cleveragents/cleveractors-core
1
0
Fork 0
Code Issues 24 Pull requests 2 Projects Releases Packages Wiki Activity Actions 1

feat(skills): expose assets and gated non-standard resources through the skill tool #167

Open
CoreRasurae wants to merge 1 commit from feature/m1-skill-resource-manifest-and-assets into develop
pull from: feature/m1-skill-resource-manifest-and-assets
merge into: cleveragents:develop
Conversation 0 Commits 1 Files changed 11 +632 -262
CoreRasurae commented 2026-11-10 14:51:18 +00:00
Member
Copy link

Summary

Implements the ADR-2034 D-10 read surface for Skill packages:

  • Activation now returns a bundled-resource manifest grouped by references/, assets/, and scripts/, with every entry tagged by its D-8 class.
  • Non-standard top-level folders are listed only when the D-9 double-safety gate is open (global unsafe mode and skill-level safe_mode: false). Reading such a path while either switch is safe fails with an ExecutionError naming both states and the requested path.
  • Assets read exactly like references: UTF-8 content is decoded, genuine binary content is returned as base64, and the existing [SKILL_RESOURCE_READ] envelope plus ADR-2033 pagination are preserved.
  • Script sources remain readable for inspection in every mode; execution is out of scope.
  • Updated the synthesized skill tool schema and the authoring/docs to describe the manifest, asset reads, and gated non-standard access.

Closes #162

Scope

Script execution, execute/args/timeout, and temporary-tree materialization remain the D-10 execution follow-up and are not included here.

Verification

  • nox -s unit_tests — 3202 scenarios passed
  • nox -s integration_tests -- robot/agent_skills.robot — 9 tests passed
  • nox -s coverage_report -- features/agent_skills.feature — new manifest/gate paths fully covered
  • nox -s lint, nox -s format -- --check, nox -s typecheck, nox -s security_scan, nox -s dead_code
  • nox -s docs, nox -s benchmark -- --bench Skill
## Summary Implements the ADR-2034 D-10 read surface for Skill packages: - Activation now returns a bundled-resource manifest grouped by `references/`, `assets/`, and `scripts/`, with every entry tagged by its D-8 class. - Non-standard top-level folders are listed only when the D-9 double-safety gate is open (global unsafe mode **and** skill-level `safe_mode: false`). Reading such a path while either switch is safe fails with an `ExecutionError` naming both states and the requested path. - Assets read exactly like references: UTF-8 content is decoded, genuine binary content is returned as base64, and the existing `[SKILL_RESOURCE_READ]` envelope plus ADR-2033 pagination are preserved. - Script sources remain readable for inspection in every mode; execution is out of scope. - Updated the synthesized `skill` tool schema and the authoring/docs to describe the manifest, asset reads, and gated non-standard access. Closes #162 ## Scope Script execution, `execute`/`args`/`timeout`, and temporary-tree materialization remain the D-10 execution follow-up and are not included here. ## Verification - `nox -s unit_tests` — 3202 scenarios passed - `nox -s integration_tests -- robot/agent_skills.robot` — 9 tests passed - `nox -s coverage_report -- features/agent_skills.feature` — new manifest/gate paths fully covered - `nox -s lint`, `nox -s format -- --check`, `nox -s typecheck`, `nox -s security_scan`, `nox -s dead_code` - `nox -s docs`, `nox -s benchmark -- --bench Skill`
CoreRasurae added this to the v2.1.0 milestone 2026-11-10 14:51:18 +00:00
feat(skills): expose assets and gated non-standard resources through the skill tool
Some checks failed
CI / lint (pull_request) Successful in 56s
Details
CI / typecheck (pull_request) Successful in 1m50s
Details
CI / integration_tests (pull_request) Has started running
Details
CI / security (pull_request) Successful in 1m27s
Details
CI / benchmark (pull_request) Has started running
Details
CI / quality (pull_request) Successful in 2m11s
Details
CI / build (pull_request) Successful in 2m58s
Details
CI / unit_tests (pull_request) Successful in 5m52s
Details
CI / coverage (pull_request) Has started running
Details
CI / status-check (pull_request) Has been cancelled
Details
695cfa7110
 
Return a class-grouped bundled-resource manifest when a skill activates and gate non-standard folder reads behind the ADR-2034 D-9 double-safety check. Assets become readable like references, with text decoded and binary content returned as base64. The skill tool schema and authoring docs describe the manifest and gating rules; Behave and Robot coverage exercise the manifest, asset reads, and the non-standard read matrix.

