mirror of
https://github.com/Fission-AI/OpenSpec.git
synced 2026-11-08 09:22:50 +08:00
7313d6b024dbcd666c1925073197ebed67ffa509
18
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
d1642cb58c |
feat(easycode): add project skills and commands (#1352)
* feat: add Easy Code as a supported AI tool - Register 'easycode' in AI_TOOLS (config.ts) with skillsDir '.easycode' - Add EasycodeAdapter (easycode.ts): generates TOML commands at .easycode/commands/opsx/<id>.toml, matching Easy Code's native format - Export easycodeAdapter from adapters/index.ts - Register easycodeAdapter in CommandAdapterRegistry Easy Code (https://easycode.ai) is a terminal-based AI coding assistant. Its commands use TOML with a description field and a prompt multiline literal string, distinct from the Markdown/YAML frontmatter format used by most other tools. Tested locally: `openspec init --tools easycode` generates 5 SKILL.md files and 5 .toml command files in the expected directory structure. * fix: robust TOML serialization for Easy Code adapter Per code review: the original formatFile had unsafe manual escaping that would corrupt output for descriptions containing backslashes or control characters, and prompt bodies containing triple-single-quotes. Changes: - Add src/core/command-generation/toml.ts with two helpers: escapeTOMLBasicString — escapes \, ", \n, \r, \t for TOML basic strings (double-quoted) escapeTOMLMultilineString — escapes \ and \r, and breaks any run of 3+ consecutive " (lookahead match) for TOML basic multiline strings - Switch prompt block from triple-single-quote literal string (''') to triple-double-quote basic multiline string ("""), which allows full escape sequence support and handles arbitrary body content - Update easycode.ts to use both helpers * fix: escape disallowed control characters in TOML helpers Per code review: TOML basic strings forbid U+0000-U+0008, U+000B-U+000C, U+000E-U+001F, and U+007F. Add escapeControlChars() helper that replaces these with \uXXXX sequences, and apply it in both escapeTOMLBasicString and escapeTOMLMultilineString after their named-escape passes. * feat(easycode): harden project skills and command integration --------- Co-authored-by: Trae <konghaifeng@cmcm.com> Co-authored-by: Clay Good <hi@claygood.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
|
a7f08b8a46 |
feat(tools): add GSD skills support (#1082)
Co-authored-by: Clay Good <hi@claygood.com> Co-authored-by: Storm-Chaser <Storm-Chaser@users.noreply.github.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
|
297092cb25 |
feat(tools): add DeepSeek Harness support (#1672)
* feat(tools): add DeepSeek Harness support * docs(cli): clarify dsh tool id shorthand * docs(changeset): clarify dsh skill invocations vs command files * fix(tools): harden deepseek harness integration --------- Co-authored-by: Clay Good <hi@claygood.com> Co-authored-by: Claude Opus 5 <noreply@anthropic.com> |
||
|
Clay GoodandClaude Opus 5
|
626269ed73 |
fix(templates): stop generated skills naming workflows the profile omits (#1775)
* fix(templates): stop generated skills naming workflows the profile omits The `core` profile installs six of the twelve workflows, but the update and apply templates named `/opsx:continue` (6 times) and `/opsx:new` (twice) regardless. On a default install those became `/openspec-continue-change` and `/openspec-new-change` — skills that were never written — so `update-change` refused to create a missing artifact and handed off to a dead end. The only guard was a sentence asking the model to check availability at runtime, 70 lines above the two places it hits the wall. `command-references.ts` decides how a reference is spelled; nothing decided whether it should be emitted at all. Add that: templates author both wordings with `optionalWorkflow()`, and `getSkillTemplates()` / `getCommandTemplates()` — the one place every generation path already funnels the resolved workflow set through — pick a branch before the reference transformers run. A profile that omits a workflow now gets a concrete `openspec status` / `openspec instructions` fallback instead of a reference to a skill that does not exist. Closes #1734 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * chore(changeset): describe profile-aware workflow references Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * test(init): assert the core profile names no uninstalled workflow The end-to-end init test pinned the runtime availability hedging that #1734 is about, and asserted `/opsx:continue` appears in the default profile's generated update workflow — the bug itself. Assert the fixed behavior instead: neither `/opsx:continue` nor `/opsx:new` appears, and the CLI fallback is stated outright, for both the update and apply surfaces. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(templates): resolve every cross-workflow reference, not just core's The first commit fixed the two templates the default profile broke on. Every other cross-workflow handoff had the same shape, and arbitrary subsets are reachable: a `custom` profile is whatever the user picked, and `openspec update` re-derives a workflow set from what it finds on disk (legacy tool overrides, inferred Codex workflows) without passing it through getProfileWorkflows. So resolve all of them: - `apply` -> archive; `continue` -> apply, archive; `ff` -> apply; `new` -> continue; `propose` -> apply; `update` -> apply, archive; `archive` and `bulk-archive` -> sync. - `onboard`'s two command-reference tables are built from the installed set rather than printed in full with an "only if installed" caveat, and its explore, resume and next-step prompts are resolved the same way. Two supporting changes: - `onlyWithWorkflow()` plus a whole-line rule in the resolver: a conditional that owns its line takes the line with it when it resolves to empty, so a dropped table row cannot leave a blank line that ends the table in markdown. - `generateSkillContent()` and `generateCommand()` now throw on an unresolved marker. A generation path that skips the choke point fails loudly instead of writing `[[opsx:...]]` into a user's SKILL.md. The propose and ff surfaces keep their deliberate wording difference (#258): the command surface never invites "ask me to implement", so its missing-`apply` fallback names the CLI rather than a conversation. The guard test now runs the property over every subset that could expose a reference — each workflow alone, everything but one, the empty set, and the two shipped profiles — for skills and commands, in both spellings. Twenty-plus of those cases fail against the previous commit. Only `openspec-onboard` changes in the skills/ mirror: with every workflow installed, all other templates render byte for byte as before. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * chore(changeset): cover the full cross-workflow reference fix Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(templates): validate conditionals before choosing a branch Resolution discarded the unselected branch and only then checked for residual markers, so a truncated block inside the *missing* branch was accepted for a profile that installs the workflow and rejected for one that does not. Profile-dependent authoring errors are exactly what this module exists to remove. Validate the authored text up front instead: every marker must be one of the three recognized forms, and they must appear as a flat sequence of if / else / end. A malformed block now throws identically for every profile. The post-resolution check stays as a backstop. Caught by CodeRabbit on #1775. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * docs: state the profile-aware handoff rule in the skills reference alfred-openspec on #1775: docs-lab/reference/skills.md described several handoffs as unconditional while this change deliberately emits a CLI or conversational fallback when the profile omits the target. Stated once, above the entries, rather than as a caveat on each of the eleven affected Response and Creates rows: the page's recipe is one fact per row, and repeating the same conditional eleven times would bury the contracts it exists to state. The rows keep naming the skill that owns the next step, which is the fact a reader looks up; the rule above them says what happens when that skill is not installed. