teddi-tool 2026.11.1__tar.gz

teddi_tool-2026.11.1/.agents/FILES.md

@@ -0,0 +1,42 @@
+# AGENTS.md — FILES
+
+Single source of truth for paths, config keys, and naming conventions.
+Kept compact — agents hallucinate less when they know where definitions live.
+
+## Pattern
+
+- One file owns each class of definition (paths, config defaults, enums).
+- Import from that file. Never hard-code values in other modules.
+- Variables that address files get `_file` suffix; directories get `_dir`.
+
+## Project-specific sources of truth
+
+| What | Where | Key names |
+|------|-------|-----------|
+| Pydantic models & enums | `src/teddi_tool/models.py` | `SearchIn`, `SearchPattern`, `TechnicalBody`, `OutputFormat`, `SearchRequest`, `SearchResponse`, `TermResult`, `DocumentRef` |
+| TEDDI endpoint URL | `src/teddi_tool/client.py:21` | `TEDDI_SEARCH_URL` = `https://webapp.etsi.org/Teddi/Main.asp` |
+| Enum → TEDDI form values | `src/teddi_tool/client.py:24`–`35` | `SEARCH_IN_TO_PARAM`, `SEARCH_PATTERN_TO_PARAM` |
+| TEDDI form field names | `src/teddi_tool/client.py:124`–`140` | `qWhatToSearch`, `qWhereOption`, `qWhatOption`, `qShowTBs` |
+| HTTP session + cache | `src/teddi_tool/http_client.py:13` | `create_cached_teddi_async_client(cache_dir=None, cache_ttl=7200)`; DB `.cache/teddi_http.sqlite3` |
+| HTML → models | `src/teddi_tool/parser.py:17` | `parse_teddi_response(html_content)` |
+| Source protocol / client | `src/teddi_tool/client.py:38`, `:75` | `TeddiSource`, `TeddiClient` |
+| Shared search + output | `src/teddi_tool/search_utils.py` | `execute_search`, `execute_list_bodies`, `build_results_payload`, `parse_technical_bodies`, `serialize_payload`, `render_table` |
+| Shared CLI options | `src/teddi_tool/cli/args.py` | `TermArgument`, `ScopeOption`, `PatternOption`, `TechnicalBodiesOption`, `OutputOption` |
+| CLI app and commands | `src/teddi_tool/cli/app.py`, `src/teddi_tool/cli/commands.py` | `search-term`, `list-bodies`, `server` commands |
+| MCP server & tools | `src/teddi_tool/server.py` | `search_teddi`, `get_term_info`, `list_technical_bodies` |
+| Console scripts | `pyproject.toml` → `[project.scripts]` | `teddi-tool`, `teddi`, `teddi-cli`, `teddi-mcp` |
+| Lint/format defaults | `ruff.toml` | `line-length = 100`, `target-version = "py313"`, Google docstrings |
+| Type-check defaults | `ty.toml` | `python-version = "3.13"`, `error-on-warning = true` |
+| Test config | `pyproject.toml` → `[tool.pytest.ini_options]`, `[tool.coverage.*]` | `asyncio_mode = "auto"`, `testpaths = ["tests"]` |
+| Test fixtures | `tests/fixtures/` (`.gitkeep`) | Reserved for reused TEDDI HTML payloads; exposed as the `test_data_dir` fixture in `tests/conftest.py` |
+| Task definitions | `.config/mise/config.toml`, `.config/mise/conf.d/*.toml` | `dev`, `test`, `lint`, `lint-check`, `typecheck`, `spell`, `format`, `format-md`, `docs`, `all`, `release-notes` |
+| Release automation | `.github/workflows/{ci,docs,release}.yml`, `scripts/release_notes.py` | CI matrix, Pages deploy, tag release + PyPI trusted publishing, LLM notes |
+| Project version | `src/teddi_tool/__about__.py`, git tag | dynamic versioning (`uv-dynamic-versioning`) |
+| Docs site | `zensical.toml`, `docs/` | nav, site URL, mkdocstrings config |
+| Project skills | `skills/cli-teddi/SKILL.md`, `skills/mcp-teddi/SKILL.md` | — |
+| User docs | `docs/index.md`, `docs/usage.md`, `docs/reference/api.md`, `docs/development.md` | — |
+
+## Subdirectory
+
+If this file grows past its size budget, split detail into
+`.agents/files/<name>.md` — every file there MUST be listed above.

