opencode-semantic-memory 0.7.1__tar.gz → 0.8.2__tar.gz

opencode_semantic_memory-0.8.2/.cache/pip/http-v2/2/e/b/6/a/2eb6afae3ceaa5367896f67f058455efab497b680ac114e94caa3e10.body

@@ -0,0 +1,79 @@
+Metadata-Version: 2.4
+Name: hatchling
+Version: 1.30.1
+Summary: Modern, extensible Python build backend
+Project-URL: Homepage, https://hatch.pypa.io/latest/
+Project-URL: Sponsor, https://github.com/sponsors/ofek
+Project-URL: History, https://hatch.pypa.io/dev/history/hatchling/
+Project-URL: Tracker, https://github.com/pypa/hatch/issues
+Project-URL: Source, https://github.com/pypa/hatch/tree/master/backend
+Author-email: Ofek Lev <oss@ofek.dev>
+License-Expression: MIT
+License-File: LICENSE.txt
+Keywords: build,hatch,packaging
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Natural Language :: English
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Classifier: Topic :: Software Development :: Build Tools
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Requires-Dist: packaging>=24.2
+Requires-Dist: pathspec>=0.10.1
+Requires-Dist: pluggy>=1.0.0
+Requires-Dist: tomli>=1.2.2; python_version < '3.11'
+Requires-Dist: trove-classifiers
+Description-Content-Type: text/markdown
+
+# Hatchling
+
+<div align="center">
+
+<img src="https://raw.githubusercontent.com/pypa/hatch/master/docs/assets/images/logo.svg" alt="Hatch logo" width="500" role="img">
+
+| | |
+| --- | --- |
+| Package | [![PyPI - Version](https://img.shields.io/pypi/v/hatchling.svg?logo=pypi&label=PyPI&logoColor=gold)](https://pypi.org/project/hatchling/) [![PyPI - Downloads](https://img.shields.io/pypi/dm/hatchling.svg?color=blue&label=Downloads&logo=pypi&logoColor=gold)](https://pypi.org/project/hatchling/) [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/hatchling.svg?logo=python&label=Python&logoColor=gold)](https://pypi.org/project/hatchling/) |
+| Meta | [![Hatch project](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pypa/hatch/master/docs/assets/badge/v0.json)](https://github.com/pypa/hatch) [![linting - Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff) [![code style - Black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black) [![types - Mypy](https://img.shields.io/badge/types-Mypy-blue.svg)](https://github.com/python/mypy) [![License - MIT](https://img.shields.io/badge/license-MIT-9400d3.svg)](https://spdx.org/licenses/) [![GitHub Sponsors](https://img.shields.io/github/sponsors/ofek?logo=GitHub%20Sponsors&style=social)](https://github.com/sponsors/ofek) |
+
+</div>
+
+-----
+
+This is the extensible, standards compliant build backend used by [Hatch](https://github.com/pypa/hatch).
+
+## Usage
+
+The following snippet must be present in your project's `pyproject.toml` file in order to use Hatchling as your build backend:
+
+```toml
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+```
+
+Then a build frontend like [pip](https://github.com/pypa/pip), [build](https://github.com/pypa/build), or Hatch itself can build or install your project automatically:
+
+```console
+# install using pip
+pip install /path/to/project
+
+# build
+python -m build /path/to/project
+
+# build with Hatch
+hatch build /path/to/project
+```
+
+## Documentation
+
+- [Project metadata](https://hatch.pypa.io/latest/config/metadata/)
+- [Dependencies](https://hatch.pypa.io/latest/config/dependency/)
+- [Packaging](https://hatch.pypa.io/latest/config/build/)

opencode_semantic_memory-0.8.2/.cache/pip/http-v2/8/3/a/9/9/83a99ac063795cf6d06df343c06449f8777237c8c3ad06917c4344ef.body