ISSUES CLOSED: #162
docs(adr): remove implementation details from ADR-2034
Some checks failed
CI / lint (pull_request) Has started running
Details
CI / security (pull_request) Has started running
Details
CI / quality (pull_request) Has started running
Details
CI / unit_tests (pull_request) Has started running
Details
CI / integration_tests (pull_request) Has started running
Details
CI / build (pull_request) Has started running
Details
CI / benchmark (pull_request) Has started running
Details
CI / coverage (pull_request) Has been cancelled
Details
CI / status-check (pull_request) Has been cancelled
Details
CI / typecheck (pull_request) Has been cancelled
Details
34fc640b40 
Describe the Skill package decisions in technology-agnostic terms: remove code identifiers, module paths, test tooling, and implementation tracking while keeping the normative schema, identity, resource taxonomy, and safety-gate decisions.

Refs: #162
CoreRasurae force-pushed feature/m1-skill-resource-manifest-and-assets from 34fc640b40
Some checks failed
CI / lint (pull_request) Has started running
Details
CI / security (pull_request) Has started running
Details
CI / quality (pull_request) Has started running
Details
CI / unit_tests (pull_request) Has started running
Details
CI / integration_tests (pull_request) Has started running
Details
CI / build (pull_request) Has started running
Details
CI / benchmark (pull_request) Has started running
Details
CI / coverage (pull_request) Has been cancelled
Details
CI / status-check (pull_request) Has been cancelled
Details
CI / typecheck (pull_request) Has been cancelled
Details
to ec7a3e3d60
Some checks failed
CI / benchmark (pull_request) Has started running
Details
CI / lint (pull_request) Successful in 1m11s
Details
CI / build (pull_request) Successful in 1m15s
Details
CI / typecheck (pull_request) Successful in 1m33s
Details
CI / quality (pull_request) Successful in 2m11s
Details
CI / security (pull_request) Successful in 2m47s
Details
CI / integration_tests (pull_request) Successful in 4m29s
Details
CI / unit_tests (pull_request) Successful in 6m40s
Details
CI / coverage (pull_request) Failing after 11m11s
Details
CI / status-check (pull_request) Has been cancelled
Details
2026-11-10 15:12:21 +00:00 Compare
hurui200320 approved these changes 2026-11-10 15:30:09 +00:00
hurui200320 left a comment
Copy link

PR Review: !167 (Ticket #162)

Verdict: Approve

The implementation faithfully delivers the ADR-2034 D-10 read surface scoped by ticket #162: the class-grouped bundled-resource manifest on activation, asset reads with text-decoding/base64 fallback, the D-9 double-safety gate for non-standard reads (correctly refusing when either switch is safe, naming both states and the path), scripts readable in every mode, and the updated skill tool schema plus docs. No critical or major issues were found; the three nits below are optional follow-ups and none block merge.

Critical Issues

None.

Major Issues

None.

Minor Issues

None.

Nits

  1. src/cleveractors/agents/tool.py:1158 — gated paths leak into the "Available resources" error listing. While the D-9 gate is closed, a failed resource lookup lists every resource including non-standard entries — the same paths the activation manifest deliberately hides. ADR-2034 D-10 says the error names "the available resources", so this is compliant as written, but filtering non_standard entries while the gate is closed would be consistent with D-9's hiding intent (a probing read currently reveals gated paths by name). Note docs/tools/built-in-tools.md documents the listing behavior too, so this would need a small ADR/docs amendment if adopted.

  2. src/cleveractors/agents/tool.py:53 — _SKILL_NON_STANDARD_CLASS = "non_standard" duplicates SkillResourceClass.NON_STANDARD.value. If the enum value ever changed, the gate would silently fail open (non-standard reads allowed). The Behave gate matrix uses the real classifier, so drift would be caught by tests, but deriving the constant from the enum (or a parity assertion) is more robust than a string literal.

