smart-commit-copilot-cli 0.1.6 → 0.1.8

package/CHANGELOG.md

@@ -6,6 +6,48 @@ The format is based on Keep a Changelog, and this project follows Semantic Versi
 
 ## [Unreleased]
 
+## [0.1.8] - 2026-05-21
+
+### Added
+
+- `smart-commit pull-request create` command for GitHub pull request and GitLab merge request creation from the current branch
+- bridge auto PR/MR creation after successful push via `pullRequest.autoCreateAfterPush`
+- `pull-request-create` schema target and structured `pullRequestCreation` bridge output
+- GitHub/GitLab remote detection, existing PR/MR checks, remote compare data, PR/MR title and description generation, and platform API creation support
+- report periods `last-week`, `last-month`, and `last-quarter`
+- focused PR/MR tests for remote parsing, generated content protocol, and prompt serialization without auth material
+
+### Changed
+
+- renamed staged summary configuration and output from `pullRequestSummary` to `stagedChangeSummary`; old canonical `pullRequestSummary` config is rejected
+- output language defaults now use `zh-cn`; `zh` is no longer accepted in CLI flags, environment variables, config files, or legacy keys
+- `connection.llmResponseCorrectionRetryCount` now defaults to `3` and validates in the `0..10` range
+- `git.pushTimeoutMs` now defaults to `180000`
+- diff and input budgets are split across `commitMessage.maxDiffChars`, `review.maxDiffChars`, `stagedChangeSummary.maxDiffChars`, `pullRequest.maxDiffChars`, and `reporting.maxInputChars`
+- report AI input is compressed to `reporting.maxInputChars` while preserving core totals, repository names, and compression notes
+- docs, example config, and schema docs now describe the staged-change-summary and PR/MR creation contracts
+
+### Security
+
+- PR/MR auth tokens are used only for GitHub/GitLab API authentication headers and are not included in LLM prompts, generated content, config rendering, or visible error output
+- config rendering now redacts `pullRequest.authToken` in addition to `connection.apiKey`
+
+## [0.1.7] - 2026-04-26
+
+### Added
+
+- optional AI pull request summary generation after successful `bridge` runs, writing timestamped Markdown under a configurable directory or the default `.smart-commit-cli/pr-summaries`
+- `pullRequestSummary.*` settings (`enabled`, `language`, `outputDirPath`, `prompt`) across CLI flags, environment variables, config files, JSON schema output, and legacy `smartCommit.*` mappings
+- structured `pullRequestSummary` in bridge output (`generated`, `outputFilePath`, `provider`, `error`) plus user-facing text render lines and non-fatal warnings when generation fails after an otherwise successful run
+- regression coverage for pull request summary plumbing and configuration resolution
+- a dedicated `0.1.7` draft release note for the current publish target
+
+### Changed
+
+- public config and bridge JSON contracts now include `pullRequestSummary` fields; `schema print --target bridge` reflects the updated shape
+- built-in `conventional` and `semantic` commit-message skill docs now note extracting a Jira or work item id from the branch name when prepending to the subject
+- publish guidance now points to the `0.1.7` release draft during pre-publish review
+
 ## [0.1.6] - 2026-04-18
 
 ### Added

package/README.md

@@ -20,7 +20,7 @@ It can:
 - optionally create a commit
 - optionally push the current branch
 - persist successful run history
-- generate daily, yesterday, weekly, monthly, quarterly, or yearly Markdown work reports
+- generate daily, yesterday, weekly, last-week, monthly, last-month, quarterly, last-quarter, or yearly Markdown work reports
 
 ## Who This Is For
 
@@ -279,11 +279,11 @@ Use this when you want a more realistic team default without enabling automatic
       "baseUrl": "https://api.openai.com/v1",
       "apiKey": "env:SMART_COMMIT_API_KEY",
       "model": "gpt-5",
-      "llmResponseCorrectionRetryCount": 1
+      "llmResponseCorrectionRetryCount": 3
     },
     "review": {
       "threshold": 6,
-      "language": "zh"
+      "language": "zh-cn"
     },
     "git": {
       "autoStageWhenNothingStaged": true,
@@ -316,7 +316,7 @@ Built-in review skills are bundled with the CLI. The default `code-review` skill
 
 If you set `review.skill.path`, the CLI keeps the current file-based custom-skill behavior and loads that file as custom prompt input instead of the bundled built-in skill assets.
 