@@ -0,0 +1,155 @@
+Metadata-Version: 2.4
+Name: idna
+Version: 3.18
+Summary: Internationalized Domain Names in Applications (IDNA)
+Author-email: Kim Davies <kim+pypi@gumleaf.org>
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-Expression: BSD-3-Clause
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: System Administrators
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Classifier: Topic :: Internet :: Name Service (DNS)
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Utilities
+License-File: LICENSE.md
+Requires-Dist: ruff >= 0.6.2 ; extra == "all"
+Requires-Dist: mypy >= 1.11.2 ; extra == "all"
+Requires-Dist: pytest >= 8.3.2 ; extra == "all"
+Project-URL: Changelog, https://github.com/kjd/idna/blob/master/HISTORY.md
+Project-URL: Issue tracker, https://github.com/kjd/idna/issues
+Project-URL: Source, https://github.com/kjd/idna
+Provides-Extra: all
+
+# Internationalized Domain Names in Applications (IDNA)
+
+Support for [Internationalized Domain Names in Applications
+(IDNA)](https://tools.ietf.org/html/rfc5891) and [Unicode IDNA
+Compatibility Processing](https://unicode.org/reports/tr46/). It
+supersedes the standard library's `encodings.idna`, which only
+implements the 2003 specification, offering broader script coverage and
+limiting domains with known security vulnerabilities.
+
+## Usage
+
+Package may be installed from [PyPI](https://pypi.org/project/idna/) via
+the typical methods (e.g. `python3 -m pip install idna`)
+
+For typical usage, the `encode` and `decode` functions will take a
+domain name argument and perform a conversion to ASCII-compatible encoding
+(known as A-labels), or to Unicode strings (known as U-labels)
+respectively.
+
+```pycon
+>>> import idna
+>>> idna.encode('ドメイン.テスト')
+b'xn--eckwd4c7c.xn--zckzah'
+>>> print(idna.decode('xn--eckwd4c7c.xn--zckzah'))
+ドメイン.テスト
+```
+
+Conversions can be applied at a per-label basis using the `ulabel` or
+`alabel` functions for specialized use cases.
+
+
+### Compatibility Mapping (UTS #46)
+
+This library provides support for [Unicode IDNA Compatibility
+Processing](https://unicode.org/reports/tr46/) which normalizes input from
+different potential ways a user may input a domain prior to performing the IDNA
+conversion operations. This functionality, known as a
+[mapping](https://tools.ietf.org/html/rfc5895), is considered by the
+specification to be a local user-interface issue distinct from IDNA
+conversion functionality.
+
+For example, "Königsgäßchen" is not a permissible label as capital letters
+are not allowed. UTS 46 will convert this into lower case prior to applying
+the IDNA conversion.
+
+```pycon
+>>> import idna
+>>> idna.encode('Königsgäßchen')
+...
+idna.core.InvalidCodepoint: Codepoint U+004B at position 1 of 'Königsgäßchen' not allowed
+>>> idna.encode('Königsgäßchen', uts46=True)
+b'xn--knigsgchen-b4a3dun'
+>>> idna.decode('xn--knigsgchen-b4a3dun')
+'königsgäßchen'
+```
+
+When performing a decode operation for display purposes, `decode()`
+accepts a `display=True` argument that leaves any `xn--` label that
+fails to decode unchanged. This is useful for user interface display
+where a domain is in use, the A-label form can be presented when it
+is not a valid IDN.
+
+
+## Exceptions
+
+All errors raised during conversion derive from the `idna.IDNAError`
+base class. The more specific exceptions are:
+
+* `idna.IDNABidiError` — raised when a label contains an illegal
+  combination of left-to-right and right-to-left characters.
+* `idna.InvalidCodepoint` — raised when a label contains a codepoint
+  that is INVALID for IDNA.
+* `idna.InvalidCodepointContext` — raised when a CONTEXTO or CONTEXTJ
+  codepoint appears in a position whose contextual requirements are
+  not satisfied.
+
+
+## Command-line tool
+
+The package supports command-line usage to convert domain names
+between their Unicode and ASCII-compatible forms. It can be run either
+as a module (`python3 -m idna`) or, once installed (such as with `uv
+tool` or `pipx`), via the `idna` script:
+
+```bash
+$ uv tool install idna
+$ idna xn--e1afmkfd.xn--p1ai
+пример.рф
+$ idna пример.рф
+xn--e1afmkfd.xn--p1ai
+```
+
+Mode can be specified with `-e`/`--encode` or `-d`/`--decode`, otherwise
+it will be chosen automatically based on the first input. Multiple
+domains can be supplied either as arguments or through standard input.
+UTS #46 mapping is applied by default, which lets the tool accept
+inputs that aren't strictly valid IDNA 2008 by normalising them first,
+pass `--strict` to disable UTS #46.
+
+Conversion failures are reported on stderr together with the
+offending input; processing continues with the remaining domains and
+the tool exits with a non-zero status if any conversion failed.
+
+
+## Additional Notes
+
+* **Version support**. This library supports Python 3.9 and higher.
+  As this library serves as a low-level toolkit for a variety of
+  applications, we strive to support all versions of Python that are
+  not beyond end-of-life.
+
+* **Emoji**. It is an occasional request to support emoji domains in
+  this library. Encoding of symbols like emoji is expressly prohibited by
+  the IDNA technical standard, and emoji domains are broadly phased
+  out across the domain industry due to associated security risks.
+
+* **Regenerating lookup tables**. The IDNA and UTS 46 functionality
+  relies upon pre-calculated lookup tables, generated using the
+  `idna-data` script in [`tools/`](tools/README.md).
+

opencode_semantic_memory-0.8.2/.cache/pip/http-v2/f/2/d/a/b/f2dabcdf97e445f98036aadbe7dddc4c9ecb47a8a60783427f548b2c.body