  3. features/agent_skills.feature:618 — no scenario reads a root-level file. The D-8 fixture set creates LICENSE.txt and the ticket's expected behavior says root-level files remain readable in every mode, but no Behave/Robot scenario reads one. The read path is shared with reference reads so line coverage is unaffected; a one-line read scenario would complete the D-8 read matrix.

Summary

Reviewed against ticket #162 and ADR-2034 (D-8/D-9/D-10), with the Package Registry Standard §16 and the skill docs as supporting context. Verification highlights:

  • Spec compliance: The manifest lists references/, assets/, scripts/ with class tags in ADR-mandated form and hides non-standard entries unless the gate is open; root files are correctly excluded from the manifest and readable in every mode. Non-standard reads raise ExecutionError naming both safety states and the path; the gate predicate (_is_global_unsafe = ToolAgent safe_mode false or context _unsafe_mode) exactly mirrors LLMAgent._resolve_parent_unsafe, and the ephemeral tool agent is constructed with safe_mode = not parent_unsafe (llm.py:1028), so end-to-end semantics are consistent. Script sources remain readable in every mode; execute/args/timeout are correctly absent (deferred to #163, matching the PR's declared scope).
  • Correctness: skill.get("safe_mode", True) is not False is safe given SkillValidator._validate_safe_mode enforces booleans; the manifest is appended to both pagination return branches on activation only; binary base64 resources fall back to the base64 string without crashing, matching the "no binary channel" ADR rationale. The previously-ungated non-standard reads are now intentionally tightened, documented in CHANGELOG and the guide.
  • Tests: New Behave scenarios cover the full gate matrix (refused ×2, allowed ×1), manifest hidden/shown, text/binary asset reads, and script reads, with meaningful assertions (including exact base64 content and negative manifest assertions); Robot covers an asset read and a refused non-standard read end-to-end through the real loader/factory path. before_scenario resets prevent cross-scenario leakage of the skills catalogue, safety flag, and binary fixture.
  • Quality/typing/doc: Code is typed and styled consistently; tool-schema, built-in-tools doc, guide, CHANGELOG, and ADR all match the implemented output format exactly. Commit is atomic with the message matching the issue Metadata; no merge commits.

Prior review comments: none existed at review time, so no previously-raised concerns needed re-checking. Script execution remains tracked by #163 and is deliberately out of scope here.

Nice work — approving. The nits are optional; address them in a follow-up if you agree with any.