-`connection.llmResponseCorrectionRetryCount` controls how many extra repair or regeneration attempts the CLI may request when a review result or generated commit message fails protocol, JSON-shape, or language validation. The default is `1`, the supported range is `0..5`, and network, HTTP, timeout, or provider failures are not retried by this setting.
+`connection.llmResponseCorrectionRetryCount` controls how many extra repair or regeneration attempts the CLI may request when a review result or generated commit message fails protocol, JSON-shape, or language validation. The default is `3`, the supported range is `0..10`, and network, HTTP, timeout, or provider failures are not retried by this setting.
 
 ### About the example config in this repo
 
@@ -401,8 +401,11 @@ Supported `--period` values:
 - `daily`
 - `yesterday`
 - `weekly`
+- `last-week`
 - `monthly`
+- `last-month`
 - `quarterly`
+- `last-quarter`
 - `yearly`
 
 If you omit `--period`, it defaults to `weekly`. `yesterday` always means the previous natural local day.
@@ -417,6 +420,23 @@ smart-commit report generate --repo . --config ./smart-commit.json --period week
 
 If AI report generation fails, the CLI falls back to local Markdown generation automatically.
 
+### I want a staged change summary after a passing review
+
+```bash
+smart-commit bridge --repo . --config ./smart-commit.json --no-commit --enable-staged-change-summary
+```
+
+When enabled, `bridge` writes a Markdown staged change summary after the reviewed action succeeds. It runs after review-only success, after local commit success when `--no-push` is used, or after push success when auto-push is enabled. Review blocks, dry runs, and commit/push failures do not generate a staged change summary.
+
+### I want to create a PR or MR from the CLI
+
+```bash
+SMART_COMMIT_PULL_REQUEST_AUTH_TOKEN=... \
+smart-commit pull-request create --repo . --config ./smart-commit.json --target-branch main --provider auto
+```
+
+Use `--dry-run` to compare branches and generate PR/MR content without creating it. The auth token is only used for GitHub/GitLab API headers and is redacted from config output and error text.
+
 ### I want machine-readable schemas
 
 ```bash
@@ -429,6 +449,7 @@ Supported schema targets:
 - `config-resolve`
 - `bridge`
 - `report-generate`
+- `pull-request-create`
 
 Examples:
 
@@ -437,6 +458,7 @@ smart-commit schema print --target config-file
 smart-commit schema print --target config-resolve
 smart-commit schema print --target bridge
 smart-commit schema print --target report-generate
+smart-commit schema print --target pull-request-create
 ```
 