@@ -0,0 +1,82 @@
+Metadata-Version: 2.4
+Name: trove-classifiers
+Version: 2026.6.1.19
+Summary: Canonical source for classifiers on PyPI (pypi.org).
+Home-page: https://github.com/pypa/trove-classifiers
+Author: The PyPI Admins
+Author-email: admin@pypi.org
+Keywords: classifiers
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Typing :: Typed
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license-file
+Dynamic: summary
+
+Canonical source for [classifiers][1] on [PyPI][2].
+
+Classifiers [categorize projects][3] per [PEP 301][4]. Use this package to
+validate classifiers in packages for PyPI upload or download.
+
+## Usage
+
+To install [from PyPI][5]:
+
+```
+$ pip install trove-classifiers
+```
+
+This package can be invoked as a module to print a list of classifiers:
+
+```
+$ python -m trove_classifiers | grep -Ei pyramid
+Framework :: Pyramid
+```
+
+In addition, this package's API is two importable objects:
+
+### Classifiers (`trove_classifiers.classifiers`)
+A `set` containing classifiers (as strings). Useful for determining membership.
+
+Example - determine if a classifier is valid:
+
+```python
+>>> from trove_classifiers import classifiers
+>>> 'License :: OSI Approved' in classifiers
+True
+>>> 'Fuzzy :: Wuzzy :: Was :: A :: Bear' in classifiers
+False
+>>>
+```
+
+### Deprecated classifiers (`trove_classifiers.deprecated_classifiers`)
+A `dict`, mapping a deprecated classifier (string) to a list of classifiers
+which replaces it (strings).
+
+Example - determine if a classifier is deprecated:
+
+```python
+>>> from trove_classifiers import deprecated_classifiers
+>>> 'License :: OSI Approved' in deprecated_classifiers
+False
+>>> 'Natural Language :: Ukranian' in deprecated_classifiers
+True
+>>> deprecated_classifiers["Natural Language :: Ukranian"]
+['Natural Language :: Ukrainian']
+```
+
+[1]: https://pypi.org/classifiers/
+[2]: https://pypi.org
+[3]: https://packaging.python.org/specifications/core-metadata/#classifier-multiple-use
+[4]: https://www.python.org/dev/peps/pep-0301/
+[5]: https://pypi.org/project/trove-classifiers/

{opencode_semantic_memory-0.7.1 → opencode_semantic_memory-0.8.2}/CHANGELOG.md

@@ -7,6 +7,30 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.8.0] - 2026-06-02
+
+### Added
+
+- **GitLab bulk ingest** - Optional indexing of an entire GitLab project's issues and
+  merge requests into a **separate** database (SQLite + LanceDB) for weak semantic matching
+  in `memory_recall`. Fully isolated from the main memory store and gated by config + DB
+  presence, so it can be disabled or deleted without affecting personal memories.
+  - Rate-limited, resumable GitLab API fetcher (title, description, labels, state, dates).
+  - Local keyword extraction (top ~50 keywords per entity; stop words, URLs, @mentions, and
+    paths stripped). No LLM required.
+  - Local embeddings (`all-MiniLM-L6-v2`) over title + description + labels.
+  - Results merge into `memory_recall` weighted `0.8` vs personal memories, plus a small
+    keyword-overlap boost (`0.1 * overlapping_keywords`).
+  - CLI: `bulk-ingest config/fetch/index/sync/status/enable/disable`.
+  - Documented activation, configuration, and data isolation in the README.
+
+### Changed
+
+- **Bulk-ingest fetcher** - Retry-with-backoff on transient errors (408/429/5xx and network
+  timeouts) with exponential backoff honoring `Retry-After`; client timeout raised 30s -> 60s.
+- **Bulk-ingest indexing** - Resume support (skips already-embedded entities; `--reindex` to
+  force), configurable encode batch size, and full-core torch threading for faster builds.
+
 ## [0.7.1] - 2026-06-01
 