teddi_tool-2026.11.1/.agents/HISTORY.md

@@ -0,0 +1,54 @@
+# AGENTS.md — HISTORY
+
+State file. The one file that may reference the past — sparingly. Read when
+relevant to the current task; long-term memory for decisions, not a log.
+Routine history lives in git; only record what is costly to rediscover.
+
+## Format
+
+| Date | Decision | Rationale | Git ref |
+| ---- | -------- | --------- | ------- |
+| YYYY-MM-DD | [description] | [why] | [commit hash/tag] |
+
+## Record
+
+- High-level architectural decisions and breaking changes.
+- Dependency, tooling, and platform choices — including the alternative that lost.
+- False turns and rejected approaches, with the reason.
+- Completion of an implementation plan (link to its archive below).
+
+## Do not record
+
+- Routine commits, refactor logs, session activity, release notes.
+- Anything obvious from git, the code, or current AGENTS.md/state files.
+
+## Guidance
+
+- Keep entries brief — enough to reconstruct the reasoning.
+- Link to the relevant commits or tags.
+- If this file grows large, move older entries to `.agents/history/` and keep
+  a pointer here.
+- Completed implementation plans are archived as single files at
+  `.agents/history/<YYYY-MM-DD-plan-name>.md` and linked from the decision
+  entry they belong to. The trigger to archive is **plan completion**, not
+  file growth — see `.agents/policies/plans-and-docs.md`.
+
+## Decisions
+
+| Date | Decision | Rationale | Git ref |
+| ---- | -------- | --------- | ------- |
+| 2026-03-19 | Repository split out of `tdoc-crawler` into a standalone `teddi-mcp` package | TEDDI lookup had no dependency on the 3GPP tdoc crawler; separate release and packaging | `08a2984` |
+| 2026-03-20 | Lint and type-check config moved out of `pyproject.toml` into `ruff.toml` and `ty.toml` | Dedicated tool config files keep `pyproject.toml` about packaging; `ty.toml` enables `error-on-warning` | `3075a71` |
+| 2026-03-20 | Task/tool config consolidated under `.config/mise/` with per-topic `conf.d/*.toml` | One task runner (`mise`) for format, lint, quality, skills, MCP registration instead of ad-hoc scripts | `d0a0208` |
+| 2026-11-10 | Adopted the agents-scaffold DOX hierarchy; root `AGENTS.md` reduced to rail + state-file index | Old `AGENTS.md` was a 96-line design document injected on every call; content moved into `.agents/` and `src/teddi_tool/AGENTS.md` | uncommitted at adoption |
+| 2026-11-10 | Dropped `refresh_ttl_on_access` from `create_cached_teddi_async_client`; hishel 2.x TTL is fixed at write time | The keyword no longer exists in `hishel.AsyncSqliteStorage` (it raised `TypeError` on every cache-backed client), and 2.x exposes no refresh-on-access API | uncommitted |
+| 2026-11-11 | Renamed distribution/package to `teddi-tool` / `teddi_tool` and adopted the copier-uv-plus template (Cyclopts CLI, Zensical docs, GitHub Actions, tag versioning) | The project is a CLI as well as an MCP server; `teddi-mcp` misrepresented it. `teddi-tool` and the other candidate names are free on PyPI; `teddi` is taken | see migration commits |
+
+## Archived plans
+
+None yet. Completed plans land in `.agents/history/<YYYY-MM-DD-plan-name>.md`.
+
+## Archive a plan
+
+Procedure, naming, and the completion trigger — see
+`.agents/policies/plans-and-docs.md` → Archive a plan.