## PR Review: !167 (Ticket #162) ### Verdict: Approve The implementation faithfully delivers the ADR-2034 D-10 read surface scoped by ticket #162: the class-grouped bundled-resource manifest on activation, asset reads with text-decoding/base64 fallback, the D-9 double-safety gate for non-standard reads (correctly refusing when either switch is safe, naming both states and the path), scripts readable in every mode, and the updated `skill` tool schema plus docs. No critical or major issues were found; the three nits below are optional follow-ups and none block merge. ### Critical Issues None. ### Major Issues None. ### Minor Issues None. ### Nits 1. **`src/cleveractors/agents/tool.py:1158` — gated paths leak into the "Available resources" error listing.** While the D-9 gate is closed, a failed resource lookup lists every resource including non-standard entries — the same paths the activation manifest deliberately hides. ADR-2034 D-10 says the error names "the available resources", so this is compliant as written, but filtering `non_standard` entries while the gate is closed would be consistent with D-9's hiding intent (a probing read currently reveals gated paths by name). Note `docs/tools/built-in-tools.md` documents the listing behavior too, so this would need a small ADR/docs amendment if adopted. 2. **`src/cleveractors/agents/tool.py:53` — `_SKILL_NON_STANDARD_CLASS = "non_standard"` duplicates `SkillResourceClass.NON_STANDARD.value`.** If the enum value ever changed, the gate would silently fail open (non-standard reads allowed). The Behave gate matrix uses the real classifier, so drift would be caught by tests, but deriving the constant from the enum (or a parity assertion) is more robust than a string literal. 3. **`features/agent_skills.feature:618` — no scenario reads a root-level file.** The D-8 fixture set creates `LICENSE.txt` and the ticket's expected behavior says root-level files remain readable in every mode, but no Behave/Robot scenario reads one. The read path is shared with reference reads so line coverage is unaffected; a one-line read scenario would complete the D-8 read matrix. ### Summary Reviewed against ticket #162 and ADR-2034 (D-8/D-9/D-10), with the Package Registry Standard §16 and the skill docs as supporting context. Verification highlights: - **Spec compliance:** The manifest lists `references/`, `assets/`, `scripts/` with class tags in ADR-mandated form and hides non-standard entries unless the gate is open; root files are correctly excluded from the manifest and readable in every mode. Non-standard reads raise `ExecutionError` naming both safety states and the path; the gate predicate (`_is_global_unsafe` = ToolAgent `safe_mode` false or context `_unsafe_mode`) exactly mirrors `LLMAgent._resolve_parent_unsafe`, and the ephemeral tool agent is constructed with `safe_mode = not parent_unsafe` (llm.py:1028), so end-to-end semantics are consistent. Script sources remain readable in every mode; `execute`/`args`/`timeout` are correctly absent (deferred to #163, matching the PR's declared scope). - **Correctness:** `skill.get("safe_mode", True) is not False` is safe given `SkillValidator._validate_safe_mode` enforces booleans; the manifest is appended to both pagination return branches on activation only; binary base64 resources fall back to the base64 string without crashing, matching the "no binary channel" ADR rationale. The previously-ungated non-standard reads are now intentionally tightened, documented in CHANGELOG and the guide. - **Tests:** New Behave scenarios cover the full gate matrix (refused ×2, allowed ×1), manifest hidden/shown, text/binary asset reads, and script reads, with meaningful assertions (including exact base64 content and negative manifest assertions); Robot covers an asset read and a refused non-standard read end-to-end through the real loader/factory path. `before_scenario` resets prevent cross-scenario leakage of the skills catalogue, safety flag, and binary fixture. - **Quality/typing/doc:** Code is typed and styled consistently; tool-schema, built-in-tools doc, guide, CHANGELOG, and ADR all match the implemented output format exactly. Commit is atomic with the message matching the issue Metadata; no merge commits. Prior review comments: none existed at review time, so no previously-raised concerns needed re-checking. Script execution remains tracked by #163 and is deliberately out of scope here. Nice work — approving. The nits are optional; address them in a follow-up if you agree with any.
features/agent_skills.feature Outdated
@ -551,0 +615,4 @@
"tools": [{"name": "skill"}]
}
"""
And a skills context with skill "pdf-processing" having resources of every D-8 class
hurui200320 commented 2026-11-10 15:30:09 +00:00
Member
Copy link

Nit: the new D-8 matrix fixtures include the root-level file LICENSE.txt, but no scenario ever reads it. The ticket's expected behavior says root-level files remain readable in every mode; the read path is shared with reference reads so coverage isn't affected, but a one-line "Reading a root-level file from an activated skill" scenario would complete the D-8 read matrix.

Nit: the new D-8 matrix fixtures include the root-level file `LICENSE.txt`, but no scenario ever reads it. The ticket's expected behavior says root-level files remain readable in every mode; the read path is shared with reference reads so coverage isn't affected, but a one-line "Reading a root-level file from an activated skill" scenario would complete the D-8 read matrix.
src/cleveractors/agents/tool.py Outdated
@ -45,0 +50,4 @@
("asset", "assets"),
("script", "scripts"),
)
_SKILL_NON_STANDARD_CLASS = "non_standard"
hurui200320 commented 2026-11-10 15:30:09 +00:00
Member
Copy link

Nit: _SKILL_NON_STANDARD_CLASS = "non_standard" duplicates SkillResourceClass.NON_STANDARD.value from skill_schema.py. If the enum value ever changed, the gate would silently fail open (non-standard reads allowed) — the Behave gate matrix would catch the drift, but deriving the constant from the enum (tool.py otherwise consumes plain data, so a module-level SkillResourceClass.NON_STANDARD.value import or a parity assertion in tests) would be more robust.

