2026-06-28 18:17:27 +08:00
|
|
|
"""Skill Hub e2e probe.
|
|
|
|
|
|
|
|
|
|
Exercises the full skill_hub client surface against a real Hub:
|
|
|
|
|
``search → get → install`` plus a SkillsSegmentBuilder dry-run that
|
|
|
|
|
hits the rewriter → router → pre-gate body hydrate → gate → post-gate
|
|
|
|
|
refs hydrate pipeline end-to-end.
|
|
|
|
|
|
|
|
|
|
Run from the project root:
|
|
|
|
|
|
|
|
|
|
.venv/bin/python scripts/skill_hub_e2e.py \\
|
|
|
|
|
--endpoint https://dev-skillhub.aws.evermind.ai \\
|
|
|
|
|
--query "generate pdf report"
|
|
|
|
|
|
|
|
|
|
Requires network reach to the Hub endpoint. In containers that route
|
|
|
|
|
through a Squid proxy refusing CONNECT to ``*.evermind.ai``, this
|
|
|
|
|
script will fail at the first ``search`` call with a network error —
|
|
|
|
|
run from a machine with direct internet or whitelist the host.
|
|
|
|
|
|
|
|
|
|
Skips LLM-driven stages (rewriter / gate) unless ``--provider <id>``
|
|
|
|
|
is supplied; without a provider, the segment builder runs in
|
|
|
|
|
no-rewriter / no-gate mode (router + hydrate only) so the script is
|
|
|
|
|
useful even when no LLM credentials are wired.
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
from __future__ import annotations
|
|
|
|
|
|
|
|
|
|
import argparse
|
|
|
|
|
import asyncio
|
|
|
|
|
import sys
|
|
|
|
|
import textwrap
|
|
|
|
|
from pathlib import Path
|
|
|
|
|
|
|
|
|
|
# Allow `python scripts/skill_hub_e2e.py` without `-m`.
|
|
|
|
|
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
|
|
|
|
|
|
|
|
|
|
from raven.memory_engine.skill_forge import (
|
|
|
|
|
HubSkillSource,
|
|
|
|
|
SkillForgeRouter,
|
|
|
|
|
)
|
|
|
|
|
from raven.skill_hub import SkillHubClient
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def probe_client(endpoint: str, api_key: str | None, query: str, limit: int) -> None:
|
|
|
|
|
"""Stage 1 — direct SkillHubClient roundtrip (search → get → install)."""
|
|
|
|
|
print("\n=== Stage 1: SkillHubClient direct ===")
|
|
|
|
|
client = SkillHubClient(endpoint, api_key=api_key, timeout_s=10.0)
|
|
|
|
|
try:
|
|
|
|
|
print(f"GET /openapi/v1/skills?q={query!r}&limit={limit} ...")
|
|
|
|
|
items = await client.search(query, limit=limit)
|
|
|
|
|
print(f" → {len(items)} item(s)")
|
|
|
|
|
for it in items[:3]:
|
|
|
|
|
print(f" - {it.get('name')!r:40s} id={it.get('id')} q={it.get('quality_score')}")
|
|
|
|
|
|
|
|
|
|
if not items:
|
|
|
|
|
print(" (empty result — nothing more to probe)")
|
|
|
|
|
return
|
|
|
|
|
|
|
|
|
|
top = items[0]
|
|
|
|
|
print(f"\nGET /openapi/v1/skills/{top['id']} ...")
|
|
|
|
|
meta = await client.get(top["id"])
|
|
|
|
|
body = meta.get("skill_md", "") or ""
|
|
|
|
|
print(f" → slug={meta.get('slug')} version={meta.get('version')} body_chars={len(body)}")
|
|
|
|
|
if body:
|
|
|
|
|
preview = body.splitlines()[:3]
|
|
|
|
|
print(" body head:")
|
|
|
|
|
for line in preview:
|
|
|
|
|
print(f" {line[:80]}")
|
|
|
|
|
|
|
|
|
|
print(f"\ninstall({top['id']}, prefetched_meta=<from get>) ...")
|
|
|
|
|
installed = await client.install(top["id"], prefetched_meta=meta)
|
|
|
|
|
print(f" → dir={installed.get('dir')}")
|
|
|
|
|
print(f" scripts_dir={installed.get('scripts_dir')}")
|
|
|
|
|
bundle_dir = Path(installed["dir"]) if installed.get("dir") else None
|
|
|
|
|
if bundle_dir and bundle_dir.is_dir():
|
|
|
|
|
entries = sorted(p.name for p in bundle_dir.iterdir())
|
|
|
|
|
print(f" files: {entries[:10]}{'...' if len(entries) > 10 else ''}")
|
|
|
|
|
finally:
|
|
|
|
|
await client.aclose()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def probe_hub_source(endpoint: str, api_key: str | None, query: str, k: int) -> None:
|
|
|
|
|
"""Stage 2 — HubSkillSource → RouterHit mapping (Tier 0 catalog)."""