teddi_tool-2026.11.1/.agents/MAINTENANCE.md

@@ -0,0 +1,37 @@
+# AGENTS.md — MAINTENANCE
+
+How to keep `.agents/` files current.
+
+## Process
+
+1. When a rule changes, update the owning file — never another file.
+2. When adding a new state file or directory under `.agents/`, add it to the
+   index table in root `AGENTS.md` and to **File update triggers** below.
+3. After any `.agents/` change, check the index for stale entries.
+
+## Principles
+
+- **Single source of truth.** Each rule lives in exactly one file. The tier,
+  pointer, rationale, and size rules are in **DOX authoring**
+  (`.agents/policies/dox-authoring.md`) — consult it on every DOX change.
+- **AGENTS.md is an index.** It points to `.agents/` files, does not replace them.
+- **No logbooks.** State files describe current contracts; git owns history — see `.agents/POLICIES.md`.
+- **State files stay lean.** When a file approaches its size budget, split
+  detail into the matching subdirectory (`.agents/files/`, `.agents/policies/`,
+  `.agents/tools/`, `.agents/maintenance/`) — every file there MUST be listed
+  in its state file.
+
+## File update triggers
+
+| File / Dir | Update when |
+| ------------ | ------------- |
+| `ONBOARDING.md` | Project structure, tooling, or entry points change |
+| `POLICIES.md` | Boundaries, priorities, or verification change |
+| `FILES.md` | Path constants, config keys, or naming conventions change |
+| `TOOLS.md` | Tools, MCP servers, skills, or CLIs added, removed, or changed |
+| `HISTORY.md` | Notable decision made or resolved |
+| `MAINTENANCE.md` | Maintenance procedures, triggers, or principles change |
+| `plans/` | New feature implementation starts |
+| `history/` | HISTORY.md overflow or completed plans archived |
+| `files/`, `policies/`, `tools/`, `maintenance/` | State files split into subdirectories |
+| `../src/teddi_tool/AGENTS.md`, `../tests/AGENTS.md` | Module layout, contracts, or test conventions change |

teddi_tool-2026.11.1/.agents/ONBOARDING.md

@@ -0,0 +1,68 @@
+# AGENTS.md — ONBOARDING
+
+Read this when starting a new session. After first read, only revisit when
+project structure or tooling changes significantly.
+
+## Project
+
+`teddi-tool` — Cyclopts CLI and FastMCP server for ETSI TEDDI term/abbreviation
+lookup. Distributed on PyPI, documented at
+<https://jr2804.github.io/teddi-tool/>. Full docs at `README.md` and `docs/`.
+
+## Quick start
+
+```bash
+mise install                        # pinned tools (uv, ruff, ty, rumdl, ...)
+mise dev                            # uv sync -U --dev --all-extras --all-groups
+mise test                           # pytest with coverage
+mise lint                           # ruff check --fix --unsafe-fixes
+mise lint-check                     # ruff check (CI mode)
+mise typecheck                      # ty check
+mise spell                          # codespell
+mise format                         # pyreorder + ruff format + import sort
+mise docs                           # zensical build
+mise all                            # everything above
+```
+
+Direct commands also work: `uv run pytest tests/ -v`, `uv run ruff check
+src/ tests/`, `uv run ty check`.
+
+## Entry points (read these first)
+
+| File | Why |
+|------|-----|
+| `AGENTS.md` | Root rail — rules + `.agents/` index |
+| `.agents/POLICIES.md` | Boundaries, priorities, verification |
+| `.agents/FILES.md` | Source-of-truth locations |
+| `src/teddi_tool/AGENTS.md` | Contracts for the package you are editing |
+| `tests/AGENTS.md` | Test conventions |
+
+## Where to dig deeper
+
+- `docs/` — `index.md`, `usage.md`, `reference/api.md`, `development.md`
+- `.agents/TOOLS.md` — tools, MCP servers, skills, CLIs in use
+- `.agents/HISTORY.md` — past decisions and rationale
+- `skills/cli-teddi/SKILL.md`, `skills/mcp-teddi/SKILL.md` — task-level usage recipes
+
+## Executables
+
+| Command | Module | Purpose |
+|---------|--------|---------|
+| `teddi-tool`, `teddi` | `src/teddi_tool/cli/app.py` | Search, `list-bodies`, `server` |
+| `teddi-cli` | `src/teddi_tool/cli/app.py` | Alias kept for existing scripts |
+| `teddi-mcp` | `src/teddi_tool/server.py` | MCP server (stdio) |
+
+## Available tools
+
+Development tools, MCP servers, skills, and CLIs are inventoried in the
+state file `.agents/TOOLS.md` — read it before assuming a tool, update it
+when tooling changes. If tooling grows large, detail moves to
+`.agents/tools/<name>.md` (each listed in TOOLS.md).
+
+## Project lifecycle
+
+- Releases: push a `v*` tag; `.github/workflows/release.yml` builds, writes
+  LLM release notes (`scripts/release_notes.py`), creates the GitHub release,
+  and publishes to PyPI via OIDC trusted publishing.
+- Template: generated from copier-uv-plus; `.copier-answers.yml` drives
+  `copier update`.