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(workflows): fold #1735 into the profile-aware references #1735 fixes the same issue (#1734) by removing the optional handoffs outright. This PR resolves them at generation time instead, which is strictly better for the template layer: an install that has `continue` still gets told about it. So the mechanism here wins and #1735's content is folded in, rather than the two competing for the same lines. What #1735 had that this did not: - src/commands/workflow/instructions.ts. The CLI's own runtime strings named the openspec-continue-change skill. Those are chosen at run time, so optionalWorkflow() cannot reach them; taken from #1735 verbatim. - The blocked-state fallback. It was a one-line pointer; it now carries #1735's full CLI recovery (select the next `ready` artifact, not `skipped` or `blocked`, read its rules with `openspec instructions`, keep the selected `--store` on both commands) plus the tracking-file repair path and the `missingArtifacts` field it branches on. The installed branch still names `/opsx:continue`, so neither audience loses. #1735's update-change.ts rewrite is not carried over: this PR already covers all six of those sites conditionally, which is the better answer. Both of #1735's test suites come across, and they are worth more here than there. test/core/templates/profile-handoffs.test.ts asserts that no generated file names an uninstalled workflow across every tool and all three delivery modes, which is the property this PR's mechanism exists to provide, and it passes against it. test/commands/profile-handoffs.test.ts covers the runtime CLI strings. The two guards are complementary: that one is broad on tools and deliveries, this PR's own profile-workflow-references.test.ts is broad on workflow subsets. #1735's command-references.test.ts assertions could not be carried as written, since they assume the reference is gone unconditionally. Replaced with a case that resolves the template against a set without `continue` and asserts the fallback carries the whole recovery. Verified it fails when the fallback is shortened. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * docs: name the core-profile fallback on the two rows that hit it The rule above the entries covers every profile, but apply-change and update-change are Core skills whose rows name openspec-continue-change, which the core profile never installs. On the default install those rows now say what the generated skill points to instead: openspec status and openspec instructions. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * docs(changeset): drop em dashes from the release note Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5 <noreply@anthropic.com> |
||
|
Clay GoodandClaude Opus 5
|
e571b5b9ae |
fix(security): harden CLI against hostile-repository inputs and clear dependency advisories (#1835)
* fix(deps): upgrade vitest to 4.1.11 and override fflate
Clears GHSA-82fw-gwwq-j7x9 (path traversal / arbitrary file read via
@vitest/mocker redirect mock), the subject of all three open Dependabot
alerts. No patched 3.x exists — 4.1.11 is the first fixed release — so the
major bump is unavoidable.
Two things the plain Dependabot bump (#1823) got wrong, which is why its
tests failed on every platform:
- It left @vitest/ui on 3.x, which dragged vite/esbuild to 0.28.2 and broke
the allowBuilds pin assertion in pnpm-workspace-config.test.ts. Upgrading
@vitest/ui in lockstep keeps esbuild on 0.28.1.
- Vitest 4 no longer lets an arrow function stand in as a constructor
implementation, so the ZshInstaller module mock threw "is not a
constructor" across 8 completion tests. Converted the three mock factories
to function expressions.
Also adds a pnpm override for fflate (GHSA-px8p-9vwx-vf98, infinite loop on
malformed ZIP64), which @vitest/ui 4.1.11 still pulls at 0.8.2.
`pnpm audit` is now clean: 0 vulnerabilities across all severities.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(core): bound schema size and stop prototype keys shadowing worksets
Two low-severity robustness defects found during the security review.
Workset lookups tested membership with `state.worksets[name] !== undefined`
on a plain-prototype object. `constructor`, `toString`, `valueof` and
friends are all valid kebab ids, so `openspec workset add constructor`
reported "already exists" against empty state, `getWorkset` returned a
function off the prototype, and `withoutWorkset` took the found branch for a
workset that was never there. All three sites now use `hasOwnProperty`.
This was never prototype *pollution* — nothing is written through these
keys and Zod's `z.record` drops `__proto__` — only a correctness defect.
`SchemaYamlSchema.artifacts` was unbounded while `validateNoCycles` walks it
with a recursive DFS, so a project-local schema declaring a long `requires`
chain crashed the CLI with an uncaught `RangeError: Maximum call stack size
exceeded` instead of a validation error. Capped at 1000 artifacts, which
also bounds the reference-resolution and graph work.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(security): stop repo-supplied text forging agent instructions
OpenSpec prints a pseudo-XML envelope that an AI coding agent consumes as
instructions, and interpolated repo content went in raw. The tags carry
authority - <project_context> means "background only", <task> means "do
this" - so a value that closes its own block is promoted from data to
directive.
Confirmed against a fresh build: a config.yaml `context:` value containing
`</project_context><system_override priority="critical">` landed a top-level
override block outside every "do NOT treat as instructions" guard. The same
breakout worked from `rules`, `description`, a dependency description, and a
schema `instruction`. A change directory name containing a quote forged
attributes on the <artifact> tag. In markdown output, a `context` line
starting with `##` forged a peer of the printer's own headings.
src/core/references.ts already had sanitizeInline written for exactly this
threat, documented as such, and simply was not applied here - it also only
flattened newlines, which one line of markup is enough to defeat. Extended it
and added three siblings beside it: escapeEnvelopeText, escapeEnvelopeAttribute,
and escapeEnvelopeCloseTags for content that must stay verbatim.
Template bodies deliberately get only their closing tags neutralized: the
shipped templates are full of `<!-- ... -->` comments and <placeholder>
markers that are copied into the generated artifact, so blanket escaping
would write <!-- into every file. A block can only end at a closing tag,
so that is the load-bearing control.
Rules and operation guidance are flattened but explicitly not truncated -
they are instructions an agent must follow in full.
Separately, `openspec update` decided skill freshness from the generatedBy:
line alone and never compared bodies, so appending a step to a generated
SKILL.md still printed "All 1 tool(s) up to date". Skills now get the same
byte-comparison command files already had, and the plan names the reason.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(security): remove super-linear scans and tighten write containment
Three regexes ran over whole repository files with a `\s` class that crosses
newlines under the `m` flag, so `^\s*` re-scanned from every line start. The
blowup is in the *failing* scan - a file with no `generatedBy:` line at all -
which is also the realistic attack file. Measured on this machine:
extractGeneratedByVersion, 63 KB whitespace SKILL.md 3,103 ms -> <5 ms
legacy-skill compare, 63 KB whitespace frontmatter 8,131 ms -> <5 ms
buildUpdatedSpec, 195 KB of `<!--` openers 6,817 ms -> ~90 ms
The first two are reached by `openspec update`, the first command run after
cloning. The third is reached from extractPurposeSection during `openspec
archive`, on the write path.
The scans now use `[ \t]` and walk lines, and maskHtmlComments is an indexOf
scan that visits each character once instead of a lazy regex that re-scans to
EOF from every `<!--`. Both rewrites were fuzzed against the originals -
200,000 random inputs each, 0 mismatches - so the `--!>` terminator and the
"unterminated comment runs to EOF" rule from #1413 are preserved exactly.
resolveTrustedSpecPath treated a failed containment check as permission to
re-root trust on the symlink's own target, on the theory that monorepo
symlinks may be intentional. A repo shipping openspec/specs/<cap> as a link
out of the tree therefore got `openspec archive` to write attacker-controlled
markdown to <external>/spec.md while printing the in-project path. The
fallback root must now still be inside the project, matching retireSpec,
which already refused to delete an external target.