 ## Core Commands Reference
@@ -570,8 +592,19 @@ Most practical flags for daily use:
 --review-language
 --code-review-skill-id
 --commit-language
+--commit-message-structure
 --commit-message
 --pass-history-write-stage
+--enable-staged-change-summary
+--staged-change-summary-language
+--staged-change-summary-output-dir
+--staged-change-summary-prompt
+--target-branch
+--provider
+--auth-token
+--assignee
+--reviewer
+--label
 --no-commit
 --no-push
 --dry-run
@@ -599,11 +632,20 @@ SMART_COMMIT_LLM_RESPONSE_CORRECTION_RETRY_COUNT
 SMART_COMMIT_REVIEW_LANGUAGE
 SMART_COMMIT_CODE_REVIEW_SKILL_ID
 SMART_COMMIT_COMMIT_LANGUAGE
+SMART_COMMIT_COMMIT_MESSAGE_STRUCTURE
 SMART_COMMIT_AUTO_COMMIT
 SMART_COMMIT_AUTO_PUSH
 SMART_COMMIT_PASS_HISTORY_WRITE_STAGE
 SMART_COMMIT_REPORT_LANGUAGE
 SMART_COMMIT_REPORT_OUTPUT_DIR
+SMART_COMMIT_ENABLE_STAGED_CHANGE_SUMMARY
+SMART_COMMIT_STAGED_CHANGE_SUMMARY_LANGUAGE
+SMART_COMMIT_STAGED_CHANGE_SUMMARY_OUTPUT_DIR
+SMART_COMMIT_STAGED_CHANGE_SUMMARY_PROMPT
+SMART_COMMIT_AUTO_CREATE_PULL_REQUEST_AFTER_PUSH
+SMART_COMMIT_PULL_REQUEST_TARGET_BRANCH
+SMART_COMMIT_PULL_REQUEST_PROVIDER
+SMART_COMMIT_PULL_REQUEST_AUTH_TOKEN
 ```
 
 ## Reporting

package/docs/configuration.md

@@ -143,11 +143,11 @@ Recommended early team setup:
       "baseUrl": "https://api.openai.com/v1",
       "apiKey": "env:SMART_COMMIT_API_KEY",
       "model": "gpt-5",
-      "llmResponseCorrectionRetryCount": 1
+      "llmResponseCorrectionRetryCount": 3
     },
     "review": {
       "threshold": 6,
-      "language": "zh"
+      "language": "zh-cn"
     },
     "git": {
       "autoStageWhenNothingStaged": true,
@@ -188,7 +188,7 @@ These settings tell the CLI how to reach your AI endpoint. `bridge` requires all
 | `connection.apiKey` | empty string | `env:SMART_COMMIT_API_KEY` | Change it only if you intentionally inject secrets another way | Putting raw secrets into committed config files |
 | `connection.model` | empty string | A model name that your chosen `baseUrl` actually serves | Change it when you switch cost, quality, or provider capabilities | Using a model name unsupported by your gateway |
 | `connection.requestTimeoutMs` | `1000000` | Leave default first | Change it only if your provider is too slow or your requests time out unexpectedly | Setting it below `5000`, which fails validation |
-| `connection.llmResponseCorrectionRetryCount` | `1` | `1` | Change it when you want `0..5` repair or regeneration retries for protocol, format, or language validation failures | Expecting it to retry provider, network, HTTP, or timeout failures |
+| `connection.llmResponseCorrectionRetryCount` | `3` | `3` | Change it when you want `0..10` repair or regeneration retries for protocol, format, or language validation failures | Expecting it to retry provider, network, HTTP, or timeout failures |
 | `connection.extraHeaders` | `{}` | Leave empty first | Add values only if your proxy or API gateway requires custom headers | Adding provider-specific headers that your endpoint does not expect |
 
 Practical guidance:
@@ -204,7 +204,7 @@ These settings control review quality, language, and pass-or-block behavior.
 | Field | Built-in default | Recommended first value | When to change it | Common mistake |
 | --- | --- | --- | --- | --- |
 | `review.threshold` | `6` | `6` | Lower it if you get too many false blocks; raise it if you want stricter gating | Misreading the rule: `score <= threshold` blocks, `score > threshold` passes |
-| `review.language` | `zh` | `zh` or `en`, depending on your team | Change it when your team wants review output in a different language | Assuming it changes Git behavior instead of review text |
+| `review.language` | `zh-cn` | `zh-cn` or `en`, depending on your team | Change it when your team wants review output in a different language | Assuming it changes Git behavior instead of review text |
 | `review.maxDiffChars` | `100000` | Leave default first | Lower it if very large diffs are too slow or costly | Setting it below `1000`, which fails validation |
 | `review.skill.id` | `code-review` | `code-review` | Change it when your repo needs domain-specific built-in review guidance | Using an unsupported id |
 | `review.skill.path` | empty string | Leave empty first | Set it when your team has a custom review rules file | Setting both a custom path and then wondering why the built-in id does not matter |
@@ -239,7 +239,8 @@ These settings control where the commit message comes from and how it is validat
 | Field | Built-in default | Recommended first value | When to change it | Common mistake |
 | --- | --- | --- | --- | --- |
 | `commitMessage.input` | empty string | Leave empty first | Set it when you already know the exact message you want | Setting it and expecting auto-generation to replace it |