teddi_tool-2026.11.1/.agents/POLICIES.md

@@ -0,0 +1,87 @@
+# AGENTS.md — POLICIES
+
+Always applicable. Boundaries, priorities, verification, checklist.
+
+Detail files (`.agents/policies/`):
+
+| File | Covers |
+| ---- | ------ |
+| `dox-authoring.md` | Tiering, reference-don't-restate, content rules, state-file subdirectories, size budget |
+| `plans-and-docs.md` | Implementation plans, plan archiving, documentation/history rules |
+
+## Priorities
+
+1. Correctness
+2. Evidence
+3. Safety
+4. Minimal changes
+5. Consistency
+6. Performance
+
+## Boundaries
+
+- NEVER fabricate paths, commits, APIs, config keys, env vars, test results,
+  or benchmark numbers. If you don't know, say so.
+- NEVER guess at command names, flags, or paths. Read source or run `--help`.
+- NEVER add secrets, API keys, or tokens to files. Use env vars.
+- NEVER run destructive commands (`rm -rf`, `git reset --hard`,
+  `git push --force`) without explicit confirmation.
+- NEVER delete or move files without explicit instruction.
+- NEVER create temp files in project root. Use dedicated temp dir.
+
+Project-specific:
+
+- Do not hit the live TEDDI endpoint from tests or automation — mock the
+  `httpx` client (see `tests/AGENTS.md`).
+- Do not commit `.cache/`, `tests/.cache/`, or `.agents/plans/`.
+- TEDDI has no public API contract. Treat the scraped page shape as evidence
+  that must be re-checked, never as prior knowledge.
+
+## Change constraints
+
+- Minimal, surgical edits. Preserve existing style.
+- No new dependencies without explicit instruction.
+- No unrelated refactoring while fixing a bug.
+- A model/enum change is a cross-layer change — see `src/teddi_tool/AGENTS.md`
+  → Work Guidance before editing `src/teddi_tool/models.py`.
+
+## Code quality
+
+Universal defaults. Project-specific standards live in child AGENTS.md.
+
+- **SRP** — one reason to change per module/function.
+- **DRY** — check before adding. Extract on third occurrence (Rule of Three).
+- **Redundant code** — remove dead branches, unreachable conditions, unused
+  params/imports before finishing.
+- **Duplication vs. abstraction** — prefer duplication over wrong premature
+  abstraction.
+- No new code-quality tooling by default — opt in per project.
+
+## Completion checklist
+
+- Change solves the stated problem
+- Relevant validation ran (or gaps stated)
+- No unintended side effects or secrets exposed
+
+## Verification
+
+Run from the repository root:
+
+```bash
+mise test          # pytest with coverage
+mise lint-check    # ruff check (no fixes)
+mise typecheck     # ty check
+mise spell         # codespell
+```
+
+Direct equivalents: `uv run pytest`, `uv run ruff check src/ tests/`,
+`uv run ty check`. `ty.toml` sets `error-on-warning = true`. CI (`.github/workflows/ci.yml`)
+runs `lint-check`, `typecheck`, `spell`, and the test matrix.
+
+## Response format
+
+Concise and specific. No filler, intros, or restated requirements.
+Answer direct questions directly.
+
+For review/debugging/analysis: findings with references, conclusion,
+approach. Mention caveats.