 ### Fixed

{opencode_semantic_memory-0.7.1 → opencode_semantic_memory-0.8.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opencode-semantic-memory
-Version: 0.7.1
+Version: 0.8.2
 Summary: Persistent semantic memory system for OpenCode sessions
 Author-email: Gregory Havenga <ghavenga@gitlab.com>
 License-Expression: MIT
@@ -59,6 +59,7 @@ opencode-memory is an MCP (Model Context Protocol) server that provides long-ter
 - **Memory age**: All outputs show age (`now`, `5m`, `2h`, `3d`, `2w`, `1mo`, `2y`) to identify potentially outdated information
 - **Proactive context injection**: Automatically injects relevant memories before each LLM call (OpenCode only, via plugin)
 - **Agent-agnostic LLM support**: Works with OpenCode, Claude CLI, GitLab Duo, Ollama, or custom commands
+- **GitLab bulk ingest (optional)**: Index an entire GitLab project's issues and MRs into a separate database for weak semantic matching in `memory_recall`
 
 ## Prerequisites
 
@@ -171,6 +172,41 @@ args = ["--prompt"]  # prompt is appended after these args
 
 **Note:** The proactive context injection feature (automatic memory loading) currently only works with OpenCode via the plugin system. Other LLM providers can still use all memory tools manually.
 
+## Updating
+
+To update an existing installation, re-run the quick install script. It is idempotent and will pull the latest code, refresh dependencies, and restart the background services:
+
+```bash
+curl -fsSL https://gitlab.com/ghavenga/opencode-memory/-/raw/master/scripts/setup.sh | bash
+```
+
+The update is **non-destructive** for your data:
+
+- Your memory database at `~/.local/share/opencode-memory/memory.db` is not touched
+- Your vector store at `~/.local/share/opencode-memory/vectors/` is not touched
+- Your existing `~/.config/opencode-memory/config.toml` is preserved (the script only writes a default if one does not already exist)
+
+The script's `rm -rf` operations are scoped to the install directory (`~/.local/share/opencode-memory-install`) and only trigger when the git checkout or virtual environment is in a broken state. Any uncommitted local changes inside the install directory will be discarded (`git reset --hard` + `git clean -fd`) before the pull.
+
+If you want to be extra cautious before a major update, snapshot the data directory first:
+
+```bash
+# Consistent SQLite backup (handles WAL files correctly)
+TS=$(date +%Y%m%d-%H%M%S)
+BACKUP_DIR="$HOME/.local/share/opencode-memory-backups/$TS"
+mkdir -p "$BACKUP_DIR"
+sqlite3 "$HOME/.local/share/opencode-memory/memory.db" ".backup '$BACKUP_DIR/memory.db'"
+cp -R "$HOME/.local/share/opencode-memory/vectors" "$BACKUP_DIR/vectors"
+cp "$HOME/.config/opencode-memory/config.toml" "$BACKUP_DIR/config.toml"
+```
+
+After the update, verify the service is healthy:
+
+```bash
+curl -s http://127.0.0.1:9824/health
+# {"status":"ok","server":"opencode-memory","daemon":{"running":true}}
+```
+
 ## Quick Start
 
 ### 1. Start the Memory Services
@@ -262,6 +298,10 @@ The setup script automatically builds and configures the plugin if Node.js 20+ i
 3. Context is injected into the system prompt before LLM call
 4. AI sees relevant history automatically
 
+**Thinking-aware injection:** The plugin also analyzes the assistant's responses to inject context mid-conversation. If the AI is "thinking" about a topic it has prior knowledge of, relevant memories are injected before the next LLM call.
+
+**Relevance filtering:** Items with semantic similarity below 0.35 are filtered out to reduce noise. This threshold was tuned based on effectiveness analysis showing low-relevance items had 0% actual usefulness.
+
 **Note:** If you're using a different LLM provider (Claude, Duo, Ollama), you'll need to call memory tools explicitly - proactive injection only works with the OpenCode plugin.
 