Also: `validate <id> --type spec|change` short-circuited the name guard that
`show` applies, so a traversing id reached a bare path.join; and markTipSeen
wrote the global config through a predictable <config>.<pid>.tmp at default
0644 instead of the repo's existing writeFileAtomically (random name, 0600).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(security): harden subprocess and shell-config write paths
Defense in depth. The audit confirmed there is no shell injection anywhere in
src/ - no `shell: true`, no user value concatenated into a command line - so
none of these are live exploits; they are the sharp edges next to that line.
Completion install wrote the completions directory into .bashrc/.zshrc inside
double quotes, so a `$(...)` or backtick in HOME/XDG_DATA_HOME became command
execution on every future shell start. Both installers now single-quote the
path through a shared helper.
`feedback` shelled out for two probes (`which gh`, `gh auth status`) directly
alongside free-form user title and body text - the most plausible site for a
future injection regression. Both are execFileSync now, behavior unchanged.
Git subprocesses inherited the default 1 MB maxBuffer with no timeout, so a
large dirty tree made `git status --porcelain` throw ENOBUFS, which gitProbe's
bare catch turned into "no git facts" - `openspec doctor` then silently stopped
reporting uncommitted changes. They now share GIT_EXEC_OPTIONS (15s timeout,
16 MB buffer) the way readCliVersion already did, and the catch distinguishes
a resource failure from "git absent" so the degraded path is no longer silent.
The GITHUB_OUTPUT heredoc in validate-changesets used a fixed EOF delimiter
over a list of PR-authored paths; it is now run-unique.
Finally, both package.json files still carried a `pnpm` block. pnpm 10 uses
that block *instead of* pnpm-workspace.yaml rather than merging with it, which
is exactly the override-displacement trap dependabot.yml documents as #1812 -
and it is where Dependabot writes when it bumps an overridden package. The
block only duplicated `allowBuilds`, so removing it leaves both lockfiles
byte-identical with every advisory override intact, and denies Dependabot the
block to write into. The workspace test now asserts `pnpm` is absent entirely.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(security): pin the update check to TLS and honor telemetry opt-out
The update check asked whatever `npm_config_registry` named, over any
protocol. A code comment asserted that file contents deliberately cannot
choose the destination; that was not true. npm exports every config source it
reads, including a `registry=` line in a repository-local .npmrc that travels
with a clone - reproduced: `registry=http://169.254.169.254/` came straight
through `npm run`.
That is a cleartext GET at an address of the repository's choosing, and it
escalates. The attacker's reply says `{"version":"99.0.0"}`, which triggers
the upgrade prompt whose default is Yes; accepting runs `npm install -g`,
which npm resolves against that same attacker registry. Cloning a repository
and answering one prompt installs an attacker-chosen global package.
Both halves are now closed. The registry override is honored only over https,
falling back to the public registry otherwise, and canSelfUpgrade() refuses
when the resolved registry is not the public origin - a private mirror can
still inform the check but can never drive an install prompt. Redirects must
stay https and on the origin resolved up front, not merely the previous hop,
so no single reply can steer the request elsewhere. The comment now describes
what the code actually guarantees.
Separately, the opt-out env vars were exact-string matches, so DO_NOT_TRACK=true
and OPENSPEC_TELEMETRY=false both silently left telemetry ON - the spellings a
user is most likely to reach for, and inconsistent with the tolerant
isCiEnvironment() helper beside them. Parsing is now tolerant, shared between
both call sites, and fails safe: an unparseable value suppresses the request.
The first --json run also sent an event before the disclosure was ever shown -
the notice is correctly deferred so it cannot corrupt machine-readable output,
but trackCommand fired regardless, and agent-driven --json may be a user's only
mode. No event is sent and no anonymous id is created until the notice has
actually been printed.
No existing guard was weakened: the 256 KB body cap, 3-redirect cap, single
budget timer, strict version regex, argv-based spawn, CI/test guards and the
four-field payload are untouched.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(security): make the close-tag escape linear
CodeQL js/polynomial-redos on the escape added in
|
||
|
|
d9e1a28c38 |
fix(update): refresh generated files that drifted (#1808)
* fix(update): refresh generated files that drifted * test(update): isolate command drift from missing files and host config * chore(changeset): track the command-drift fix `openspec update` now reports and repairs tools it previously called up to date, so users will see a behavior change. That belongs in the changelog. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> --------- Co-authored-by: Clay Good <hi@claygood.com> Co-authored-by: Claude Opus 5 <noreply@anthropic.com> |
||
|
Clay Good
|
59bfb27a76 |
fix(codex): install skills in canonical agents directory (#1511)
* fix(codex): install skills in canonical agents directory * fix(codex): preserve shared agents compatibility * fix(codex): harden shared skill migration * fix(codex): preserve customized legacy skills * fix(codex): reject malformed generated versions |
||
|
|
161f9454a3 |
feat: add MiniMax Code skills support (#1214)
* feat: add MiniMax Code skills support to OpenSpec * fix: separate init skill and command output summaries * feat(minimax): add global skills support --------- Co-authored-by: showms <showms@users.noreply.github.com> Co-authored-by: Clay Good <hi@claygood.com> |
||
|
solanabandClay Good
|
1aa0f2abfc |
feat(init): add shared agents skills target (#1303)
Co-authored-by: Clay Good <hi@claygood.com> |
||
|
|
1637856c42 |
feat(adapters): follow the Windsurf rename to Devin Desktop (#1167)
* proposal: add devin desktop support
* feat(adapters): add devin desktop command adapter
- Create new Devin Desktop adapter for .devin/workflows/opsx-<id>.md
- Register adapter in CommandAdapterRegistry
- Export adapter from adapters index
- Update docs/supported-tools.md with Devin Desktop entry
- Add 'devin' to available tool IDs list
Devin Desktop uses the same Cascade workflow system as Windsurf,
making it a natural migration path for existing users.
* fix(config): add devin desktop to AI_TOOLS
Add Devin Desktop entry to AI_TOOLS configuration so that:
- getToolsWithSkillsDir() includes 'devin' as a valid tool ID
- getWorkspaceSkillToolIds() returns 'devin' in the list
- parseWorkspaceSkillToolsValue() accepts 'devin' as valid input
- openspec init --tools devin works correctly
This fixes validation failures where 'devin' was documented in
docs/supported-tools.md but not recognized by validation functions
that derive valid IDs from AI_TOOLS.
* fix(devin-adapter): escape implicit YAML scalars in frontmatter
Update escapeYamlValue to detect and quote implicit YAML scalars that
would be coerced by parsers:
- Booleans: true, false, yes, no, on, off
- Null variants: null, ~
- Numbers: integers, floats, exponentials, hex (0x), octal (0o)
- Edge cases: standalone dash (-) and dot (.)
This ensures values like 'true', '123', 'null' remain strings in YAML
frontmatter instead of being interpreted as booleans, numbers, or nulls.
Preserves existing escaping logic for special characters and newlines.
