` (code outside the type).
 - `impact` walks dependents (`up`), dependencies (`down`), or both.
 - `diff-impact` aggregates impact for tracked changes relative to a verified
   Git commit; new or excluded files are reported as unresolved.
@@ -49,6 +70,18 @@ codebase-index graph "<target>" --direction both --depth 2 --output graph.html
 For headless work, use `--output`; do not use `--open`. Exports also support
 `--format graphml|dot|neo4j`.
 
+## Evidence
+
+```bash
+codebase-index verify --session <tag> --json
+codebase-index verify "<path:start-end@hash>" ... --json
+```
+
+- `verify` is read-only and needs no index: it checks evidence against the
+  working tree. `all_valid` is true only when every checked span still holds.
+- `--strict` exits 1 when anything is invalid (useful in scripts).
+- See [memory.md](memory.md) for verdict states and when to reread.
+
 ## Index health
 
 ```bash

codebase_index-2.1.0/.codex/skills/codebase-index/references/memory.md

@@ -0,0 +1,49 @@
+# Evidence Memory
+
+Load this when you use `--session`, when a packet contains `reused`, `stale` or
+`memory`, or when you want to cite evidence for later.
+
+## What is guaranteed
+
+Evidence is identified by the exact bytes of a file span. `reused: true` is set
+only when this session already received the same text — or the whole span —
+and those bytes are unchanged now. Nothing is decided by query similarity, and
+memory stores no source text.
+
+## Verdict states
+
+| state | still true? | do this |
+|---|---|---|
+| `valid` | yes | use it |
+| `relocated` | yes — identical content moved inside the file | use it; cite the new lines |
+| `changed` | no | reread the range before relying on it |
+| `ambiguous` | no — identical content now occurs more than once | reread |
+| `deleted` | no — file gone; a rename or move counts as deleted | search again |
+| `excluded` | no — now ignored or secret-like | do not read it |
+| `unreadable` | no | search again |
+
+## Reread even when evidence is valid
+
+- You are about to edit and need the exact current text.
+- The earlier snippet was a skeleton or a signature and you need the body.
+- Your context was cleared or compacted, or you cannot see the earlier snippet.
+- A tool output was truncated.
+
+## Citing evidence across conversations
+
+`codebase-index verify --session <tag> --json` lists everything the session
+received as `path:start-end@hash` references. Keep the references next to the
+conclusions they support in notes or handoffs:
+
+```text
+Refunds are capped at the invoice total [billing/refund.py:3-4@3f9a2c1b7d4e8a90]
+```
+
+Later, from any agent, check them before trusting the note:
+
+```bash
+codebase-index verify "billing/refund.py:3-4@3f9a2c1b7d4e8a90" --json
+```
+
+`all_valid: true` means every cited span still holds exactly. Otherwise reread
+the invalid spans and re-derive the conclusion; do not patch the old one.

{codebase_index-1.9.0/.claude → codebase_index-2.1.0/.codex}/skills/codebase-index/references/response-contract.md

@@ -16,9 +16,20 @@ Each result can contain:
 - `snippet`
 - `skeletonized`
 - `elided_lines`
+- `stale` — only when the index text no longer matches the file
+- `reused` — only with `--session`, when `snippet` was withheld because this
+  session already received that exact text from unchanged source
 
 `recommended_reads` is the read plan. Start with its first one to three entries
-and use exact line ranges.
+and use exact line ranges. An entry with `truncated: true` was capped at the
+definition head (`max_read_lines`, default 120); `line_end_full` gives the real
+extent. Read the capped range first and continue only when the head is not
+enough.
+
+With `--session`, the packet also carries `memory`: `session`, `reused`,
+`tokens_saved`, and `invalidated` — references to evidence the session received
+that has since changed. `available: false` means nothing was withheld. See
+[memory.md](memory.md).
 
 `pagination.has_more` and `pagination.next_offset` indicate additional results.
 Prefer a more specific command or a larger token budget before paging.