teddi_tool-2026.11.1/.agents/TOOLS.md

@@ -0,0 +1,65 @@
+# AGENTS.md — TOOLS
+
+State file: inventory of tools used in development — CLIs, MCP servers,
+skills, runtimes, and project scripts. Demand-loaded like all state files;
+keep it current (see `.agents/MAINTENANCE.md`).
+
+## Rules
+
+- Use an existing tool before adding a new one. No new tools, MCP servers,
+  skills, or dependencies without explicit instruction (`.agents/POLICIES.md`).
+- Each tool appears exactly once, in its primary table.
+- Tables describe current usage — delete rows when tools leave; this is not a
+  historical log.
+
+## Subdirectory
+
+If this file grows past its size budget, split detail into
+`.agents/tools/<name>.md` — every file there MUST be listed above.
+
+## CLI tools & runtimes
+
+| Tool | When | Purpose |
+| ---- | ---- | ------- |
+| `uv` | Always | Environment sync (`uv sync --dev`) and every command (`uv run …`, `uvx …`) |
+| `mise` | Running project tasks | Toolchain + task runner reading `.config/mise/conf.d/*.toml` |
+| `ruff` | Before finishing any edit | Lint, import sorting, formatting (`ruff.toml`, py313) |
+| `ty` | After changing types or signatures | Static type check (`ty.toml`, warnings are errors) |
+| `pytest` | After behaviour changes | Test suite with coverage; `asyncio_mode = "auto"` |
+| `pyreorder` | `mise format` | Orders class members (public/protected/private) |
+| `rumdl` | `mise format-md` | Markdown lint/format |
+| `codespell` | `mise spell` | Spelling check over `src/ tests/` |
+| `zensical` | `mise docs` | Builds the documentation site (`zensical.toml`) |
+| `bun` / `bun x skills` | `mise add-skills` | Installs agent skills from the CSV catalogue |
+| `bun x add-mcp` | `mise add-mcp-servers <agent>` | Registers MCP servers with an AI client |
+
+## MCP servers
+
+| Server | When | Purpose |
+| ------ | ---- | ------- |
+| `teddi-mcp` (this repo) | Querying TEDDI from an MCP client | Tools `search_teddi`, `get_term_info`, `list_technical_bodies`; stdio transport |
+
+## Skills
+
+| Skill | When | Purpose |
+| ----- | ---- | ------- |
+| `cli-teddi` (`skills/cli-teddi/SKILL.md`) | Terminal TEDDI searches | `uv run teddi-tool search-term|list-bodies` recipes and filters |
+| `mcp-teddi` (`skills/mcp-teddi/SKILL.md`) | MCP-client TEDDI lookups | Tool arguments, TB filtering, multi-definition behaviour |
+
+## Project scripts & tasks
+
+| Command | Purpose |
+| ------- | ------- |
+| `mise dev` | `uv sync -U --dev --all-extras --all-groups` |
+| `mise test` | `uv run pytest --cov=teddi_tool` |
+| `mise lint` | `ruff check src/ tests/ --fix --unsafe-fixes` |
+| `mise lint-check` | `ruff check src/ tests/` (CI mode) |
+| `mise typecheck` | `ty check src/ tests/` |
+| `mise spell` | `codespell src/ tests/` |
+| `mise format` | `pyreorder` + ruff import sort + `ruff format` on `src/ tests/` |
+| `mise format-md` | `rumdl` over Markdown |
+| `mise docs` | `zensical build` |
+| `mise all` | test, lint, spell, format, format-md, docs |
+| `mise release-notes` | `scripts/release_notes.py` via OpenAI-compatible endpoint |
+| `mise clean` | Remove build, coverage, and docs artifacts |
+| `mise add-mcp-servers <agent>` / `mise add-skills` | Install MCP servers / skills from the template catalogues |