* test(devin-adapter): add comprehensive tests for Devin Desktop adapter
Add test coverage for the Devin Desktop adapter including:
- Command reference transformation from colon to hyphen syntax
- YAML frontmatter escaping for special characters and implicit scalars
- File path generation for workflows
- Integration with available tools detection
- Init and update command workflows
* Add cross-platform testcase.
* fix(devin): refresh deltas against canonical specs and point skills at skills
Addresses the two release blockers on this PR.
Archive: the change's MODIFIED blocks were written against an older
canonical `cli-init`, so `openspec archive add-devin-desktop-support`
aborted rather than merging. The deltas are regenerated from the current
canonical specs (cli-init `Skill Generation` + `Slash Command
Generation`, cli-update `Slash Command Updates`, and a new
`ai-tool-paths` delta for the `.devin` skillsDir), each restating every
existing scenario so archive is purely additive.
Invocation syntax: only Devin Desktop reads `.devin/workflows/`, so a
`/opsx-*` workflow reference is dead text on Devin Local, which supports
skills only. Devin now takes the skill-reference transformer, so skill
bodies and the getting-started hint say `/openspec-*`. Workflow bodies
keep hyphen references, applied by devinAdapter itself.
The adapter also drops its private copy of escapeYamlValue /
formatTagsArray in favor of the shared helpers main centralized in
#1447, which quote unconditionally and escape control characters.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix(devin): correct commands-only hint, fill doc gaps, cover both surfaces
Follow-up from adversarial review of the previous commit.
The devin special case in getTransformerForTool was unconditional, so
under commands-only delivery — where `.devin/skills/` is deleted — the
getting-started hint named `/openspec-propose`, a skill that is not on
disk. Devin now takes the skill transformer only when skills are
generated, and the hyphen form otherwise. The cli-init delta records the
fallback, and a unit test pins all three delivery modes.
Docs: `devin` was missing from the `--tools` list in docs/cli.md (which
mirrors the list supported-tools.md already had) and from the
command-syntax tables in docs/commands.md and docs/how-commands-work.md.
The supported-tools row gains a footnote citing Cognition's docs for the
`.windsurf/` -> `.devin/` move and the Devin Local workflow gap.
Tests: init and update now assert both surfaces — workflows carry
`/opsx-*`, skills carry `/openspec-*`, neither carries `/opsx:` — and
update checks the seeded skill was actually refreshed. Adds the negative
detection case. Drops three devin-only YAML assertions that duplicated,
less rigorously, the registry-derived escaping matrix that now enrolls
devin automatically.
Also reverts an unrelated zcode export and lingma reorder that a merge
resolution had pulled into adapters/index.ts. zcodeAdapter is registered
but missing from that barrel on main; that is a pre-existing gap and
belongs in its own change.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix(devin): name the right command in the profile migration notice
The profile-migration notice printed by both `init` and `update` hardcoded
`/opsx:propose` for every adapter-backed tool. Devin registers no such
command on any surface — its workflows answer to `/opsx-propose` and its
skills to `/openspec-propose` — so an upgrading Devin user was told to run
something that does not exist:
Migrated: custom profile with 6 workflows
New in this version: /opsx:propose.
The reference now goes through getTransformerForTool, the same call
init.ts already makes for the getting-started hint. Devin prints
`/openspec-propose`; opencode and the other filename-invoked tools are
corrected to `/opsx-propose` as a side effect; claude is unchanged.
Also corrects two inherited false claims in the cli-update delta — Devin
workflows carry no OpenSpec markers, and update writes every profile
workflow rather than only refreshing files that already exist, which the
PR's own test demonstrates. Qualifies the supported-tools footnote for
commands-only delivery, and strips trailing whitespace.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix(devin): keep the cli-update delta in step with the canonical spec
The delta restates the whole 'Slash Command Updates' requirement, and its
copy of the OpenCode scenario predated #1471 — archiving it would have
quietly reverted the spec to calling the hyphen rewrite an OpenCode special
case, the hand-maintained framing #1471 removed. Archive on a scratch copy
is now purely additive.
Also point tasks.md at the generator rather than the deleted
transformToHyphenCommands, and enroll devin in the pure-formatter tripwire —
it is the one adapter whose private body transform was just removed, so it
is the likeliest to have it re-added.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat(adapters): follow the Windsurf rename to Devin Desktop, with migration
Windsurf was rebranded to Devin Desktop on 2026-06-02 and its config
directory moved: `.devin/` is the preferred read+write location, `.windsurf/`
a legacy read-only fallback. Devin Local does not read `.windsurf/` at all,
so an existing Windsurf user's OpenSpec files are invisible to it.
Carrying `devin` as a second tool id alongside `windsurf` would list one
product twice and leave upgraders with two parallel installs — `openspec
update` even told them to create the second one ("Detected new tool: Devin
Desktop"). This follows the rename instead, as the repo already did for
Kimi CLI -> Kimi Code:
- `windsurf` is retired as a tool id; `devin` takes its place, with
`detectionPaths: ['.devin', '.windsurf']` so pre-rebrand projects are
still recognized. The Windsurf adapter is replaced, not duplicated.
- `TOOL_ID_ALIASES` keeps `--tools windsurf` resolving, so existing setup
scripts and CI keep working; they now configure `.devin/`.
- OpenSpec-managed skills (`openspec-*`) and command files (`opsx-*`) under
`.windsurf/` move to `.devin/`. The kimi migration handled skills only;
command files now move too, deriving the legacy path from the adapter's
own getFilePath rather than hard-coding a layout.
- The move is offered, not taken: nothing on disk distinguishes a user who
took the rebrand from one still on a pre-rebrand Windsurf build that reads
only `.windsurf/`. `openspec update` explains the rename and asks; --force
and non-interactive runs migrate; declining leaves every file untouched and
says what that costs. Files the user wrote are never moved.
Also gives Devin its own row in the authoritative invocation table — the
catch-all row claimed `/opsx-<id>` for both agents, which is wrong for Devin
Local.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix(devin): stop the migration from deleting anything it does not own
An adversarial pass found two ways the move destroyed files.
Symlinked roots wiped the install. `ln -s .devin .windsurf` is a realistic
way to straddle the rebrand, and it makes source and destination the same
file — so the "destination exists, drop the legacy copy" branch deleted the
only copy. Twelve generated files, gone, and not regenerated: the wipe
happens before tool detection, so update then reported no configured tools.
Both roots are now realpath'd and a self-move is skipped.
User content inside an OpenSpec-managed path was deleted. The same branch
rm -rf'd the whole legacy skill directory, taking a hand-written
reference.md beside SKILL.md with it, and deleted a legacy command file even
when the user had edited it. Now only SKILL.md is removed from a skill
directory, and a command file is removed only when byte-identical to the
one that survives — an edit is left where it is.
Also: declining the move stranded the user. `update` then printed "No
configured tools found. Run openspec init", which is wrong — the project is
configured, just in the directory OpenSpec no longer writes. It now says so
and how to resume. A closed stdin during the prompt aborted the whole
update; it is treated as a decline.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs(devin): add a changeset for the Windsurf rename and migration
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix(devin): move only SKILL.md, never the skill directory around it
alfred caught a data-loss path the earlier fix missed. When the destination
did not yet exist, migration renamed the whole legacy skill directory into
`.devin/` — carrying any file the user kept beside `SKILL.md` with it. That
destination is a directory OpenSpec owns and removes on its own: under
commands-only delivery, or for a workflow outside the active profile. So the
move handed the user's file to a later rm and it vanished.