|
|
|
|
|
print("\n=== Stage 2: HubSkillSource → RouterHit ===")
|
|
|
|
|
client = SkillHubClient(endpoint, api_key=api_key, timeout_s=10.0)
|
|
|
|
|
try:
|
|
|
|
|
src = HubSkillSource(client)
|
|
|
|
|
hits = await src.search(query, [], k=k)
|
|
|
|
|
print(f" → {len(hits)} RouterHit(s); body empty (catalog only):")
|
|
|
|
|
for h in hits[:5]:
|
|
|
|
|
assert h.content == "", "HubSkillSource must emit empty content"
|
|
|
|
|
print(f" {h.qualified_id} name={h.name!r} score={h.score:.3f}")
|
|
|
|
|
finally:
|
|
|
|
|
await client.aclose()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def probe_segment(
|
|
|
|
|
endpoint: str,
|
|
|
|
|
api_key: str | None,
|
|
|
|
|
query: str,
|
|
|
|
|
k: int,
|
|
|
|
|
) -> None:
|
|
|
|
|
"""Stage 3 — SkillsSegmentBuilder body hydrate (no rewriter / gate)."""
|
|
|
|
|
print("\n=== Stage 3: SkillsSegmentBuilder hydrate (no LLM) ===")
|
fix(tools): an array sent as its own JSON is still an array
## Summary
Reported as "deliver_files is broken". It is not: **the tool never ran.**
Every `deliver_files` call on one install was refused before dispatch -- five in a row in a single session -- and nothing was ever delivered:
```
Error: Invalid parameters for tool 'deliver_files': files should be array
```
What the model sent was the array, spelled as a string:
```json
{"files": "[{\"path\": \"...poster.png\", \"title\": \"...\"}]", "message": "..."}
```
`cast_params` already forgives that spelling for every scalar type -- `"3"` for an integer, `"true"` for a boolean -- and did not for arrays or objects, which are exactly the types a model is most likely to stringify.
## Type
- [x] Fix
- [ ] Feature
## The edge of the forgiving is the design
When the value is a string, try `json.loads`, and take the result **only if it is the type the schema asked for**. A string that is not JSON, or is JSON of the wrong shape, is returned unchanged so the validator still names the real problem -- the point is to widen what is accepted, not to swallow a type error.
**Nothing here can raise.** Turning "your argument has the wrong type" into a traceback would be worse than the refusal it replaces, so the parse is wrapped and failure falls through.
**A `type: "string"` field is never parsed.** JSON is ordinary text in a message body or a file's content, and replacing it would hand the tool something it never asked for. Two independent things prevent it today (the string branch returns before the parse is reached, and the parse only wins on a type match), which is why the case pinning it is a tripwire rather than a load-bearing assertion -- said so in its own docstring rather than left to look like coverage.
## Not just deliver_files
Six built-in tools declare an array or object parameter and were all exposed:
| tool | parameter |
|---|---|
| `deliver_files` | `files` |
| `ask_user` | `questions` |
| `image_generate` | `images` |
| `message` | `media` |
| `create_playbook` | `skills` |
| `video_generate` | `params` |
The same failure was already seen from the other side: `acp_client/acp_agent.py` records `update_task_state` and `operations should be array` from a real dispatch.
## Verification
```
make lint-python ruff check + ruff format --check, 1850 files
make lint-imports 9 contracts kept, 0 broken
pytest tests/ 19,699 passed, 7 failed (all pre-existing, see below)
```
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots -- no user-facing string
**End to end, through the real tool**, with the exact payload that failed five times in production:
```
files sent as: str -> [{"path": ".../poster.png", "title": "..."}]
returned: Delivered 1 file(s): poster.png (72 B).
still "should be array": False
registered in the store: True
```
Twelve cases, five mutations, each killing at least one:
| mutation | red |
|---|---|
| drop the whole branch (the old behaviour) | 3 |
| raise instead of falling through on a parse failure | 5 |
| accept the parse whatever type it yielded | 1 |
| do not re-cast the parsed value, so items are not cast | 1 |
| widen the tuple to include `string` | **survived -- unreachable** |
The last is worth stating rather than hiding: that mutation cannot change behaviour, because the `type == "string"` branch returns earlier and the type check would refuse the result anyway. I also tried moving the new block above that branch, alone and combined with widening the tuple, and neither reddens anything either. The invariant holds by construction; the case that documents it says so.