teddi_tool-2026.11.1/.agents/policies/dox-authoring.md

@@ -0,0 +1,73 @@
+# AGENTS.md — DOX authoring
+
+Owned by `.agents/POLICIES.md`. How to keep AGENTS.md and state files lean.
+
+AGENTS.md and `.agents/` files share limited context. Bloat and duplication
+are the failure mode.
+
+## Where a rule lives
+
+A rule goes in the **highest (most general) tier that fully applies**:
+
+- Applies to **all code in the project** → `.agents/POLICIES.md` (default).
+- Meaningful **only inside one subtree** → that subtree's `AGENTS.md`.
+- Just helps navigation → the parent's Child DOX Index, nothing else.
+
+## Reference, don't restate
+
+A rule appears in **exactly one file**. Other files use a **pointer line**:
+`<topic> — see <file>`. Never copy the rule, rationale, or example.
+
+## Rule first, rationale second, never third
+
+A DOX line is the rule. If a rationale is costly to rediscover, add one
+short clause. No multi-paragraph explanations or code pairs — those belong
+in a skill or `docs/`, linked once.
+
+## Content rules
+
+- **No tree views.** Generate on demand with `rg --files | tree-cli --fromfile`.
+- **No history in AGENTS.md files.** Git log has routine history. Record only
+  decisions costly to rediscover — in `.agents/HISTORY.md` (or
+  `.agents/history/` for overflow archives). Archiving completed plans:
+  see `plans-and-docs.md`.
+- **Lean state files, optional subdirectories.** State files stay brief entry
+  points (index-style, not sprawling documents). A state file that grows past
+  its size budget (≤ **120 lines**) must be split into
+  `.agents/<topic>/<name>.md` subdirectories — not stuffed longer. Every file
+  in an optional subdirectory **MUST** be mentioned in the state file that
+  owns it.
+- **No TODO lists.** Use issue trackers or beads.
+- Prefer direct bullets with explicit names.
+- Trim obvious statements, repeated rules, and detail that no longer applies.
+
+## State file subdirectories
+
+Each state file has a matching optional subdirectory for growth — the file
+stays a lean index and the subdirectory carries the detail:
+
+| State file | Optional subdirectory |
+| ---------- | -------------------- |
+| `FILES.md` | `.agents/files/` |
+| `POLICIES.md` | `.agents/policies/` |
+| `TOOLS.md` | `.agents/tools/` |
+| `MAINTENANCE.md` | `.agents/maintenance/` |
+
+- Only create a subdirectory when its state file approaches its size budget.
+- Every file in a subdirectory MUST be listed in its state file (name + one
+  line of what it covers). A subdirectory file missing from the index is
+  dead content — move it or delete it.
+- `ONBOARDING.md` and `HISTORY.md` have no subdirectories: entry points stay
+  a single file, and history growth goes to `.agents/history/`.
+
+## Size budget
+
+- `.agents/` files: ≤ **120 lines** (always-injected context).
+- Subtree `AGENTS.md`: ≤ **250 lines** (loaded cumulatively with parents).
+
+Exceeding the budget signals restating instead of pointing, or hoarding
+rationale. Cut first; split the subtree only as a last resort.
+
+When a state file exceeds its budget, split detail into its matching
+subdirectory — the file stays a lean index and every file in the
+subdirectory MUST be listed in it.

teddi_tool-2026.11.1/.agents/policies/plans-and-docs.md

@@ -0,0 +1,45 @@
+# AGENTS.md — Plans and documentation
+
+Owned by `.agents/POLICIES.md`. Where working plans live, and how history
+and shipped docs are kept.
+
+## Implementation Plans
+
+- Plans, refactoring plans, and design docs go in
+  `.agents/plans/<YYYY-MM-DD>-<feature-name>/` — NOT under version control
+  (gitignored).
+- Name descriptively with phase-number prefixes so file order matches
+  implementation order, e.g. `01-sub-feature.md`, `02-next-sub-feature.md`.
+- NEVER commit plans to git. They are mutable working artifacts.
+- The archive trigger is **plan completion**: archive the moment the work
+  lands — don't wait for the next maintenance pass. Archive naming and
+  procedure: see **Documentation → Archive a plan**.
+- Shipped docs (user-facing guides, API references) go in `docs/` and
+  ARE committed.
+
+## Documentation
+
+- When `.agents/HISTORY.md` grows too large, archive older entries to
+  `.agents/history/`. Reference them from `.agents/HISTORY.md`.
+- Completed plans (`.agents/plans/<YYYY-MM-DD>-<feature-name>/`) are durable
+  once implemented: consolidate them into
+  `.agents/history/<YYYY-MM-DD-plan-name>.md`, remove the plan directory, and
+  reference the archive from `.agents/HISTORY.md`. The trigger is **plan
+  completion** — archive when the work lands, not at a later maintenance pass.
+- `.agents/history/` IS version-controlled (durable decision records).
+- AGENTS.md and state files describe the project's current contracts — never
+  append session notes, iteration logs, or changelogs; delete stale text
+  instead. `.agents/HISTORY.md` is the only permitted exception and holds
+  high-level decisions only.
+
+## Archive a plan
+
+1. Consolidate `.agents/plans/<YYYY-MM-DD>-<feature-name>/` into a single
+   file `.agents/history/<YYYY-MM-DD-plan-name>.md` (use the plan directory's
+   date prefix, e.g. `2026-07-14-api-migration.md`).
+2. Delete the plan directory.
+3. Add an entry to `.agents/HISTORY.md` referencing the archive and its
+   commit.
+
+If the date prefix on the plan directory is missing or wrong, use the date
+work started — record it in the archive filename exactly as-is.