-| `commitMessage.language` | `zh` | `zh` or `en` | Change it to match your team's commit language | Mixing a team English convention with a non-English expectation |
+| `commitMessage.language` | `zh-cn` | `zh-cn` or `en` | Change it to match your team's commit language | Mixing a team English convention with a non-English expectation |
+| `commitMessage.structure` | `subjectOnly` | `subjectOnly` | Change it when your team wants optional commit bodies or footers | Expecting body/footer to be allowed while the default single-line mode is still active |
 | `commitMessage.autoGenerate` | `true` | `true` | Set `false` only if users always provide a message themselves | Turning it off with no provided message, which causes a commit-message-required error |
 | `commitMessage.hybridGenerate` | `false` | `false` | Set `true` when users provide a draft and want AI to refine it | Enabling it without understanding that it uses `commitMessage.input` as a draft |
 | `commitMessage.validation.protocol` | `none` | `none` first, then `conventional` if your team standardizes on it | Change it when your team enforces a commit style | Enabling validation before the team is ready |
@@ -257,6 +258,14 @@ How `hybridGenerate` actually works:
 - if `commitMessage.input` is empty and `autoGenerate=true`, the CLI generates from the diff
 - if `commitMessage.input` is empty and `autoGenerate=false`, the CLI errors because no message source exists
 
+Supported commit message structures:
+
+- `subjectOnly`: exactly one non-empty subject line
+- `subjectBody`: a subject plus optional body separated by one blank line
+- `subjectBodyFooter`: a subject plus optional body and optional footer/trailer lines
+
+Protocol, language, ticket, and regex validation apply to the subject. Ticket injection from the branch preserves any accepted body or footer.
+
 Supported validation protocols:
 
 - `none`
@@ -311,7 +320,7 @@ These settings control report generation behavior.
 
 | Field | Built-in default | Recommended first value | When to change it | Common mistake |
 | --- | --- | --- | --- | --- |
-| `reporting.language` | `zh` | `zh` or `en` | Change it when your team wants report output in another language | Assuming this changes review or commit-message language too |
+| `reporting.language` | `zh-cn` | `zh-cn` or `en` | Change it when your team wants report output in another language | Assuming this changes review or commit-message language too |
 | `reporting.weekStartsOn` | `monday` | `monday` | Change it to `sunday` only if your reporting convention starts weeks on Sunday | Picking a week start different from your team's reporting habit |
 | `reporting.outputDirPath` | empty string | Leave empty first | Change it only when you want reports in a different directory | Thinking empty means invalid, when it actually falls back to the repo-local default directory |
 | `reporting.prompt` | empty string | Leave empty first | Add it when you want reports to emphasize business outcomes or another angle | Writing a very large prompt when a short focus instruction would do |
@@ -319,6 +328,43 @@ These settings control report generation behavior.
 
 If `reporting.outputDirPath` is empty, the CLI writes reports to `.smart-commit-cli/reports` under the repository root.
 
+### `stagedChangeSummary.*`
+
+These settings control optional Markdown staged change summary generation after a passing `bridge` run.
+
+| Field | Built-in default | Recommended first value | When to change it | Common mistake |
+| --- | --- | --- | --- | --- |
+| `stagedChangeSummary.enabled` | `false` | `false` first | Set `true` when you want a staged change summary after review success | Expecting it to run for dry-run, blocked review, or failed commit/push paths |
+| `stagedChangeSummary.language` | `zh-cn` | Match your reviewer language | Change it independently from review and commit-message language | Assuming it changes review output language |
+| `stagedChangeSummary.outputDirPath` | empty string | Leave empty first | Set it when your automation needs a specific artifact location | Thinking empty means invalid; it writes under `.smart-commit-cli/staged-change-summaries` |
+| `stagedChangeSummary.prompt` | empty string | Leave empty first | Add concise team PR template guidance | Asking it to invent tests, reviewers, links, or review findings |
+
+The generated summary uses only the reviewed staged diff, commit message, branch, changed files, and run facts. Review scores, thresholds, findings, and suggestions are treated as internal gate data and are not included in the staged change summary.
+
+### `pullRequest.*`
+
+These settings control GitHub pull request and GitLab merge request creation from the current branch.
+
+| Field | Built-in default | Recommended first value | When to change it | Common mistake |
+| --- | --- | --- | --- | --- |