{codebase_index-1.9.0/.opencode → codebase_index-2.1.0/.codex}/skills/codebase-index/scripts/cbx

@@ -4,7 +4,7 @@
 # - Whitelists subcommands so the skill can never invoke destructive ones (clean/init/watch).
 set -euo pipefail
 
-ALLOWED="search explain architecture symbol refs impact diff-impact path describe graph stats doctor update index"
+ALLOWED="search explain architecture symbol refs impact diff-impact path describe verify graph stats doctor update index"
 
 sub="${1:-}"
 case " $ALLOWED " in

{codebase_index-1.9.0 → codebase_index-2.1.0}/.codex/skills/codebase-index/scripts/cbx.ps1

@@ -10,7 +10,7 @@ param(
 $ErrorActionPreference = "Stop"
 $allowed = @(
     "search", "explain", "architecture", "symbol", "refs", "impact", "diff-impact",
-    "path", "describe", "graph", "stats", "doctor", "update", "index"
+    "path", "describe", "verify", "graph", "stats", "doctor", "update", "index"
 )
 
 if ($allowed -notcontains $Subcommand) {

codebase_index-2.1.0/.gitattributes

@@ -0,0 +1,16 @@
+# Скрипты-инсталляторы должны иметь LF, иначе ломаются на macOS/Linux
+# (shebang "#!/usr/bin/env sh\r" недопустим). PowerShell-файлы — тоже LF для единообразия.
+*.sh    text eol=lf
+*.ps1   text eol=lf
+*.py    text eol=lf
+# cbx — POSIX-скрипт без расширения; CRLF в worktree ломает shebang при копировании
+cbx     text eol=lf
+# .skill_version хранит ровно "<version>\n"; scripts/sync_skill_copies.py пишет и
+# сравнивает байты, поэтому при core.autocrlf=true git подставлял CRLF в worktree и
+# test_real_repo_is_in_sync падал на любом свежем клоне под Windows.
+.skill_version  text eol=lf
+# sample_repo сравнивается побайтно: tests/fixtures/index-1.10.0/index.sqlite хранит sha256
+# её файлов. Файлы без правила (web/app.ts) git под Windows с core.autocrlf=true отдавал
+# с CRLF, под Linux/macOS с LF, и update на CI переиндексировал файл. -text отключает
+# любую конверсию: в рабочем дереве те же байты, что в репозитории, на любой ОС.
+tests/fixtures/sample_repo/** -text

codebase_index-2.1.0/.github/ISSUE_TEMPLATE/benchmark_report.yml

@@ -0,0 +1,62 @@
+name: Benchmark report
+description: Share a reproduced, failed, or new benchmark run (good or bad numbers both welcome)
+title: "[Benchmark]: "
+labels: ["benchmark"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Independent runs are how this project keeps its numbers honest. Unflattering results are as useful as flattering ones.
+
+  - type: dropdown
+    id: kind
+    attributes:
+      label: What did you run?
+      options:
+        - tests/eval/run_eval.py (retrieval eval, own corpus)
+        - tests/eval/run_eval.py (shipped query sets)
+        - tests/benchmark_public.py (synthetic suite)
+        - tests/benchmark_honest.py (index vs rg+window)
+        - Something else (describe below)
+    validations:
+      required: true
+
+  - type: input
+    id: version
+    attributes:
+      label: codebase-index version / commit
+      placeholder: "1.9.0 or git SHA"
+    validations:
+      required: true
+
+  - type: input
+    id: corpus
+    attributes:
+      label: Corpus
+      description: Public repository URL + commit SHA, or language / size if private.
+      placeholder: "https://github.com/pallets/flask @ d318b68 — Python, ~18k LOC"
+    validations:
+      required: true
+
+  - type: textarea
+    id: command
+    attributes:
+      label: Exact commands
+      render: shell
+    validations:
+      required: true
+
+  - type: textarea
+    id: results
+    attributes:
+      label: Results table / raw output
+      description: Paste the pooled table and significance rows as printed. Attach the JSON if large.