Nit: `_SKILL_NON_STANDARD_CLASS = "non_standard"` duplicates `SkillResourceClass.NON_STANDARD.value` from `skill_schema.py`. If the enum value ever changed, the gate would silently fail open (non-standard reads allowed) — the Behave gate matrix would catch the drift, but deriving the constant from the enum (tool.py otherwise consumes plain data, so a module-level `SkillResourceClass.NON_STANDARD.value` import or a parity assertion in tests) would be more robust.
src/cleveractors/agents/tool.py Outdated
hurui200320 commented 2026-11-10 15:30:09 +00:00
Member
Copy link

Nit: while the D-9 gate is closed, this "Available resources" listing includes non-standard entries (e.g. fixtures/sample.pdf) — the same paths the activation manifest deliberately hides. ADR-2034 D-10 does say the error names the available resources, so this is spec-compliant as written; but filtering non_standard entries from this listing while the gate is closed would be consistent with D-9's hiding intent (a probing read currently reveals gated paths by name). Would require a small ADR wording amendment if you choose to filter.

Nit: while the D-9 gate is closed, this "Available resources" listing includes non-standard entries (e.g. `fixtures/sample.pdf`) — the same paths the activation manifest deliberately hides. ADR-2034 D-10 does say the error names the available resources, so this is spec-compliant as written; but filtering `non_standard` entries from this listing while the gate is closed would be consistent with D-9's hiding intent (a probing read currently reveals gated paths by name). Would require a small ADR wording amendment if you choose to filter.
CoreRasurae force-pushed feature/m1-skill-resource-manifest-and-assets from ec7a3e3d60
Some checks failed
CI / benchmark (pull_request) Has started running
Details
CI / lint (pull_request) Successful in 1m11s
Details
CI / build (pull_request) Successful in 1m15s
Details
CI / typecheck (pull_request) Successful in 1m33s
Details
CI / quality (pull_request) Successful in 2m11s
Details
CI / security (pull_request) Successful in 2m47s
Details
CI / integration_tests (pull_request) Successful in 4m29s
Details
CI / unit_tests (pull_request) Successful in 6m40s
Details
CI / coverage (pull_request) Failing after 11m11s
Details
CI / status-check (pull_request) Has been cancelled
Details
to ead2669a44
Some checks are pending
CI / lint (pull_request) Successful in 50s
Details
CI / typecheck (pull_request) Successful in 1m39s
Details
CI / quality (pull_request) Successful in 2m7s
Details
CI / benchmark (pull_request) Has started running
Details
CI / security (pull_request) Successful in 2m43s
Details
CI / build (pull_request) Successful in 2m10s
Details
CI / integration_tests (pull_request) Successful in 2m47s
Details
CI / unit_tests (pull_request) Successful in 4m55s
Details
CI / coverage (pull_request) Successful in 6m23s
Details
CI / status-check (pull_request) Successful in 3s
Details
2026-11-10 15:45:29 +00:00 Compare
Some checks are pending
CI / lint (pull_request) Successful in 50s
Details
CI / typecheck (pull_request) Successful in 1m39s
Details
CI / quality (pull_request) Successful in 2m7s
Details
CI / benchmark (pull_request) Has started running
Details
CI / security (pull_request) Successful in 2m43s
Details
CI / build (pull_request) Successful in 2m10s
Details
CI / integration_tests (pull_request) Successful in 2m47s
Details
CI / unit_tests (pull_request) Successful in 4m55s
Details
CI / coverage (pull_request) Successful in 6m23s
Details
CI / status-check (pull_request) Successful in 3s
Details
This pull request can be merged automatically.
You are not authorized to merge this pull request.
View command line instructions

Checkout

From your project repository, check out a new branch and test the changes.
git fetch -u origin feature/m1-skill-resource-manifest-and-assets:feature/m1-skill-resource-manifest-and-assets
git switch feature/m1-skill-resource-manifest-and-assets
Sign in to join this conversation.
Reviewers
No reviewers
hurui200320
Labels
Clear labels
  
auto/blocked-by-deps
PR blocked by an open issue dependency. Operator must close the dep (or remove the dependency link) before the merge driver can act. Auto-cleared by merge_drive when no open deps remain.

  
auto/ci-timeout
Most recent merge cycle hit CI timeout. Driver excludes this PR while last merge_cycle row is < 30 min old; label persists thereafter as visible history.

  
auto/claimed-implementer
Currently being processed by an implementer worker.

  
auto/claimed-merge
Currently being processed by the merge driver.