 For more details, see the [plugin documentation](plugin/README.md).
@@ -411,7 +451,8 @@ Work item queue for tracking todos, MRs to review, and authored MRs. Supports P0
 
 | Tool | Description |
 |------|-------------|
-| `memory_effectiveness_report(days?)` | Memory usage patterns and suggestions |
+| `memory_effectiveness_report(days?)` | Memory usage patterns, injection effectiveness, and suggestions |
+| `memory_injection_metrics_trend(days?)` | Daily injection metrics over time for tracking improvements |
 | `memory_background_report(days?)` | Background process activity |
 | `memory_tool_metrics(action?, since_hours?)` | MCP tool call timing metrics |
 | `memory_vector_index(action?)` | Manage vector search index |
@@ -427,6 +468,89 @@ Work item queue for tracking todos, MRs to review, and authored MRs. Supports P0
 | `memory_memory_status()` | Check system health and queue status |
 | `memory_get_proactive_context(query, entities?, project?)` | Get context for proactive injection (plugin use) |
 
+## GitLab Bulk Ingest (Optional)
+
+Bulk ingest indexes **all issues and merge requests** from a GitLab project (default: `gitlab-org/gitlab`) into a **separate** database, so `memory_recall` can surface related upstream issues/MRs alongside your personal memories.
+
+It is fully isolated from your main memory: a dedicated SQLite DB and vector store that can be disabled or deleted at any time without affecting your memories.
+
+### How it works
+
+1. **Fetch** - pulls issue/MR metadata (title, description, labels, state, dates) via the GitLab API, rate-limited and resumable.
+2. **Keywords** - extracts the top ~50 keywords per entity (stop words, URLs, @mentions, and paths stripped). No LLM required.
+3. **Index** - embeds title + description + labels with the same local `all-MiniLM-L6-v2` model used for memories.
+4. **Search** - results merge into `memory_recall`, scored by vector similarity (weighted `0.8` vs personal memories) plus a small keyword-overlap boost (`0.1 * overlapping_keywords`).
+
+All processing is local. The only network calls are to the GitLab API (fetching metadata) and a one-time embedding-model download.
+
+### Data isolation
+
+| | Main memory | Bulk ingest |
+|---|---|---|
+| SQLite | `~/.local/share/opencode-memory/memory.db` | `~/.local/share/opencode-memory/gitlab-org.db` |
+| Vectors | `~/.local/share/opencode-memory/vectors/` | `~/.local/share/opencode-memory/gitlab-org.lance/` |
+
+Bulk-ingested entities are never written into your main memory DB, knowledge graph, or consolidation/archiving flows. They are a read-time overlay only.
+
+### Activation
+
+```bash
+# 1. Create the config file (~/.config/opencode-memory/bulk_ingest.toml)
+opencode-memory bulk-ingest config --init
+
+# 2. Fetch all issues + MRs (resumable; safe to re-run if interrupted)
+#    For gitlab-org/gitlab this is ~580K entities and takes ~2 hours.
+GITLAB_TOKEN=<your-token> opencode-memory bulk-ingest fetch
+
+# 3. Build the vector index (embeds locally; ~3 hours for 580K on CPU)
+opencode-memory bulk-ingest index --create-index
+
+# 4. Check progress / counts at any time
+opencode-memory bulk-ingest status
+```
+
+Once indexed, results appear automatically in `memory_recall` with `match_type: "bulk_ingest"` and a `bulk_ingest:<project>#<iid>` source.
+
+### CLI commands
+
+| Command | Description |
+|---------|-------------|
+| `bulk-ingest config --init` | Create the default config file |
+| `bulk-ingest fetch` | Fetch issue/MR metadata (resumable) |
+| `bulk-ingest index --create-index` | Embed entities and build the IVF-PQ search index |
+| `bulk-ingest index --reindex` | Re-embed everything (default skips already-indexed) |
+| `bulk-ingest sync` | Incremental fetch of entities updated since last run |
+| `bulk-ingest status` | Show entity counts, tiers, and DB size |
+| `bulk-ingest enable` / `disable` | Toggle inclusion in `memory_recall` |
+
+### Configuration
+
+Key settings in `~/.config/opencode-memory/bulk_ingest.toml`:
+
+```toml
+[gitlab]
+project = "gitlab-org/gitlab"   # any project path
+api_rate_limit = 100            # requests per minute
+
+[query]
+enabled = true                  # include results in memory_recall
+relevance_weight = 0.8          # discount vs personal memories
+
+[summarizer]
+enabled = false                 # LLM summaries are OPTIONAL and off by default
+provider = "none"               # title + description is enough for search
+```
+
+> **Note:** LLM summarization is optional and disabled by default. Avoid the `opencode` summarizer provider - it has MCP access and would write entries into your main memory DB.
+
+### Disabling
+
+```bash
+opencode-memory bulk-ingest disable        # stop including in recall (keeps data)
+# or remove the data entirely:
+rm -rf ~/.local/share/opencode-memory/gitlab-org.db ~/.local/share/opencode-memory/gitlab-org.lance
+```
+
 ## Memory Categories
 
 | Category | Use For |