Reproduced on `d94af8b`: with `delivery: commands`, a `reference.md` beside a
legacy `SKILL.md` was gone after `openspec update`.
Only `SKILL.md` crosses now, in both branches; anything else stays under the
legacy root, and the legacy directory is still removed when the move leaves
it empty. Regression tests cover the commands-only and deselected-workflow
cases and both fail against the previous code.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix(devin): treat an edited skill the way an edited command is already treated
A final adversarial pass found the two paths disagreeing. When both roots
held the same file with different content, the command path compared bytes
and kept the user's version; the skill path deleted it with no comparison —
so one `openspec update` destroyed an edited SKILL.md while preserving an
edited opsx-*.md in the same project.
Both now share one `classifyManagedFile` rule: move when the destination is
empty, drop the legacy copy only when byte-identical, otherwise leave it.
Anything left behind is reported, so a user who customized a file knows two
copies exist rather than discovering it later.
Note on the other finding from that pass: OpenSpec regenerating or pruning
the files it owns is long-standing behavior, not something this PR
introduces. Verified against main — an edited SKILL.md under a deselected
workflow, and an edited selected skill and command, are all destroyed by
`openspec update` on
|
||
|
|
10fa39b1c3 |
fix(update): refresh command files for tools configured without skills (#1442)
* fix(update): mark command-configured tools as needing update when skill version is missing * fix(update): compare command content fingerprint for commands-only tools when skill version is missing * test(update): isolate config homes in regressions * fix(update): keep skill drift detectable behind the command fingerprint Review follow-ups on the commands-only update fix: - Only fall back to the command-content fingerprint when a tool has no skill files at all. Gating on `generatedByVersion === null` also swallowed the case where a SKILL.md exists but its version is unreadable, so a truncated or hand-edited skill file could never be repaired by `openspec update` again. - Drop the command `generatedBy` scan: command adapters emit no version stamp, so the loop was unreachable and made the fingerprint fallback read as a secondary path rather than the only one. - Compute version status with the same workflow set the generation loop writes (`legacyWorkflowOverrides[toolId] ?? desiredWorkflows`), so a legacy-upgraded tool is not fingerprinted against commands it was never given. - Remove the unread `delivery` option from the three tool-detection signatures, the leftover `getCommandConfiguredTools` / `COMMAND_IDS` imports, and the unused `toolHasAnyConfiguredCommand` re-export. - runCLI: never let temp-dir cleanup replace the CLI result or a real failure, and treat an explicitly-empty XDG_CONFIG_HOME as an override. Adds regressions for the unreadable-skill case and for a deselected workflow leaving a command file behind, and documents how "up to date" is decided. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(update): ignore CRLF and BOM when fingerprinting command files Round-two review follow-ups: - Command files are committed project files. A Windows clone with `core.autocrlf` re-materializes them with CRLF endings, which the byte-exact comparison read as drift: every fresh checkout spent one `openspec update` rewriting identical content and announcing a bogus "unknown → <version>". Normalize CRLF and a leading BOM on both sides before comparing. - Collapse `getCommandConfiguredTools`, which the widened `getConfiguredTools` made a strict subset of itself, into the single remaining caller. - Correct the new `openspec update` doc paragraph: content drift is only detected for commands-only installs, so it must not promise that hand edits are always overwritten. - Add the changeset this repo requires per fix. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore(update): drop dead exports and correct stale status doc comments `ToolVersionStatus.configured` and `.generatedByVersion` are now fed by command files too, so their comments no longer say "skills". Removes the barrel exports and the `options` parameter this change added but nothing consumes, and the import left dangling by the previous commit. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * test(update): make the CRLF fixture idempotent on a CRLF checkout Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * test(update): cover non-claude adapters and a custom profile The fingerprint regressions all ran against claude and the core profile, so two things were covered by reasoning rather than by an executed test: - Command paths differ in shape per adapter. Added a parametrized case over gemini (nested dir, TOML), cursor (flat opsx-* file), and cline, whose commands live in .clinerules/workflows — not in its skillsDir (.cline) at all, so a commands-only install leaves that directory absent. Each asserts detection, a clean fingerprint, and drift. Reverting the getConfiguredTools widening fails all three. - A custom profile must be fingerprinted against its own workflow subset. The new case inits with ['explore', 'apply'] and asserts the same tree reads as drifted when compared against the wider core set. Making the fingerprint ignore the caller's workflows and fall back to global config fails it. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Clay Good <hi@claygood.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Clay GoodandClaude Opus 4.8
|
a874d1d671 |
chore(security): create test temp dirs with mkdtemp and override two pinned CVEs (#1432)
* test: create temp dirs with fs.mkdtemp
Every one of these suites built its temp directory by hand:
testDir = path.join(os.tmpdir(), `openspec-test-${randomUUID()}`);
await fs.mkdir(testDir, { recursive: true });
That check-then-create is what CodeQL's js/insecure-temporary-file flags,
and it accounted for 452 of the repo's 467 dismissed code-scanning alerts.
Dismissing them one by one is a treadmill: every new suite that copies the
idiom mints fresh alerts, and a real finding is easy to lose in that volume.
fs.mkdtemp creates the directory atomically at mode 0700 with a random
suffix, so there is no window to pre-empt and no name to guess. The suites
that already used it are the evidence this silences the rule: 33 of the 34
files calling mkdtemp carry zero alerts. The lone exception, archive.test.ts,
was scanned one commit before its own mkdtemp fix landed and is left to that
change rather than conflicting with it.
The dirs named on Date.now() alone were genuinely predictable; the randomUUID
ones were not, but they trained the same copy-paste. Both are gone now.
Behavior is unchanged: mkdtemp creates the root the old mkdir created, and
no assertion depended on the root being absent. Verified with the full suite
(2196 tests, 111 files).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(deps): override postcss and sharp in the website
Two advisories on the docs site have no Dependabot PR and never will:
Next pins postcss at 8.4.31 as a direct dependency and sharp at ^0.34.5 as
an optional one, so Dependabot cannot raise either without a Next release
that does it first. 16.2.11 does not — it still pins both. Left alone these
sit open indefinitely.
postcss 8.4.31 -> 8.5.22 GHSA-qx2v-qp2m-jg93 (XSS via unescaped </style>)
sharp 0.34.5 -> 0.35.3 GHSA-f88m-g3jw-g9cj (4 libvips CVEs)
A version-ranged selector (`postcss@<8.5.10`) was the first instinct, since it
lapses on its own once Next moves past it. It is the wrong tool: it pins the
override to one advisory's floor, and silently stops applying when the next
advisory raises that floor. GHSA-6g55-p6wh-862q landed while this branch was
open and moved postcss's patched floor to 8.5.12 — under the ranged selector a
dependency pinning 8.5.11 would have resolved to 8.5.11 and stayed vulnerable.
A plain floor cannot under-match, so that is what this uses.
The floor also covers the new advisory: 8.5.22 is past 8.5.12. postcss dedupes
to the single copy the site already had for Tailwind.