  
auto/claimed-reviewer
Currently being processed by a reviewer worker.

  
auto/driver-down
Merge driver heartbeat stale; pipeline halted. Closed automatically on next clean tick.

  
auto/invariant-violation
Detected master commit violating the strict merge invariant. Tracked as an issue (not a PR label); kept here for label completeness.

  
auto/last-attempt-tier-0
In-cycle escalation: most recent attempt ran at the Tier 0 slot (`tier-0`). Slot's model defined in .opencode/models/tiers.yaml.

  
auto/last-attempt-tier-1
In-cycle escalation: most recent attempt ran at the Tier 1 slot (`tier-1`). Slot's model defined in .opencode/models/tiers.yaml.

  
auto/last-attempt-tier-2
In-cycle escalation: most recent attempt ran at the Tier 2 slot (`tier-2`). Slot's model defined in .opencode/models/tiers.yaml. Gated behind IMPLEMENTER_ESCALATION_TIER2_ENABLED.

  
auto/last-attempt-tier-min
In-cycle escalation: most recent attempt ran at the Tier -1 slot (`tier-min`). Slot's model defined in .opencode/models/tiers.yaml. Suffix is ``-min`` (not ``--1``) so the Forgejo UI reads naturally.

  
Automation Tracking
Tracking issues used by the AI Automation system for agents to communicate and report.

  
auto/needs-conflict-resolution
Rebase conflict needs LLM conflict-resolver.

  
auto/needs-implementer
Failing CI needs implementer attention.

  
auto/postmortem
Documenting a driver incident or rollback.

  
auto/ready-to-merge
Reviewer has APPROVED this PR and no later REQUEST_CHANGES is outstanding. The merge driver requires this label to even consider a PR for merging. Set by the reviewer worker on APPROVE; cleared on REQUEST_CHANGES.

  
auto/restart-throttled
Train repeatedly lost master-tempo races. Driver excludes via merge_cycle until cooldown elapses; label persists as visible history.

  
auto/revert
Revert PR backing out an invariant violation. Fast-tracked through the merge driver.

  
auto/sentinel
Sentinel PR duplicated from upstream into a personal fork by tools/duplicate_prs_to_fork.py for pipeline testing. Lives only in the fork; the canonical pipeline never sees it.

  
auto/stale-inactivity
No implementer activity for N days. Flagged for human review. Auto-cleared on next push to head branch.

  
auto/unstable
Repeatedly fails on current master (>= 3 ci-fail-on-rebased-sha releases in 12 h). Excluded from driver until human triage.

  
Blocked
A ticket in a blocked state and unable to complete until some other task is completed first.

  
Bounty
$100
 A bounty of $100 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$1000
 A bounty of $1000 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$10000
 A bounty of $10000 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$20
 A bounty of $20 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$2000
 A bounty of $2000 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$250
 A bounty of $250 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$50
 A bounty of $50 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$500
 A bounty of $500 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$5000
 A bounty of $5000 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$750
 A bounty of $750 for any open-source contributor who provides a MR that solves this issue

  
MoSCoW
Could have
 Could have feature in order to satisfy the epic/legendary.

  
MoSCoW
Must have
 Must have feature in order to satisfy the epic/legendary.

  
MoSCoW
Should have
 Should have feature in order to satisfy the epic/legendary.

  
Needs Feedback
There are questions in the ticket that can not be completed until the project owner provides clarity.

  
Points
1
 1 man-hours worth of work for an expert with no learning curve.

  
Points
13
 13 man-hours worth of work for an expert with no learning curve.

  
Points
2
 2 man-hours worth of work for an expert with no learning curve.

  
Points
21
 21 man-hours worth of work for an expert with no learning curve.

  
Points
3
 3 man-hours worth of work for an expert with no learning curve.

  
Points
34
 34 man-hours worth of work for an expert with no learning curve.

  
Points
5
 5 man-hours worth of work for an expert with no learning curve.

  
Points
55
 55 man-hours worth of work for an expert with no learning curve.

  
Points
8
 8 man-hours worth of work for an expert with no learning curve.

  
Points
88
 88 man-hours worth of work for an expert with no learning curve.