+| `pullRequest.autoCreateAfterPush` | `false` | `false` first | Set `true` when `bridge` should create a PR/MR after a successful push | Expecting it to run when push is disabled or fails |
+| `pullRequest.targetBranch` | empty string | Your default integration branch | Set it in shared config when most branches target the same branch | Forgetting that `pull-request create` requires this value or `--target-branch` |
+| `pullRequest.provider` | `auto` | `auto` | Use `github` or `gitlab` when remote detection is ambiguous | Setting a provider that does not match the remote host |
+| `pullRequest.apiBaseUrl` | empty string | Leave empty for public GitHub/GitLab | Set it for GitHub Enterprise or self-managed GitLab | Including a trailing slash or a repository path instead of the API base |
+| `pullRequest.titlePrompt` | empty string | Leave empty first | Add short team guidance for generated PR/MR titles | Putting auth tokens, reviewer names, or process notes into the title prompt |
+| `pullRequest.descriptionPrompt` | empty string | Leave empty first | Add concise PR/MR template guidance | Asking it to invent tests, links, or approvals |
+| `pullRequest.maxDiffChars` | `200000` | `200000` | Lower it for very large repositories or slow models | Setting it below `1000`, which fails validation |
+| `pullRequest.assignees` | `[]` | `[]` | Set default assignees for created PRs/MRs | Assuming these are LLM prompt hints; they are sent to the provider API |
+| `pullRequest.reviewers` | `[]` | `[]` | Set default reviewers for created PRs/MRs | Assuming every provider accepts every reviewer identifier format |
+| `pullRequest.labels` | `[]` | `[]` | Apply standard labels during creation | Expecting missing provider labels to be created automatically |
+| `pullRequest.milestone` | empty string | Leave empty first | Set it when your provider project uses milestones | Using a display name where the provider expects an id |
+| `pullRequest.draft` | `false` | `false` | Set `true` when generated PRs/MRs should start as drafts | Expecting GitLab draft behavior to exactly match GitHub |
+| `pullRequest.removeSourceBranch` | `false` | `false` | Set `true` when accepted MRs should remove the source branch | Expecting GitHub to support this GitLab-only field |
+| `pullRequest.skipBranches` | `["main", "master", "develop"]` | Keep the defaults | Add protected branch names that should never auto-create PRs/MRs | Forgetting this only applies to source branch names |
+| `pullRequest.authToken` | empty string | `env:SMART_COMMIT_PULL_REQUEST_AUTH_TOKEN` | Set it when creating PRs/MRs through provider APIs | Hardcoding a token in committed config |
+
+PR/MR auth tokens are used only for provider API authentication headers. They are redacted from resolved config, generated content, LLM prompts, and visible error output.
+
 ### `output.*`
 
 These settings control how results are presented.
@@ -336,7 +382,8 @@ These are the validated option sets enforced by the CLI.
 
 Supported output and commit-message languages:
 
-- `zh`
+- `zh-cn`
+- `zh-tw`
 - `en`
 - `de`
 - `fr`
@@ -390,8 +437,29 @@ Most practical flags:
 --review-language
 --code-review-skill-id
 --commit-language
+--commit-message-structure
 --commit-message
 --pass-history-write-stage
+--enable-staged-change-summary
+--staged-change-summary-language
+--staged-change-summary-max-diff-chars
+--staged-change-summary-output-dir
+--staged-change-summary-prompt
+--auto-create-pull-request-after-push
+--target-branch
+--provider
+--api-base-url
+--auth-token
+--pull-request-title-prompt
+--pull-request-description-prompt
+--pull-request-max-diff-chars
+--assignee
+--reviewer
+--label
+--milestone
+--draft
+--remove-source-branch
+--skip-branch
 --no-commit
 --no-push
 --dry-run
@@ -419,11 +487,32 @@ SMART_COMMIT_LLM_RESPONSE_CORRECTION_RETRY_COUNT
 SMART_COMMIT_REVIEW_LANGUAGE
 SMART_COMMIT_CODE_REVIEW_SKILL_ID
 SMART_COMMIT_COMMIT_LANGUAGE
+SMART_COMMIT_COMMIT_MESSAGE_STRUCTURE
 SMART_COMMIT_AUTO_COMMIT
 SMART_COMMIT_AUTO_PUSH
 SMART_COMMIT_PASS_HISTORY_WRITE_STAGE
 SMART_COMMIT_REPORT_LANGUAGE
 SMART_COMMIT_REPORT_OUTPUT_DIR
+SMART_COMMIT_ENABLE_STAGED_CHANGE_SUMMARY
+SMART_COMMIT_STAGED_CHANGE_SUMMARY_LANGUAGE
+SMART_COMMIT_STAGED_CHANGE_SUMMARY_MAX_DIFF_CHARS
+SMART_COMMIT_STAGED_CHANGE_SUMMARY_OUTPUT_DIR
+SMART_COMMIT_STAGED_CHANGE_SUMMARY_PROMPT
+SMART_COMMIT_AUTO_CREATE_PULL_REQUEST_AFTER_PUSH
+SMART_COMMIT_PULL_REQUEST_TARGET_BRANCH
+SMART_COMMIT_PULL_REQUEST_PROVIDER
+SMART_COMMIT_PULL_REQUEST_API_BASE_URL
+SMART_COMMIT_PULL_REQUEST_TITLE_PROMPT
+SMART_COMMIT_PULL_REQUEST_DESCRIPTION_PROMPT
+SMART_COMMIT_PULL_REQUEST_MAX_DIFF_CHARS
+SMART_COMMIT_PULL_REQUEST_ASSIGNEES
+SMART_COMMIT_PULL_REQUEST_REVIEWERS
+SMART_COMMIT_PULL_REQUEST_LABELS
+SMART_COMMIT_PULL_REQUEST_MILESTONE
+SMART_COMMIT_PULL_REQUEST_DRAFT
+SMART_COMMIT_PULL_REQUEST_REMOVE_SOURCE_BRANCH
+SMART_COMMIT_PULL_REQUEST_SKIP_BRANCHES
+SMART_COMMIT_PULL_REQUEST_AUTH_TOKEN
 ```
 