These are the last two open Dependabot alerts on the repo. `pnpm audit` on
website/ goes from 2 advisories to "No known vulnerabilities found". The site
builds clean, OG image generation included, and the package set grows by
exactly two platform-gated wasm32 binaries that never install on CI.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* ci(security): audit the docs site too
Both `pnpm audit` steps run at the repo root. The docs site keeps its own
lockfile and is not a workspace member, so neither step could see it — the
root audit passed all the way through while postcss and sharp sat open in
website/. That blind spot is why they needed a manual override to find.
Blocking rule copied from the published-dependency audit: advisory on pull
requests, blocking on the weekly schedule and on pushes to main. An
always-advisory step would only relocate the blind spot — the sweep would stay
green with a live advisory and someone would have to read the log of a passing
run to notice.
`!cancelled()` because the two audits above can fail hard. Without it a root
advisory would skip this step entirely, in exactly the situation where the
site's own state matters most.
Verified against the pre-fix lockfile — the step reports the two advisories it
would have caught:
2 vulnerabilities found
Severity: 1 moderate | 1 high
and reports "No known vulnerabilities found" against the fixed one. Confirmed
it reads website/pnpm-lock.yaml and not the root: with a vulnerable website
lockfile and a clean root, it exits 1; a missing website lockfile is a hard
ERR_PNPM_AUDIT_NO_LOCKFILE rather than a false clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
||
|
|
ac656c983f |
feat: add CodeArts Agent skills support (#1266)
* feat/add codeartsagent to tool list * feat/add codeartsagent to tool list * test: clarify CodeArts init log assertions * docs(cli): union hermes and zcode into the supported tool-ID list Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Clay Good <hi@claygood.com> Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
Clay GoodandClaude Fable 5
|
a70daccf0e |
feat(skills): propose /opsx:update planning-artifact update skill (#1278)
* docs(openspec): propose add-update-workflow — graph-driven /opsx:update + cohesive audit
Dogfooded OpenSpec proposal for the missing first-class "update" action:
a /opsx:update workflow that propagates an edit to one artifact across its
downstream dependents (targeted mode) or audits a whole change for stale/
incoherent artifacts (audit mode) — driven by the schema's artifact graph,
never hardcoded filenames, editing planning artifacts only (never code).
- artifact-graph: expose reverse-dependency queries (getDependents/getDownstream)
+ a requires-edge mtime staleness signal (the engine already builds the
dependents map at graph.ts:98 and discards it).
- cli-artifact-workflow: surface requires/dependents/stale on `openspec status
--json` and add a `--impact <artifact>` downstream-revisit-order selector.
- opsx-update-skill: the user-facing /opsx:update command (targeted + audit).
Supersedes the proposal-only stub add-artifact-regeneration-support. Addresses
the cluster #1188/#705/#673/#247 (closes), #694/#684/#618 (answers), and is
graph-driven to avoid the #777/#666 hardcoded-artifact-pattern bug class.
Validates clean under `openspec validate --strict`.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(openspec): make add-update-workflow deterministic & grounded (Tabish review)
Reframe per the steer "more deterministic and grounded in reality":
- Deterministic spine: the CLI computes the impact set (which downstream
artifacts to revisit, in build order, with paths) as a pure function of
schema edges + filesystem. The agent only rewrites prose. Grounded in real
APIs already present: getUnlockedArtifacts (direct dependents), getBuildOrder
(order), resolveArtifactOutputs (paths); reverse map built at graph.ts:82-87.
- Replace fragile mtime staleness with a newline-normalized SHA-256 content
digest (reproducible cross-platform). Drift = upstream digest vs recorded
baseline; no baseline => "unknown", never a false positive. mtime and pure-git
rejected with rationale; digest ledger is a separable, optional layer.
- Explicit determinism boundary decision (CLI decides files/order/drift; agent
rewrites). Skill MUST source the file list/order from `openspec status
--impact`, never compute it.
- Corrected all code citations to verified lines (graph.ts:82-87,
instruction-loader.ts:366/429, status.ts); noted #1277's coverage helpers are
not in this branch's base (coordinate, don't reuse).
- Specs updated: artifact-graph Content Digest requirement; cli status digest +
deterministic impact ordering; skill determinism + baseline-aware audit.
tasks add digest/determinism/cross-platform tests + optional ledger section.
Still validates clean under `openspec validate add-update-workflow --strict`.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(openspec): harden add-update-workflow determinism; drop direct name refs
- Digest ledger tracks DIRECT upstream digests; document that transitive drift
emerges hop-by-hop as downstream is reconciled (no transitive bookkeeping).
- Ground audit's no-baseline structural facts on signals available in this
branch (missing/empty output, blocked/incomplete); capability-coverage is an
add-on only when #1277's validateChangeCapabilityCoverage is present.
- Add the "update revises only existing downstream; defer not-yet-created ones
to /opsx:continue" rule across proposal/design/specs/tasks; impact entries now
carry existence/status.
- Note artifact-level (not file-level) granularity and that getDownstream
terminates by the schema's acyclic guarantee.
- Remove direct personal references from the docs.
Validates clean under `openspec validate add-update-workflow --strict`; 10 deltas.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(openspec): full issue/PR/discussion coverage + command-family design
After a comprehensive sweep of open issues, PRs, and discussions, grounded the
proposal in the complete adjacent landscape and answered the open design
questions the cluster raises:
- #783 (Cross-artifact quality review before apply) is now a primary Closes:
it IS audit mode. Answer its open "new skill vs. extend validate" question via
the determinism split — deterministic checks (drift/completeness/coverage) are
CLI/validate-shaped; the semantic cross-artifact review is the skill. Added a
skill spec scenario for the #783 patterns (scope contradiction, spec gap,
duplication).
- Discussion #1206 ("refine proposal now?") + prior-art PR #372: official answer
is /opsx:update.
- New design Decision 8 (command family): delineate /opsx:update from
/opsx:clarify (#702, within-artifact), /opsx:review (#1251, plan-vs-code), and
verify; /opsx:update consolidates update+regen+refine into one action,
addressing skill-sprawl (#1263, #783).
- Reuse, don't reinvent: audit's empty/incomplete check reuses #1098's
artifactOutputComplete (same outputs.ts the digest helper lives in); capability
coverage reuses #1277's validateChangeCapabilityCoverage.
- New open questions: surface deterministic coherence in `validate` for a CI gate
(#783-B, #829); naming reconciliation with #783's /opsx:refine.
- Confirmed add-update-command* branches are the `openspec update` tool-file
refresh (not artifact update) — no collision.
Validates clean under --strict; 10 deltas; all relative links resolve.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(openspec): resolve open questions to committed decisions; drift in scope
Per review steer, every open question is now a committed happy-path decision so
build-out has no dangling forks, and the deterministic drift baseline is pulled
into scope (it is what makes audit-mode drift deterministic vs. agent-guessed):
- Digest ledger IN SCOPE (design Decision 3): per-artifact DIRECT upstream
digests in ChangeMetadataSchema, written by a deterministic `openspec status
--record`; pre-existing changes (no baseline) degrade to drift `unknown` +
structural checks. Generating-flow auto-recording stays optional (graceful).