  
Priority
Backlog
 This ticket has backlogged priority and is not to be worked on yet

  
Priority
CI Blocker
 Critical priority issue that blocks CI/CD pipeline and prevents PR merges

  
Priority
Critical
 The priority is critical

  
Priority
High
 The priority is high

  
Priority
Low
 The priority is low

  
Priority
Medium
 The priority is medium

  
Signed-off: Owner
When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.

  
Signed-off: Scrum Master
When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.

  
Signed-off: Tech Lead
When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.

  
Spike
A ticket for learning a tool or technology that is needed to be able to do future planning and design.

  
State
Completed
 The ticket has been fully implemented, completed, and merged with the source code. This label should only be applied once a ticket is closed.

  
State
Duplicate
 A ticket that represents the same content as an existing ticket.

  
State
In Progress
 A ticket that is actively being developed.

  
State
In Review
 A ticket that has had some code completed to implement but is waiting to pass peer review and is not yet merged in.

  
State
Paused
 This ticket's work started but wasn't finished. It's on hold (likely in a feature branch) and will be resumed later, either due to a blocker or a delay.

  
State
Unverified
 All new tickets start in this state. A developer may set it to show the ticket is unverified. This means we haven't agreed to work on it. It will either move to a verified state or be closed as wontdo.

  
State
Verified
 The issue has been verified by a developer as legitimate. It will be worked on and verified tickets are now considered part of the backlog.

  
State
Wont Do
 This ticket has been decided it wont be done. This may mean the bug has been determined to not be real (cant verify) or the feature is one we have decided we dont want to adopt.

  
Type
Automation
 Any edits or discussion about the AI automated coding system.

  
Type
Bug
 Something that doesnt work as intended.

  
Type
Discussion
 Anytime a ticket represents a discussion about a subject and doesnt fall into one of the other categories.

  
Type
Documentation
 An error or improvement needed in the documentation.

  
Type
Epic
 Any first tier epic. That is, an epic which contains only issues as children and will not have sub-epics.

  
Type
Feature
 Some new functionality not present.

  
Type
Legendary
 A type of Epic which will contain other Epics.

  
Type
Refactor
 A code change that restructures existing code without changing its external behavior.

  
Type
Support
 Someone needs help using the project.

  
Type
Task
 A generic task that doesnt fit into the other type categories.

  
Type
Testing
 Work exclusively focusing on fixing or expanding testing.

No labels
auto/blocked-by-deps
auto/ci-timeout
auto/claimed-implementer
auto/claimed-merge
auto/claimed-reviewer
auto/driver-down
auto/invariant-violation
auto/last-attempt-tier-0
auto/last-attempt-tier-1
auto/last-attempt-tier-2
auto/last-attempt-tier-min
Automation Tracking
auto/needs-conflict-resolution
auto/needs-implementer
auto/postmortem
auto/ready-to-merge
auto/restart-throttled
auto/revert
auto/sentinel
auto/stale-inactivity
auto/unstable
Blocked
Bounty
$100
Bounty
$1000
Bounty
$10000
Bounty
$20
Bounty
$2000
Bounty
$250
Bounty
$50
Bounty
$500
Bounty
$5000
Bounty
$750
MoSCoW
Could have
MoSCoW
Must have
MoSCoW
Should have
Needs Feedback
Points
1
Points
13
Points
2
Points
21
Points
3
Points
34
Points
5
Points
55
Points
8
Points
88
Priority
Backlog
Priority
CI Blocker
Priority
Critical
Priority
High
Priority
Low
Priority
Medium
Signed-off: Owner
Signed-off: Scrum Master
Signed-off: Tech Lead
Spike
State
Completed
State
Duplicate
State
In Progress
State
In Review
State
Paused
State
Unverified
State
Verified
State
Wont Do
Type
Automation
Type
Bug
Type
Discussion
Type
Documentation
Type
Epic
Type
Feature
Type
Legendary
Type
Refactor
Type
Support
Type
Task
Type
Testing
Milestone
Clear milestone
No items
No milestone
v2.1.0
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
2 participants
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Blocks
#162 feat(skills): expose assets and gated non-standard resources through the skill tool
cleveragents/cleveractors-core
Reference
cleveragents/cleveractors-core!167
No description provided.