**Pre-existing failures, checked against the base.** 7 failed in the full run, all in `tests/test_security_network.py` (`test_a_redirect_to_a_dangerous_address_is_refused` and siblings). Running that file alone on this same tree gives 4 -- the count is order-dependent -- and the change touches only `raven/agent/tools/params.py` plus a new test file, neither of which `raven/security/network.py` imports. The failures are the box's resolver: it returns poisoned answers roughly half the time, which I measured separately (`en.wikipedia.org` came back as `2001::1` on 3 of 6 lookups). Not introduced here, and worth someone's attention on its own.
## Risk
- [x] Security impact considered -- widens what reaches a tool's own validation, not what bypasses it. A parsed value is still validated against the same schema, and a parse that yields the wrong type is refused exactly as before
- [x] Backward compatibility considered -- a call that worked before takes the identical path; the new branch is reached only by a `str` where an array or object is declared, which previously always failed
- [x] Rollback path is clear -- single-commit revert
## Related Issues
N/A
## Swept
`mr-review-patterns` pre-submit sweep, over `git diff origin/main...HEAD`.
- **1 (a write location moved)** -- nothing moved; a branch was added to an existing dispatch on `target_type`. Grepped every caller of `cast_params`: the registry is the only one, and it runs `validate_params` right after, which is the reader this affects.
- **2 (a value with several entry points)** -- the cast is the single funnel every tool argument passes through, which is why the fix belongs here and not in `deliver_files`.
- **3 (a guard)** -- checked both directions: what it wrongly lets through (JSON of the wrong type, non-JSON text -- both refused, with cases) and what it wrongly refuses (a real list, unaffected, with a case).
- **4 (tests)** -- five mutations above, one honestly reported as unreachable. Failing-ID sets diffed against the base rather than counts.
- **6 (stale text)** -- the module docstring enumerated what is coerced ("a string that should be an integer"); it now names arrays and objects too. Grepped the tracked tree for other statements of the rule: none.
- **9 (error handling)** -- the new path adds one way to end and it is caught: `json.loads` raises `ValueError` on bad text and `TypeError` on a non-string, and both fall through to the untouched value.
- **11** -- `git ls-files | grep -c node_modules` is 0; the commit-message gate was run, not eyeballed.
Not applicable, with reasons: **3b, 3c, 3d, 3e** (no tool schema produced, no state moved, one lane, no assertion lost its symbol); **4b, 4c, 4d** (no platform branch, no shell, no rendered number); **5, 5b** (no dependency; `json` is stdlib and already imported across this package); **6b, 6c** (no backup, no generated artifact); **7, 7b** (nothing on disk); **8** (no asset, no secret); **10** (no prompt text).
## Deliberately not fixed
The error text still ends with `[Analyze the error above and try a different approach.]`, and the model plainly did not -- it sent the same shape five times. A message naming the expected spelling (`files must be a JSON array, not a string containing one`) would give it something to act on. That is a change to the registry's error surface, affects every tool, and deserves its own argument.
## Moved from !594
Opened on a compliant source branch. AGENTS.md 2.1 asks for a 3-5 word snake_case description and the previous branch had seven; GitLab cannot change an existing merge request's source branch, so the change moves rather than the name.
Same commits, rebased onto `c2a9768f`. Both code findings from the review on !594 are already in them -- `RecursionError` caught with its regression case, and the implementation comment reduced to the two non-obvious reasons. Nothing else changed, so that review carries.
2026-09-09 15:42:36 +00:00
|
|
|
from raven.context_engine.segments.skills import SkillsSegmentBuilder
|
chore(*): gate call correctness with a pinned type checker (#416)
## Summary
Nothing in this repo could see a signature change reach its callers.
Ruff reads one file at a time, the import contracts read edges rather
than calls, and the suite only covers lines it executes. The consequence
was concrete: a required `sandbox_home` argument added to
`BoxliteExecutor` reached `plugins-dist/design-engine`'s render path
with CI green, and a reviewer -- not a gate -- found it.
`ty` answers that question. This adds it as a pinned dev dependency, a
`make lint-types` target and a CI step, with **110 of its 133 rules
live**: nine switched off with their measured backlog recorded beside
each, fourteen shipped disabled upstream and untouched.