+      render: markdown
+    validations:
+      required: true
+
+  - type: textarea
+    id: notes
+    attributes:
+      label: Observations
+      description: Anything surprising, queries that failed, or where the baseline beat the index.

codebase_index-2.1.0/.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,74 @@
+name: Bug report
+description: Something is wrong, crashes, or returns the wrong result
+title: "[Bug]: "
+labels: ["bug", "triage"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks. A reproducible report gets fixed fastest. Do not paste real secrets — the tool redacts snippets, your logs may not.
+
+  - type: input
+    id: version
+    attributes:
+      label: codebase-index version
+      description: "`pip show codebase-index` (there is no --version flag)"
+      placeholder: "1.9.0"
+    validations:
+      required: true
+
+  - type: input
+    id: env
+    attributes:
+      label: Python and OS
+      placeholder: "Python 3.12.3 · macOS 14.4 / Ubuntu 24.04 / Windows 11"
+    validations:
+      required: true
+
+  - type: dropdown
+    id: surface
+    attributes:
+      label: Surface
+      options:
+        - CLI
+        - Claude Code skill / plugin
+        - Codex CLI
+        - OpenCode
+        - MCP server
+        - Installer scripts
+        - Other
+    validations:
+      required: true
+
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: What happened, and what did you expect?
+      placeholder: |
+        Ran `codebase-index refs open_session --json` on <repo>. Expected the call in ctx.py; got an empty list with coverage.partial=false.
+    validations:
+      required: true
+
+  - type: textarea
+    id: repro
+    attributes:
+      label: Steps to reproduce
+      description: Ideally against a public repository or a tiny snippet we can index.
+      placeholder: |
+        1. git clone https://github.com/... && cd ...
+        2. codebase-index index
+        3. codebase-index search "..." --json
+    validations:
+      required: true
+
+  - type: textarea
+    id: doctor
+    attributes:
+      label: "`codebase-index doctor` output"
+      render: shell
+
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant output (`--json` where applicable) or traceback
+      render: shell

codebase_index-2.1.0/.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,8 @@
+blank_issues_enabled: false
+contact_links:
+  - name: Questions and ideas
+    url: https://github.com/denfry/codebase-index/discussions
+    about: Ask how to use the tool, discuss design, or share what you built with it.
+  - name: Security vulnerability
+    url: https://github.com/denfry/codebase-index/security/advisories/new
+    about: Report privately. Please do not open a public issue (see SECURITY.md).

codebase_index-2.1.0/.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,50 @@
+name: Feature request
+description: Propose an improvement or a new capability
+title: "[Feature]: "
+labels: ["enhancement", "triage"]
+body:
+  - type: textarea
+    id: problem
+    attributes:
+      label: Problem
+      description: What are you trying to do with your agent that the tool makes hard today?
+      placeholder: "When I ask Claude Code about ..., codebase-index returns ..., so the agent ends up reading ..."
+    validations:
+      required: true
+
+  - type: textarea
+    id: proposal
+    attributes:
+      label: Proposal
+      description: What should happen instead? A CLI example or a sketch of the JSON is ideal.
+    validations:
+      required: true
+
+  - type: dropdown
+    id: area
+    attributes:
+      label: Area
+      options:
+        - Retrieval quality (ranking, fusion, budget)
+        - Graph extraction (edges, impact, paths)
+        - Language support
+        - Indexing (discovery, parsing, freshness)
+        - CLI / output format
+        - MCP server
+        - Claude Code / Codex / OpenCode integration
+        - Benchmarks / evaluation
+        - Documentation
+        - Other
+    validations:
+      required: true
+
+  - type: textarea
+    id: evidence
+    attributes:
+      label: How would we know it worked?
+      description: Retrieval changes need a measurable effect (see tests/eval). A query and the file you expected is enough to start.
+
+  - type: textarea
+    id: alternatives
+    attributes:
+      label: Alternatives or workarounds you tried