teddi_tool-2026.11.1/.config/mise/conf.d/docs.toml

@@ -0,0 +1,7 @@
+
+[tasks.docs]
+description = "Build documentation"
+# --link-mode=copy: zensical's file watcher panics under uv's symlink link
+# mode (UV_LINK_MODE=symlink); copy links keep the build deterministic.
+run = ["uv run --link-mode=copy zensical build"]
+

teddi_tool-2026.11.1/.config/mise/conf.d/format.toml

@@ -0,0 +1,11 @@
+[tasks.format]
+description = "Format code (ruff, isort, pyreorder)"
+run = [
+	"pyreorder run src/ tests/ scripts/ --config .config/pyreorder.toml",
+	"ruff format src/ tests/",
+	"ruff check src/ tests/ --select I --fix",
+]
+
+[tasks.format-md]
+description = "Lint and reformat Markdown files with rumdl"
+run = "rumdl fmt --config .config/rumdl.toml src/ docs/ tests/ ./"

teddi_tool-2026.11.1/.config/mise/conf.d/lint.toml

@@ -0,0 +1,15 @@
+[tasks.lint]
+description = "Run linter (ruff) and apply safe and unsafe fixes"
+run = 'ruff check src/ tests/ --fix --unsafe-fixes'
+
+[tasks.lint-check]
+description = "Run linter (ruff) without applying fixes"
+run = 'ruff check src/ tests/'
+
+[tasks.typecheck]
+description = "Run type checker (ty)"
+run = 'ty check src/ tests/'
+
+[tasks.spell]
+description = "Run spell checker (codespell)"
+run = "codespell src/ tests/"

teddi_tool-2026.11.1/.config/mise/conf.d/mcp.toml

@@ -0,0 +1,8 @@
+[tasks.add-mcp-servers]
+description = "Install dev-feature tools and register MCP servers (driven by data/dev-features.csv)"
+depends = ["dev"]
+usage = '''
+arg "<ai_agent>" help="AI assistant: claude, gemini, copilot, opencode, ... (see https://github.com/neondatabase/add-mcp)"
+'''
+run = "uv run .config/mise/scripts/install_dev_features.py add-mcp-servers {{usage.ai_agent}}"
+

teddi_tool-2026.11.1/.config/mise/conf.d/quality.toml

@@ -0,0 +1,24 @@
+[tasks.test]
+description = "Run tests with coverage"
+run = "uv run pytest --cov=teddi_tool"
+sources = ["src/**/*.py", "tests/**/*.py"]
+outputs = ["htmlcov/", ".coverage"]
+
+[tasks.all]
+description = "Run all quality checks"
+depends = [
+  "test",
+  "lint",
+  "spell",
+  "format",
+  "format-md",
+  "docs",
+]
+
+[tasks.release-notes]
+description = "Generate release notes for the latest tag with an OpenAI-compatible endpoint"
+run = "uv run --with httpx python scripts/release_notes.py"
+
+[tasks.clean]
+description = "Clean build artifacts"
+run = ["rm -rf build dist *.egg-info .pytest_cache .coverage htmlcov docs/_build"]

teddi_tool-2026.11.1/.config/mise/conf.d/skills.toml

@@ -0,0 +1,5 @@
+[tasks.add-skills]
+description = "Install agent skills for AI assistants (driven by data/dev-features.csv and skills.csv)"
+depends = ["dev"]
+run = "uv run .config/mise/scripts/install_dev_features.py add-skills"
+

teddi_tool-2026.11.1/.config/mise/conf.d/tasks.toml

@@ -0,0 +1,3 @@
+[tasks.dev]
+description = "Install development dependencies"
+run = "uv sync -U --dev --all-extras --all-groups"

teddi_tool-2026.11.1/.config/mise/config.toml

@@ -0,0 +1,23 @@
+# mise configuration
+# Task definitions are in conf.d/*.toml files (automatically loaded by mise)
+[tools]
+# basic frameworks that should always be available
+node = "latest"
+bun = "latest"
+
+# Linter/formatter/type checker tools
+"ruff" = "latest"
+"ty" = "latest"
+"rumdl" = "latest"
+"pypi:git+https://github.com/jr2804/pyreorder.git" = "latest"
+"pypi:codespell" = "latest"
+
+# CLI tools rg and tree-cli -> use `rg --files | tree-cli --fromfile` to get a nice tree view of the project files
+ripgrep = "latest"
+"github:peteretelej/tree" = { version = "latest", rename_exe = "tree-cli" }
+
+[settings.npm]
+package_manager = "bun"
+
+[settings.pypi]
+uvx = true