Getting there meant clearing 81 diagnostics. This PR folds what were
three stacked PRs (#422 and #423, now closed); each rule's story is a
commit of its own.
### 1. The gate, at 108 rules (`chore(*): gate call correctness...`)
21 diagnostics to clear, five of them real:
| Where | What |
|---|---|
| `evolver/orchestrator/production.py` | `design_of` annotated as taking
two parameters while its docstring, its only implementation and its one
call site all use three |
| `raven/cli/provider_commands.py` | `dict[str, callable]` -- the
builtin function, not a type, so the annotation asserted nothing |
| `raven/config/schema.py` | `Config` is a `BaseSettings` but declared
`env_prefix` / `env_nested_delimiter` through pydantic's `ConfigDict`,
which does not carry those keys |
| `raven/spine/delivery.py` | `StreamDelta.conversation_id` is optional
and was used as a `dict[str, str]` key; a delta without one stored a
`None` entry the close path then read as "no open stream", losing that
stream's done marker |
| `research_flow/support/harness_text.py` | a predicate table typed its
matchers as `object`, so nothing checked they are callable |
The rest were unproven invariants and annotations wider than the code:
three late-bound callables asserted where a comment used to carry the
claim, one closure binding the callable it guarded instead of re-reading
it, four `hasattr` probes that now check what the call actually needs,
and a contextmanager yielding the value it just set.
### 2. `unresolved-import` (`fix(*): resolve the imports the type gate
could not`)
21 diagnostics; three were stale module paths nothing had run into:
- `HarnessNode.current_core_version()` read `raven.__core_version__`, a
module that exists neither here nor in the wheel
`scripts/build_core_wheel.py` produces. The read sat inside `try/except
ImportError`, so the except branch was the only branch and **every node
`store.py` saved recorded `core_version="unknown"`**. It reads
`raven.__version__` now and returns `0.1.13`.
- `raven/agent/loop/wiring.py` imported `SkillForgeRouterConfig` from
`raven.config.schema`; it lives in `raven.config.raven`. Under
`TYPE_CHECKING`, so the annotation simply meant nothing.
- three scripts imported `raven.context_engine.base` and
`raven.memory_engine.base`, neither of which exists. **Two failed at
module import** -- running them was not possible.
The other eighteen were the environment: the three agent products keep
their plugin package beside them, so their roots are declared in
`[tool.ty.environment]`; `lxml` ships a compiled `etree` with no type
information, so `lxml-stubs` is a dev dependency (real types rather than
five silenced lines); `uno` and `com.sun.star.*` are suppressed per
line, since that worker runs inside LibreOffice's own interpreter.
### 3. `invalid-return-type` (`fix(*): make the declared return types
true`)
39 diagnostics, and **one stale annotation held eight of them**:
`run_turn` and the `_run_turn` behind it were declared `-> LoopOutcome`
while all three of their returns build a `TurnOutcome` -- a different
dataclass with no field in common. Nothing broke, because the spine
worker reads what it actually gets and `LoopOutcome` never leaves
`_run_agent_loop`. The annotation was the only thing wrong.
The other 31: nine annotations narrower than the code (five `return
tuple(<genexpr>)` typed as fixed-arity tuples, an inner `one()` still
declaring the two-tuple it returned before a third element was added,
`image_block`'s TypedDict), five declarations refusing a value the
function returns (four tool `execute` overrides saying `-> str` while
returning `ToolResult`), seven invariants that lived in a `# type:
ignore` comment, and ten honest widenings.
### 4. What the gates then caught in this PR's own work
- The qq factory guard passed locally only because an earlier test had
left an event loop behind. Reproduced the CI state
(`asyncio.set_event_loop(None)`), then made the test async so the loop
is its own.
- `invalid-return-type`, while still disabled, hid a regression
introduced here: the qq factory returning the class instead of an
instance. Found by diffing the rule histogram, which is why that rule is
on now.
- The diff-coverage gate named four lines in `raven/routing/cache.py` --
the asserts this work had just added, sitting inside a `try` whose
`except Exception` would have swallowed the `AssertionError` and served
the stale cache. `_do_refresh` returns its data now; the asserts, their
noqa and the swallowing all go with it.
`child_scope`, `QQChannel.start()` and `BenchmarkCache` had no tests at
all and have them now. Every one was mutation-checked.