 Useful boolean environment variables accept:
@@ -478,8 +567,11 @@ Supported periods:
 - `daily`
 - `yesterday`
 - `weekly`
+- `last-week`
 - `monthly`
+- `last-month`
 - `quarterly`
+- `last-quarter`
 - `yearly`
 
 If `--period` is omitted, it defaults to `weekly`. `yesterday` always uses the previous natural local day.

package/docs/contracts.md

@@ -9,6 +9,7 @@ For formal JSON Schema output, use:
 ```bash
 smart-commit schema print --target bridge
 smart-commit schema print --target report-generate
+smart-commit schema print --target pull-request-create
 ```
 
 ## Shared Rules
@@ -36,7 +37,7 @@ Stable top-level fields:
 
 Use it to validate merged config before wiring `bridge` or `report generate` into automation.
 
-Contract consumers can safely read newly added resolved settings such as `config.connection.llmResponseCorrectionRetryCount`, `config.passHistory.writeStage`, and `config.review.skill.id` from the returned `config` object.
+Contract consumers can safely read newly added resolved settings such as `config.connection.llmResponseCorrectionRetryCount`, `config.passHistory.writeStage`, `config.review.skill.id`, `config.commitMessage.structure`, and `config.stagedChangeSummary.enabled` from the returned `config` object.
 
 ## `bridge`
 
@@ -57,6 +58,8 @@ Stable top-level fields:
 - `didPush`
 - `commitSha`
 - `passHistory`
+- `stagedChangeSummary`
+- `pullRequestCreation`
 - `reviewDecision`
 - `score`
 - `summary`
@@ -65,6 +68,10 @@ Stable top-level fields:
 Stable nested fields often used by automations:
 
 - `passHistory.eventType`
+- `stagedChangeSummary.generated`
+- `stagedChangeSummary.outputFilePath`
+- `pullRequestCreation.status`
+- `pullRequestCreation.url`
 - `reviewDetails`
 
 `passHistory.writeStage` controls when a pass-history record is first allowed to exist. Once a record exists, later successful stages update that same record, so `passHistory.eventType` always reflects the furthest successful stage reached by the run.
@@ -82,6 +89,21 @@ Stable nested fields often used by automations:
 
 For example, when `passHistory.writeStage = "commit_completed"`, a successful local commit can still leave `passHistory.eventType = "commit_completed"` if the later push cannot start, fails, or times out. When `passHistory.writeStage = "commit_push_completed"`, those same push failures keep `passHistory.eventType = null` because no record is written.
 
+`stagedChangeSummary` is always present in bridge output. When `stagedChangeSummary.enabled = true`, the CLI attempts generation only after the review/commit/push action for that run succeeds. Generation failures are reported in `stagedChangeSummary.error` and do not change the already successful bridge exit code.
+
+`pullRequestCreation` is always present in bridge output. When `pullRequest.autoCreateAfterPush = true`, the CLI attempts creation only after push succeeds and the source branch is not in `pullRequest.skipBranches`. Creation failures are reported in `pullRequestCreation.error` and do not change the already successful bridge exit code.
+
+`pullRequestCreation.status` semantics:
+
+- `skipped`
+  PR/MR creation was disabled, dry-run skipped it, push did not succeed, or the source branch is skipped.
+- `created`
+  A new PR/MR was created.
+- `existing`
+  An open PR/MR already exists for the source and target branch.
+- `error`
+  PR/MR creation failed after the bridge commit/push flow had already succeeded.
+
 Status semantics:
 