- cli-artifact-workflow spec: folded drift into the digest requirement (record
baseline / drift vs baseline / unknown-without-baseline) — stays at 10 deltas.
- opsx-update-skill spec: skill records baseline via `--record` after each
confirmed edit, so audits clear once reconciled.
- Replaced "## Open Questions" with "## Decisions resolved": ledger in scope;
targeted entry baseline-aware; apply stays standalone (points to update on
drift); cross-change (#247), continue/ff de-hardcoding (#777), and validate
CI-gate (#783-B/#829) are named follow-ups, not deferrals of the core feature;
/opsx:update kept as the umbrella name.
- Migration Plan + Capabilities + Impact + tasks updated; status JSON gains
`drift`, CLI gains `--record`. Re-synced with upstream main (0 behind).
Validates clean under --strict; 10 deltas; all links resolve.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(openspec): harden add-update-workflow — close cross-OS, read-only, edge gaps
Stress-tested every claim against live source and fixed the soft spots:
- Cross-OS digest determinism (real bug): resolveArtifactOutputs (outputs.ts:34)
sorts ABSOLUTE paths via .sort(), which differs by OS — so a multi-file glob
artifact (specs/**/*.md) would hash differently on Windows vs POSIX. Digest now
specified to order files by change-relative forward-slash path and hash
relpath+content. Added spec scenarios (cross-platform glob stability; rename
changes digest) and a cross-OS test task.
- Read-only status invariant: moved baseline recording OFF `openspec status`
(a read command silently mutating the drift reference is a footgun) to a
dedicated `openspec reconcile` write verb. Updated spec, skill, design, impact,
capabilities, tasks; reconciled the "no new verb" claims.
- Edge case: missing upstream at record time is stored as an explicit `absent`
marker so later creating it registers as drift (spec scenario added).
- Edge case: coherent change yields no edits (clean-path scenario).
- Grounding fixes: continue-change hardcoded block is duplicated (skill 103-112 +
command 225-234) — both must be fixed in the #777 follow-up; verified no
content-hash util exists.
- Fixed two stale claims the layered edits left: the Impact digest bullet
(concatenation→relative-path) and the naming-boundary line.
Validates clean under --strict; 10 deltas (4+3+3), 44 scenarios; all links
resolve; re-synced with upstream main (0 behind); issue/PR/discussion sweep
re-run, no new items.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(openspec): pin data contracts + digest forward-compat; delineate #880
Grounded the surface so an implementer builds it without guessing, and added
proportionate forward-compatibility:
- New design "Data contracts" section with exact shapes: extended ArtifactStatus
(requires/dependents/digest/drift/driftFrom — additive to the real interface at
instruction-loader.ts:120), the --impact response, and the `.openspec.yaml`
baselines ledger. All additive; nothing existing changes type.
- Digest scheme tag (`sha256-relpath-v1:`) + forward-compat: drift compares only
same-scheme digests; an unrecognized/older scheme reports `unknown` rather than
silently mis-comparing — re-reconcile restores it. Added a cli spec scenario
and tasks for it.
- Grounded the ledger write: there is no central change-metadata writer today
(change-metadata/index.ts only re-exports schema), so reconcile does a safe
read-modify-write of .openspec.yaml mirroring the store's
parse/serialize/writeStoreMetadataState pattern (foundation.ts).
- Coverage: re-swept; folded #880 (/opsx:validate code-vs-living-specs) into the
plan-vs-code delineation alongside #1251/#1073. Main unchanged (
|
||
|
Tabish Bidiwale
|
4ba26902df |
feat: simplify skill installation with profiles and smart defaults (#726)
* feat: implement simplified skill installation with profiles and smart defaults Introduces a profile system (core/custom) to reduce the default workflow count from 10 to 4, auto-detects AI tools during init, adds a new `propose` workflow combining new+ff, fixes multi-select keybindings, and adds backwards-compatible migration for existing users. * feat: harden update config drift, command-only detection, and init profile validation Address post-implementation review findings: update now detects profile/delivery drift even when template versions are current, recognizes command-only installs as configured tools, init validates --profile values and applies delivery cleanup on re-init. Specs and design docs updated with new scenarios and rationale. * fix: address AI reviewer feedback on config, detection, and test cleanup - Add error handling for execSync in config profile apply and use static import - Fix config list showing "(explicit)" for core profile workflows misleadingly - Add missing 'openspec-onboard' to SKILL_NAMES for parity with COMMAND_IDS - Remove unused fsSync import in init tests - Fix configTempDir leak in test afterEach cleanup * docs: add qa smoke harness change proposal |
||
|
Rodrigo Passos
|
697738bc9b |
fix(opencode): transform command references from colon to hyphen format (#626)
* Add OpenCode files to gitignore * docs(changes): add opencode-command-references change artifacts * fix(opencode): transform command references from colon to hyphen format |
||
|
Tabish Bidiwale
|
3261ccf6dc |
feat: onboarding skill and comprehensive documentation overhaul (#574)
* feat(skills): add opsx:onboard guided workflow skill Add a new onboard skill that walks users through their first complete OpenSpec workflow cycle. The skill provides interactive guidance through task selection, change creation, artifact building, implementation, and archiving. Also includes: - New README with updated branding and workflow examples - Documentation structure placeholders - Change artifacts for the onboard skill feature * test(skills): update skill-generation tests for onboard skill Update test expectations from 9 to 10 skills after adding opsx:onboard. * docs: update README links and add doc cleanup checklist - Replace placeholder links in README_NEW.md with actual doc paths - Add documentation cleanup checklist to README_RENEWAL_PROMPTS.md * docs: overhaul documentation with new workflows, getting-started, and customization guides - Rewrite workflows.md with action-based philosophy and workflow patterns - Rewrite getting-started.md with clearer onboarding flow - Rewrite customization.md with schema customization guidance - Add cross-references between docs (Commands, Customization links) - Remove obsolete docs: artifact_poc, experimental-release-plan, project-config-demo, schema-customization, schema-workflow-gaps - Update README_RENEWAL_PROMPTS.md checklist * docs: continue documentation overhaul with expanded guides and restructuring - Expand cli.md, commands.md, and concepts.md with comprehensive content - Add installation.md, multi-language.md, and supported-tools.md - Rename experimental-workflow.md to opsx.md - Remove i18n.md (replaced by multi-language.md) - Update README links and cleanup prompts * chore(assets): consolidate logo images * docs: enhance README with badges, usage notes, and contributing guidelines - Update Discord badge to show member count - Add collapsible section with stars/downloads/contributors badges - Add OpenSpec Dashboard preview section - Add usage notes for model selection and context hygiene - Expand contributing section with guidelines for small/large changes - Clarify AI-generated code policy * docs: remove misleading mid-flight update claims The documentation claimed users could edit artifacts mid-implementation and seamlessly continue, but no such mechanism exists. This removes: - "Mid-Flight Correction" section from workflows.md - Feedback arrows and "update as you learn" from all diagrams - Mid-flight claims from commands.md, opsx.md, concepts.md - Example blocks showing edit-then-continue workflow Also adds a proposal for future artifact regeneration support that would actually make this workflow possible. * docs: fix PR review comments (markdown linting and accuracy) - Add language tags to fenced code blocks (MD040) - Remove blank line between blockquotes (MD028) - Capitalize "Markdown" as