## Type
- [ ] Fix
- [ ] Feature
- [ ] Docs
- [x] CI / tooling
- [ ] Refactor
- [ ] Other
## Verification
- `make lint-types` -> All checks passed; 81 diagnostics cleared across
the three rule sets
- Gate proven live three times, once per rule: a missing argument, an
import of a module that does not exist, and a function returning a str
under `-> int` each turn it red, and removing the probe turns it green
- `uv run ruff check` + `ruff format --check` over all six trees ->
clean
- `uv run lint-imports` -> 10 kept, 0 broken; `deptry raven` (all
extras) -> no issues; `uv lock --check` -> resolved
- `make check-source-language` -> exit 0; `commitlint` -> exit 0
- `make coverage` locally: **22050 passed, 45 skipped, 4 failed**; diff
coverage 92.59%
- All four failures are **pre-existing on `main`**, checked by a real
checkout in the same environment where they fail identically: two
`test_the_products_tool_face_*` launcher tests,
`test_a_ceiling_as_large_as_the_window_still_leaves_room_for_history`
(`reserved_tools = 6044 > 6_000`), and
`test_a_missing_key_is_said_once_rather_than_per_query`
(environment-dependent: it asserts `SERPER_API_KEY` is absent)
- Rule counts measured with both `--extra dev` and `--all-extras` --
identical, so this gate's verdict does not depend on which optional
packages are installed
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots are updated when needed
## Risk
Behaviour changes are confined to the fixes listed above, and each
replaces an error path with a correct one: nodes are stamped with the
real raven version instead of `"unknown"`, two scripts that could not
start now start, the stream bookkeeping no longer stores a `None` key,
and a cache refresh returns what it fetched. Everything else is a
declaration moved to match what the function already returned.
`tests/` is out of the gate's scope (113 diagnostics under the same
rules). Tests are executed, so a broken call there is already loud; this
gate is for code CI does not run. Bringing them in is sized, separate
work.
Rollback: revert the whole PR to drop the gate and its fixes together,
or delete the `[tool.ty]` block, the `lint-types` target and its CI step
to keep the fixes and drop only the gate.
- [x] Security impact considered
- [x] Backward compatibility considered
- [x] Rollback path is clear for risky changes
## Related Issues
N/A
---------
Co-authored-by: Claude (claude-opus-5) <noreply@anthropic.com>
2026-09-16 22:33:14 +08:00
|
|
|
from raven.contracts.assembled import TokenBudget
|
|
|
|
|
from raven.contracts.context import AssemblyContext
|
fix(tools): an array sent as its own JSON is still an array
## Summary
Reported as "deliver_files is broken". It is not: **the tool never ran.**
Every `deliver_files` call on one install was refused before dispatch -- five in a row in a single session -- and nothing was ever delivered:
```
Error: Invalid parameters for tool 'deliver_files': files should be array
```
What the model sent was the array, spelled as a string:
```json
{"files": "[{\"path\": \"...poster.png\", \"title\": \"...\"}]", "message": "..."}
```
`cast_params` already forgives that spelling for every scalar type -- `"3"` for an integer, `"true"` for a boolean -- and did not for arrays or objects, which are exactly the types a model is most likely to stringify.
## Type
- [x] Fix
- [ ] Feature
## The edge of the forgiving is the design
When the value is a string, try `json.loads`, and take the result **only if it is the type the schema asked for**. A string that is not JSON, or is JSON of the wrong shape, is returned unchanged so the validator still names the real problem -- the point is to widen what is accepted, not to swallow a type error.
**Nothing here can raise.** Turning "your argument has the wrong type" into a traceback would be worse than the refusal it replaces, so the parse is wrapped and failure falls through.
**A `type: "string"` field is never parsed.** JSON is ordinary text in a message body or a file's content, and replacing it would hand the tool something it never asked for. Two independent things prevent it today (the string branch returns before the parse is reached, and the parse only wins on a type match), which is why the case pinning it is a tripwire rather than a load-bearing assertion -- said so in its own docstring rather than left to look like coverage.
## Not just deliver_files
Six built-in tools declare an array or object parameter and were all exposed:
| tool | parameter |
|---|---|
| `deliver_files` | `files` |
| `ask_user` | `questions` |
| `image_generate` | `images` |
| `message` | `media` |
| `create_playbook` | `skills` |
| `video_generate` | `params` |
The same failure was already seen from the other side: `acp_client/acp_agent.py` records `update_task_state` and `operations should be array` from a real dispatch.