teddi_tool-2026.11.1/.config/mise/data/dev-features.csv

@@ -0,0 +1,21 @@
+enabled,category,tool,tool_value,mcp_command,mcp_name,skill_repo,skill
+0,slop,pypi:sloppylint,latest,,,https://codeberg.org/jr2804/copier-uv-plus.git,cli-sloppylint
+0,slop,pypi:ai-slop-detector,"{ version = ""latest"", extras = [""all""] }",,,https://codeberg.org/jr2804/copier-uv-plus.git,cli-ai-slop-detector
+0,slop,npm:@yuvrajangadsingh/vibecheck,latest,vibecheck --mcp,vibecheck,https://codeberg.org/jr2804/copier-uv-plus.git,cli-vibecheck
+0,slop,npm:aislop,latest,mise x --command aislop-mcp,aislop,https://codeberg.org/jr2804/copier-uv-plus.git,cli-aislop
+0,slop,,,,,https://codeberg.org/jr2804/copier-uv-plus.git,cli-deep-slop-scan
+0,slop,github:djinn-soul/CytoScnPy,latest,cytoscnpy mcp-server,cytoscnpy,,
+0,slop,github:ChuprinaDaria/Vibecode-Cleaner-Fartrun,latest,fartrun mcp,fartrun,https://codeberg.org/jr2804/copier-uv-plus.git,cli-fartrun
+0,codebase,github:yoanbernabeu/grepai,latest,grepai mcp-serve,grepai,https://codeberg.org/jr2804/copier-uv-plus.git,cli-grepai
+1,codebase,npm:@colbymchenry/codegraph,latest,codegraph serve --mcp,codegraph,https://codeberg.org/jr2804/copier-uv-plus.git,cli-codegraph
+0,codebase,pypi:repowise,latest,repowise mcp .,repowise,https://codeberg.org/jr2804/copier-uv-plus.git,cli-repowise
+0,codebase,github:1broseidon/ketch,latest,ketch mcp serve,ketch,1broseidon/ketch,ketch
+0,dev,github:AlmogBaku/debug-skill,latest,,,AlmogBaku/debug-skill,
+0,dev,github:rtk-ai/rtk,latest,,,https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/main/examples,rtk-optimizer
+1,tracking,github:gastownhall/beads,latest,,,gastownhall/beads,
+1,tracking,github:dolthub/dolt,latest,,,,
+1,tracking,pypi:beads-mcp,"{ version = ""latest"", uvx_args = ""-p 3.13"" }",mise x --command beads-mcp,beads,,
+1,docs,pypi:kompend,"{ version = ""latest"", extras = [""pdf-full"", ""ocr""], uvx_args = ""-p 3.13 --index https://download.pytorch.org/whl/cu126 --index-strategy unsafe-best-match"" }",,,,
+0,general,,,bun x @wonderwhy-er/desktop-commander@latest,desktop-commander,wonderwhy-er/DesktopCommanderMCP,desktop-commander-overview
+0,general,,,bun x @modelcontextprotocol/server-sequential-thinking,sequential-thinking,,
+0,rust,rust-skills,,,https://codeberg.org/jr2804/copier-uv-plus.git,rust-skills,

teddi_tool-2026.11.1/.config/mise/data/skills.csv

@@ -0,0 +1,16 @@
+enabled,category,repo,skill
+1,coding,https://github.com/jr2804/pyreorder,
+1,coding,https://github.com/jr2804/prompts,python-ultimate
+1,coding,https://github.com/alinaqi/claude-bootstrap,code-deduplication
+1,coding,https://github.com/s2005/uv-skill,
+1,coding,https://github.com/shadcn/improve,
+1,docs,plannotator/effective-html,
+1,docs,adewale/good-readme,
+1,docs,https://github.com/nicobailon/visual-explainer,
+1,docs,https://github.com/oil-oil/beautify-github-readme,
+1,docs,https://github.com/jr2804/prompts,scientific-figures
+1,docs,https://codeberg.org/jr2804/copier-uv-plus.git,project-docs
+1,docs,https://codeberg.org/jr2804/copier-uv-plus.git,mermaid-diagrams
+0,rust,https://codeberg.org/jr2804/copier-uv-plus.git,rust-skills
+0,rust,https://codeberg.org/jr2804/copier-uv-plus.git,rust-pyo3-bindings
+0,rust,https://codeberg.org/jr2804/copier-uv-plus.git,rust-dsp-stack