 - `ready`
@@ -118,7 +140,7 @@ Command:
 smart-commit report generate --repo /path/to/repo --period weekly
 ```
 
-Supported `periodType` values are `daily`, `yesterday`, `weekly`, `monthly`, `quarterly`, and `yearly`.
+Supported `periodType` values are `daily`, `yesterday`, `weekly`, `last-week`, `monthly`, `last-month`, `quarterly`, `last-quarter`, and `yearly`.
 
 Stable top-level fields:
 
@@ -161,6 +183,50 @@ Recommended automation behavior:
 - use `facts.totals.commitCompleted` and `facts.totals.commitPushCompleted` separately if local commit completion and remote push completion need different downstream handling
 - fail on `status: "error"`
 
+## `pull-request create`
+
+Command:
+
+```bash
+SMART_COMMIT_PULL_REQUEST_AUTH_TOKEN=... \
+smart-commit pull-request create --repo /path/to/repo --config ./smart-commit.json --target-branch main
+```
+
+Stable top-level fields:
+
+- `schemaVersion`
+- `status`
+- `command`
+- `repositoryPath`
+- `platform`
+- `sourceBranch`
+- `targetBranch`
+- `title`
+- `url`
+- `warnings`
+- `dryRun`
+- `config`
+- `summary`
+- `error`
+
+`status` semantics:
+
+- `created`
+  A new GitHub pull request or GitLab merge request was created.
+- `existing`
+  An open PR/MR already exists for the same source and target branch.
+- `ready`
+  Dry-run mode generated and validated PR/MR content without creating it.
+- `error`
+  Configuration or runtime validation failed.
+
+Recommended automation behavior:
+
+- archive or surface `url` on `created` or `existing`
+- use `--dry-run` before first enabling provider writes
+- treat `warnings` as non-fatal context
+- fail on `status: "error"`
+
 ## Versioning Guidance
 
 - treat `schemaVersion` as the primary compatibility gate

package/docs/getting-started.md

@@ -129,7 +129,7 @@ This config is intentionally conservative:
 - `autoCommit=false` prevents creating a local commit
 - `autoPush=false` prevents pushing to remote
 
-The built-in default for `connection.llmResponseCorrectionRetryCount` is already `1`, which means the CLI will allow one extra repair or regeneration pass when a review result or generated commit message fails local protocol validation. Set it to `0` later if you want to disable that behavior.
+The built-in default for `connection.llmResponseCorrectionRetryCount` is already `3`, which means the CLI will allow one extra repair or regeneration pass when a review result or generated commit message fails local protocol validation. Set it to `0` later if you want to disable that behavior.
 
 If you want a fuller example, see `examples/config/smart-commit.json`, but do not copy its side-effect settings blindly for first use.
 
@@ -260,8 +260,11 @@ Supported periods:
 - `daily`
 - `yesterday`
 - `weekly`
+- `last-week`
 - `monthly`
+- `last-month`
 - `quarterly`
+- `last-quarter`
 - `yearly`
 
 If `--period` is omitted, the CLI defaults to `weekly`. `yesterday` always uses the previous natural local day in local time.

package/docs/publish.md

@@ -21,7 +21,7 @@ Current package name:
 3. Run `npm run pack:dry-run`
 4. Review [`CHANGELOG.md`](../CHANGELOG.md)
 5. Review [`docs/release-checklist.md`](./release-checklist.md)
-6. Review the matching release draft in [`docs/releases/0.1.6-draft.md`](./releases/0.1.6-draft.md)
+6. Review the matching release draft in [`docs/releases/0.1.8-draft.md`](./releases/0.1.8-draft.md)
 
 ## Recommended Release Order
 

package/docs/releases/0.1.7-draft.md

@@ -0,0 +1,55 @@
+# `smart-commit-copilot-cli` 0.1.7 Draft Release Notes
+
+## Summary
+
+`smart-commit-copilot-cli` 0.1.7 adds optional pull request description generation to the `bridge` workflow, alongside full configuration and contract support for automation consumers.
+
+This release focuses on turning a successful review-and-commit run into a ready-to-paste staged change summary artifact without changing the bridge exit code when summary generation fails.
+
+## Highlights
+
+- opt-in `stagedChangeSummary.enabled` with independent `language`, optional `outputDirPath`, and optional free-form `prompt` template guidance
+- generation runs only after the applicable successful `bridge` outcome (review-only, commit, or push, depending on your flow); failures surface in `stagedChangeSummary.error` and optional stderr warnings
+- Markdown files use a stable `smart-commit-pr-summary-*.md` naming pattern under the chosen or default output directory
+- legacy `smartCommit.stagedChangeSummary*` keys map into the same resolved `stagedChangeSummary` object as other Smart Commit settings
+
+## Why This Release Matters
+
+This version closes the loop for teams that open pull requests immediately after local automation:
+
+- hooks and agents can enable one setting and receive a file path in structured JSON output
+- consumers can treat summary failure as telemetry without losing a green bridge result
+- configuration remains consistent with the rest of the CLI resolution order (args, env, file, defaults)
+
+## Notable Behavior Updates
+
+### Staged change summary
+
+- when disabled, bridge output still includes `stagedChangeSummary` with `generated: false` and null file or provider fields as appropriate