proper noun - Update deprecated command reference (experimental -> update) - Update skill count from 9 to 10, add openspec-onboard - Fix typo: fix-midlight -> fix-midflight * chore: remove polish-release-notes CI workflow Replaced with local /polish-release skill. The claude-code-action doesn't work well with repository_dispatch triggers (no PR context). * docs: clarify /opsx:sync is optional (archive prompts if needed) Remove sync from main workflow flows and diagrams since archive already prompts to sync when needed. Most users will never need to call sync directly. - Remove sync from completion flow diagrams - Remove "Sync Specs Regularly" best practice section - Update command descriptions to note it's optional - Update "When to sync" to "When to use manually" * docs: redesign README with simplified content and new OPSX callout - Simplify badges and logo presentation - Add collapsible "most loved" section - Replace detailed explanation with concise philosophy - Add prominent /opsx:onboard callout for new workflow - Remove README_NEW.md (content merged into README.md) - Remove renewal prompts documentation * docs: add README_OLD.md as reference backup * docs: fix command directory paths for multiple tools Correct commands locations for Antigravity, Codex, Crush, OpenCode, and Qoder in the supported tools table. |
||
|
Tabish Bidiwale
|
39bebefcc4 |
feat(cli): merge init and experimental commands (#565)
* feat(core): add legacy cleanup detection functions for init migration Implement src/core/legacy-cleanup.ts with detection and cleanup functions for all legacy OpenSpec artifact types: Detection functions: - detectLegacyConfigFiles() - checks for config files with OpenSpec markers (CLAUDE.md, CLINE.md, CODEBUDDY.md, COSTRICT.md, QODER.md, IFLOW.md, AGENTS.md, QWEN.md) - detectLegacySlashCommands() - checks for old /openspec:* command directories and files across all 21 tool integrations - detectLegacyStructureFiles() - checks for openspec/AGENTS.md and openspec/project.md (project.md preserved for migration hint) - detectLegacyArtifacts() - orchestrates all detection Utility functions: - hasOpenSpecMarkers() - checks if content has OpenSpec markers - isOnlyOpenSpecContent() - checks if file is 100% OpenSpec content - removeMarkerBlock() - surgically removes marker blocks from mixed content Cleanup functions: - cleanupLegacyArtifacts() - orchestrates removal with proper edge cases: - Deletes files that are 100% OpenSpec content - Removes marker blocks from files with mixed content - Deletes legacy slash command directories and files - Preserves openspec/project.md (shows migration hint only) Formatting functions: - formatDetectionSummary() - formats what was detected before cleanup - formatCleanupSummary() - formats what was cleaned up after This is task 1.1 for the merge-init-experimental change. * feat(utils): add removeMarkerBlock() for surgically removing marker blocks - Add removeMarkerBlock() function to file-system.ts that properly handles inline marker mentions by using findMarkerIndex/isMarkerOnOwnLine - Refactor legacy-cleanup.ts to use the shared utility - Export removeMarkerBlock from utils/index.ts for reusability - Add comprehensive tests for inline marker mention edge cases - Add tests for shell-style markers and various whitespace scenarios The new implementation correctly ignores markers mentioned inline within text and only removes actual marker blocks that are on their own lines. * feat(core): add formatProjectMdMigrationHint() for migration messaging - Add standalone formatProjectMdMigrationHint() function for reusable migration hint output directing users to migrate project.md content to config.yaml's "context:" field - Update formatDetectionSummary() to include the migration hint when project.md is detected (not just in cleanup summary) - Refactor formatCleanupSummary() to use the new function for consistency - Add unit tests for the new function and updated behavior * test(init): rewrite init tests for experimental workflow approach Rewrites the init command tests to verify the new experimental workflow implementation. The new tests cover: - OpenSpec directory structure creation (specs, changes, archive) - config.yaml generation with default schema - 9 Agent Skills creation for various tools (Claude, Cursor, Windsurf, etc.) - 9 slash commands generation using tool-specific adapters - Multi-tool support (--tools all, --tools none, specific tools) - Extend mode (re-running init) - Tool-specific adapters (Gemini TOML, Continue .prompt, etc.) - Error handling for invalid tools and permissions Removes old tests for legacy config file generation (AGENTS.md, CLAUDE.md, project.md, etc.) as the new init command uses Agent Skills instead. * test(update): rewrite tests for skills/commands refresh behavior Update the update command tests to match the new implementation that refreshes skills and opsx commands instead of config files. Changes: - Remove old ToolRegistry import (deleted module) - Rewrite tests to verify skill file updates - Rewrite tests to verify opsx command generation - Add tests for multi-tool support (Claude, Cursor, Qwen, Windsurf) - Add tests for error handling and tool detection - Fix test assertions to match actual skill template names The update command now: - Detects configured tools by checking skill directories - Updates SKILL.md files with latest skill templates - Generates opsx commands using tool-specific adapters * docs(readme): update documentation for new init behavior - Replace tool list with simplified supported tools section (skills-based) - Update init instructions to document --tools flag, --force, and legacy cleanup - Replace project.md with config.yaml documentation - Update workflow examples to use /opsx:* commands instead of /openspec:* - Add command reference table for slash commands - Update Team Adoption and Updating sections for new workflow - Replace Experimental Features with Workflow Customization section * refactor(cli): remove legacy configurators and merge experimental into workflow - Delete src/core/configurators/ directory (ToolRegistry, all config generators) - Delete legacy templates (agents-template, claude-template, project-template, etc.) - Move experimental commands to src/commands/workflow/ with cleaner structure - Remove experimental setup.ts and index.ts (functionality merged into init) - Update CLI to register workflow commands directly instead of through experimental - Update openspec update command to refresh skills/commands instead of config files - Update tests for new command structure * refactor: extract shared modules and move AGENTS.md to root - Move AGENTS.md from openspec/ to project root - Add shared module with tool-detection and skill-generation utilities - Update legacy-cleanup with improved cleanup logic - Enhance update.ts with additional functionality - Add comprehensive tests for shared modules * fix(ui): update welcome screen tagline Change from experimental reference to reflect the merged workflow. * fix: improve Windows cross-platform compatibility - Handle both forward and backward slashes in path parsing - Normalize paths before regex matching for legacy artifact detection - Use regex split for both path separators in tool directory extraction - Handle CRLF line endings when cleaning up multiple blank lines - Add retry logic for test file cleanup to handle Windows file locking * fix(init): use dynamic counts for skills and commands in success message Replace hard-coded "9 skills and 9 commands" with dynamic values from getSkillTemplates().length and getCommandContents().length to prevent the message from diverging from reality when skills/commands change. * fix: various small improvements across init, cleanup, and file handling - Remove shell prompt characters from README bash examples (MD014) - Show actual config filename (config.yaml vs config.yml) in init output - Include hasProjectMd in hasLegacyArtifacts to show migration hint - Add existence check before AGENTS.md deletion to avoid spurious errors - Preserve leading whitespace and original newline style in file operations - Use dynamic tool list from CommandAdapterRegistry in tests |