## Verification
```
make lint-python ruff check + ruff format --check, 1850 files
make lint-imports 9 contracts kept, 0 broken
pytest tests/ 19,699 passed, 7 failed (all pre-existing, see below)
```
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots -- no user-facing string
**End to end, through the real tool**, with the exact payload that failed five times in production:
```
files sent as: str -> [{"path": ".../poster.png", "title": "..."}]
returned: Delivered 1 file(s): poster.png (72 B).
still "should be array": False
registered in the store: True
```
Twelve cases, five mutations, each killing at least one:
| mutation | red |
|---|---|
| drop the whole branch (the old behaviour) | 3 |
| raise instead of falling through on a parse failure | 5 |
| accept the parse whatever type it yielded | 1 |
| do not re-cast the parsed value, so items are not cast | 1 |
| widen the tuple to include `string` | **survived -- unreachable** |
The last is worth stating rather than hiding: that mutation cannot change behaviour, because the `type == "string"` branch returns earlier and the type check would refuse the result anyway. I also tried moving the new block above that branch, alone and combined with widening the tuple, and neither reddens anything either. The invariant holds by construction; the case that documents it says so.
**Pre-existing failures, checked against the base.** 7 failed in the full run, all in `tests/test_security_network.py` (`test_a_redirect_to_a_dangerous_address_is_refused` and siblings). Running that file alone on this same tree gives 4 -- the count is order-dependent -- and the change touches only `raven/agent/tools/params.py` plus a new test file, neither of which `raven/security/network.py` imports. The failures are the box's resolver: it returns poisoned answers roughly half the time, which I measured separately (`en.wikipedia.org` came back as `2001::1` on 3 of 6 lookups). Not introduced here, and worth someone's attention on its own.
## Risk
- [x] Security impact considered -- widens what reaches a tool's own validation, not what bypasses it. A parsed value is still validated against the same schema, and a parse that yields the wrong type is refused exactly as before
- [x] Backward compatibility considered -- a call that worked before takes the identical path; the new branch is reached only by a `str` where an array or object is declared, which previously always failed
- [x] Rollback path is clear -- single-commit revert
## Related Issues
N/A
## Swept
`mr-review-patterns` pre-submit sweep, over `git diff origin/main...HEAD`.
- **1 (a write location moved)** -- nothing moved; a branch was added to an existing dispatch on `target_type`. Grepped every caller of `cast_params`: the registry is the only one, and it runs `validate_params` right after, which is the reader this affects.
- **2 (a value with several entry points)** -- the cast is the single funnel every tool argument passes through, which is why the fix belongs here and not in `deliver_files`.
- **3 (a guard)** -- checked both directions: what it wrongly lets through (JSON of the wrong type, non-JSON text -- both refused, with cases) and what it wrongly refuses (a real list, unaffected, with a case).
- **4 (tests)** -- five mutations above, one honestly reported as unreachable. Failing-ID sets diffed against the base rather than counts.
- **6 (stale text)** -- the module docstring enumerated what is coerced ("a string that should be an integer"); it now names arrays and objects too. Grepped the tracked tree for other statements of the rule: none.
- **9 (error handling)** -- the new path adds one way to end and it is caught: `json.loads` raises `ValueError` on bad text and `TypeError` on a non-string, and both fall through to the untouched value.
- **11** -- `git ls-files | grep -c node_modules` is 0; the commit-message gate was run, not eyeballed.
Not applicable, with reasons: **3b, 3c, 3d, 3e** (no tool schema produced, no state moved, one lane, no assertion lost its symbol); **4b, 4c, 4d** (no platform branch, no shell, no rendered number); **5, 5b** (no dependency; `json` is stdlib and already imported across this package); **6b, 6c** (no backup, no generated artifact); **7, 7b** (nothing on disk); **8** (no asset, no secret); **10** (no prompt text).
## Deliberately not fixed
The error text still ends with `[Analyze the error above and try a different approach.]`, and the model plainly did not -- it sent the same shape five times. A message naming the expected spelling (`files must be a JSON array, not a string containing one`) would give it something to act on. That is a change to the registry's error surface, affects every tool, and deserves its own argument.
## Moved from !594
Opened on a compliant source branch. AGENTS.md 2.1 asks for a 3-5 word snake_case description and the previous branch had seven; GitLab cannot change an existing merge request's source branch, so the change moves rather than the name.
Same commits, rebased onto `c2a9768f`. Both code findings from the review on !594 are already in them -- `RecursionError` caught with its regression case, and the implementation comment reduced to the two non-obvious reasons. Nothing else changed, so that review carries.
2026-09-09 15:42:36 +00:00
|
|
|
|
2026-06-28 18:17:27 +08:00
|
|
|
client = SkillHubClient(endpoint, api_key=api_key, timeout_s=10.0)
|
|
|
|
|
try:
|
|
|
|
|
hub_source = HubSkillSource(client)
|
|
|
|
|
router = SkillForgeRouter([hub_source])
|
|
|
|
|
builder = SkillsSegmentBuilder(
|
|
|
|
|
router,
|
|
|
|
|
skill_top_k=k,
|
|
|
|
|
hub_client=client,
|
|
|
|
|
)
|
|
|
|
|
ctx = AssemblyContext(
|
|
|
|
|
session_key="e2e",
|
|
|
|
|
current_message=query,
|
|
|
|
|
media=None,
|
|
|
|
|
channel=None,
|
|
|
|
|
chat_id=None,
|
|
|
|
|
session_messages=[],
|
|
|
|
|
budget=TokenBudget(
|
build: whole-repo lint + pre-commit convention (config only) (#59)
## Change description
> Whole-repo lint + pre-commit convention, CONFIG ONLY (no source
reformat in this PR). Python (ruff) and TypeScript (eslint + prettier)
share a 120-col margin via the committed pre-commit gate. This upgrades
main's existing basic ruff setup and adds the TS lint stack (none
existed on main).
>
> What this PR adds:
> - ruff: line-length 120; security rules
S101/S105/S106/S107/S506/S605/S607; policy per-file-ignores (tests +
accepted CLI deferred-imports + product asserts + N818, each commented);
ruff pinned <0.16.
> - eslint/prettier: shared base (`eslint.base.mjs` +
`prettier.config.mjs`); ui-tui extends it with React rules, bridge with
a Node-only config; hermes-ink vendor and generated RPC types excluded.
> - pre-commit: keeps main's hooks (conventional-commit,
detect-private-key, etc.), adds a top-level exclude and 4 local
eslint/prettier hooks; bumps the pre-commit dev dep.
> - 2 lint-surfaced fixes: PlannerContext import (F821) in the sentinel
runner; lower-cased file-local cron-heartbeat constants (N806).
(raven/config/raven.py's F821 was already fixed on main.)
>
> Sequencing: config only. `ruff check` is intentionally red on ~307
auto-fixables (I001/F401/F541/E701/E702); a SEPARATE reformat branch
runs `ruff --fix` + `ruff format` + eslint/prettier --fix to clear them
(100% auto-resolvable, zero manual). Enforcement (pre-commit install /
CI) turns on only after the reformat lands, so do not expect a green
tree from this PR alone.
>
> CLI-owned files (the reformat and several per-file-ignores touch
`raven/cli/*`) are under review by the CLI team. Judgment items (TS
no-explicit-any, no-unused-expressions, S101 convert-vs-keep, N818
rename, C90, mypy) are deferred to v2.
## Type of change
- [ ] Bug fix
- [x] New feature
- [ ] Document
- [x] Others
## Related issues (if there is)
> none
## Checklists
### Development
- [ ] Lint rules pass locally
- [ ] Application changes have been tested thoroughly
- [ ] Automated tests covering modified code pass
> config-only: `ruff check` is red on auto-fixables by design (the
reformat branch clears them); eslint/prettier configs load in both
ui-tui and bridge.
### Security
- [x] Security impact of change has been considered
- [ ] Code follows company security practices and guidelines
> Only dependency change is the dev-only pre-commit tool plus the ruff
pin; the detect-private-key hook from main is retained.
### Code review
- [x] Pull request has a descriptive title and context useful to a
reviewer
- [ ] Pull request linked to JIRA ticket when applicable
---------
Co-authored-by: Sheng Zhao <sheng.zhao@evermind.ai>
Co-authored-by: Claude (claude-opus-4-8) <noreply@anthropic.com>
2026-07-01 12:09:42 +08:00
|
|
|
context_length=200_000,
|
|
|
|
|
reserved_output=8000,
|
|
|
|
|
reserved_tools=4000,
|
|
|
|
|
reserved_system=4000,
|
2026-06-28 18:17:27 +08:00
|
|
|
available_history=184_000,
|
|
|
|
|
),
|
|
|
|
|
)
|
|
|
|
|
seg = await builder.build(ctx)
|
|
|
|
|
ids = seg.meta.get("injected_skill_ids", [])
|
|
|
|
|
print(f" → injected_skill_ids: {ids}")
|
|
|
|
|
print(f" text length: {len(seg.text)} chars")
|
|
|
|
|
print(" text preview:")
|
|
|
|
|
for line in textwrap.indent(seg.text[:1200], " ").splitlines()[:25]:
|
|
|
|
|
print(line)
|
|
|
|
|
finally:
|
|
|
|
|
await client.aclose()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def main() -> None:
|
|
|
|
|
p = argparse.ArgumentParser(description="Skill Hub e2e probe")
|
|
|
|
|
p.add_argument("--endpoint", required=True, help="Hub base URL")
|
|
|
|
|
p.add_argument("--api-key", default=None, help="Bearer token (optional)")
|
|
|
|
|
p.add_argument("--query", default="generate pdf report")
|
|
|
|
|
p.add_argument("--limit", type=int, default=5)
|
|
|
|
|
p.add_argument("--k", type=int, default=3, help="top-K for hub source / segment")
|
|
|
|
|
p.add_argument(
|
build: whole-repo lint + pre-commit convention (config only) (#59)
## Change description
> Whole-repo lint + pre-commit convention, CONFIG ONLY (no source
reformat in this PR). Python (ruff) and TypeScript (eslint + prettier)
share a 120-col margin via the committed pre-commit gate. This upgrades
main's existing basic ruff setup and adds the TS lint stack (none
existed on main).
>
> What this PR adds:
> - ruff: line-length 120; security rules
S101/S105/S106/S107/S506/S605/S607; policy per-file-ignores (tests +
accepted CLI deferred-imports + product asserts + N818, each commented);
ruff pinned <0.16.
> - eslint/prettier: shared base (`eslint.base.mjs` +
`prettier.config.mjs`); ui-tui extends it with React rules, bridge with
a Node-only config; hermes-ink vendor and generated RPC types excluded.
> - pre-commit: keeps main's hooks (conventional-commit,
detect-private-key, etc.), adds a top-level exclude and 4 local
eslint/prettier hooks; bumps the pre-commit dev dep.
> - 2 lint-surfaced fixes: PlannerContext import (F821) in the sentinel
runner; lower-cased file-local cron-heartbeat constants (N806).
(raven/config/raven.py's F821 was already fixed on main.)
>
> Sequencing: config only. `ruff check` is intentionally red on ~307
auto-fixables (I001/F401/F541/E701/E702); a SEPARATE reformat branch
runs `ruff --fix` + `ruff format` + eslint/prettier --fix to clear them
(100% auto-resolvable, zero manual). Enforcement (pre-commit install /
CI) turns on only after the reformat lands, so do not expect a green
tree from this PR alone.
>
> CLI-owned files (the reformat and several per-file-ignores touch
`raven/cli/*`) are under review by the CLI team. Judgment items (TS
no-explicit-any, no-unused-expressions, S101 convert-vs-keep, N818
rename, C90, mypy) are deferred to v2.
## Type of change
- [ ] Bug fix
- [x] New feature
- [ ] Document
- [x] Others
## Related issues (if there is)
> none
## Checklists
### Development
- [ ] Lint rules pass locally
- [ ] Application changes have been tested thoroughly
- [ ] Automated tests covering modified code pass
> config-only: `ruff check` is red on auto-fixables by design (the
reformat branch clears them); eslint/prettier configs load in both
ui-tui and bridge.
### Security
- [x] Security impact of change has been considered
- [ ] Code follows company security practices and guidelines
> Only dependency change is the dev-only pre-commit tool plus the ruff
pin; the detect-private-key hook from main is retained.
### Code review
- [x] Pull request has a descriptive title and context useful to a
reviewer
- [ ] Pull request linked to JIRA ticket when applicable
---------
Co-authored-by: Sheng Zhao <sheng.zhao@evermind.ai>
Co-authored-by: Claude (claude-opus-4-8) <noreply@anthropic.com>
2026-07-01 12:09:42 +08:00
|
|
|
"--stage",
|
|
|
|
|
choices=["1", "2", "3", "all"],
|
|
|
|
|
default="all",
|
2026-06-28 18:17:27 +08:00
|
|
|
help="Which stage to run (1=client, 2=hub_source, 3=segment).",
|
|
|
|
|
)
|
|
|
|
|
args = p.parse_args()
|
|
|
|
|
|
|
|
|
|
if args.stage in {"1", "all"}:
|
|
|
|
|
await probe_client(args.endpoint, args.api_key, args.query, args.limit)
|
|
|
|
|
if args.stage in {"2", "all"}:
|
|
|
|
|
await probe_hub_source(args.endpoint, args.api_key, args.query, args.k)
|
|
|
|
|
if args.stage in {"3", "all"}:
|
|
|
|
|
await probe_segment(args.endpoint, args.api_key, args.query, args.k)
|
|
|
|
|
|
|
|
|
|
print("\n✓ all stages completed")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
|
asyncio.run(main())
|