+- when enabled, the CLI uses the same AI connection as review and commit-message generation; empty or invalid model output is reported without failing the bridge
+- text output includes whether a file was written and any error string for operator visibility
+
+### Commit message skills
+
+- bundled `conventional` and `semantic` skill documentation now explicitly calls out extracting Jira or work item identifiers from the branch when present
+
+## Verification Coverage Added Or Strengthened
+
+The project now has stronger regression protection for:
+
+1. `stagedChangeSummary` defaults and legacy key mapping in config resolution
+2. bridge JSON shape and schema output for the new fields
+3. mock-provider success and empty-output failure paths for staged change summary generation
+
+## Suggested Upgrade Path
+
+1. update to `0.1.7`
+2. run `npm test`
+3. run `npm run smoke:test`
+4. run `npm run pack:dry-run`
+5. publish only after all three checks pass
+
+## Known Follow-Up Areas
+
+- richer provider options or templates if teams need multiple PR formats per repository
+- deeper integration tests against real OpenAI-compatible endpoints if mock coverage is not enough for your release bar

package/docs/releases/0.1.8-draft.md

@@ -0,0 +1,80 @@
+# `smart-commit-copilot-cli` 0.1.8 Draft Release Notes
+
+## Summary
+
+`smart-commit-copilot-cli` 0.1.8 brings the CLI up to the latest Smart Commit workflow semantics for staged change summaries, PR/MR creation, stricter language handling, and reporting windows.
+
+This release is focused on CLI-native PR/MR automation: create a GitHub pull request or GitLab merge request directly with `smart-commit pull-request create`, or let `bridge` attempt PR/MR creation automatically after a successful push.
+
+## Highlights
+
+- new `smart-commit pull-request create` command with GitHub and GitLab support
+- bridge output now includes `pullRequestCreation` and can auto-create after push when `pullRequest.autoCreateAfterPush=true`
+- staged summary config/output is now `stagedChangeSummary`; old canonical `pullRequestSummary` config is rejected
+- output language defaults now use `zh-cn`, with strict support for `zh-cn` and `zh-tw`; legacy `zh` is rejected
+- response correction retry default is now `3`, with a validated `0..10` range
+- reporting now supports `last-week`, `last-month`, and `last-quarter`
+- AI report facts are compressed to `reporting.maxInputChars` with a clear compression note
+
+## Security Notes
+
+PR/MR auth tokens are only used for GitHub/GitLab API authentication headers.
+
+They are not included in:
+
+- LLM prompts or messages
+- generated PR/MR content
+- report or summary facts
+- rendered config output
+- visible error messages
+
+Use `SMART_COMMIT_PULL_REQUEST_AUTH_TOKEN` or `pullRequest.authToken: "env:VAR_NAME"` for normal use.
+
+## Notable Behavior Updates
+
+### PR/MR creation
+
+- `smart-commit pull-request create` supports `--repo`, `--target-branch`, `--provider`, `--api-base-url`, `--auth-token`, `--draft`, `--assignee`, `--reviewer`, `--label`, `--milestone`, `--remove-source-branch`, `--skip-branch`, `--dry-run`, and `--output`
+- existing open PRs/MRs are detected and returned as `existing` instead of creating duplicates
+- dry runs compare branches and generate content without sending the create request
+- bridge auto-create runs only after push success; failures are reported without changing the successful commit/push exit code
+
+### Configuration and contracts
+
+- new `pullRequest.*` config covers auto-create, target branch, provider, API base URL, token, prompts, metadata, and skip branches
+- bridge output fields are now `stagedChangeSummary` and `pullRequestCreation`
+- `schema print --target pull-request-create` exposes the new command output contract
+- old canonical `pullRequestSummary` is not parsed or emitted
+
+### Reporting and language
+
+- `report generate --period` now accepts `last-week`, `last-month`, and `last-quarter`
+- Chinese language selection is explicit: use `zh-cn` for Simplified Chinese or `zh-tw` for Traditional Chinese
+- Traditional Chinese prompts explicitly prevent Simplified Chinese output
+
+## Verification Coverage Added Or Strengthened
+
+The project now has stronger regression protection for:
+
+1. strict rejection of legacy `zh` across flags, env, config files, and legacy keys
+2. rejection of canonical `pullRequestSummary` and acceptance of `stagedChangeSummary`
+3. PR/MR platform detection and generated content protocol handling
+4. PR/MR prompt serialization without auth token or auth header material
+5. report period expansion and report-facts compression
+6. bridge staged summary and PR/MR creation contract fields
+
+## Suggested Upgrade Path
+
+1. update to `0.1.8`
+2. replace any `zh` config value with `zh-cn` or `zh-tw`
+3. replace canonical `pullRequestSummary` config with `stagedChangeSummary`
+4. configure `pullRequest.targetBranch` or pass `--target-branch` when creating PRs/MRs
+5. use `SMART_COMMIT_PULL_REQUEST_AUTH_TOKEN` or `authToken: "env:VAR_NAME"` for PR/MR API auth
+6. run `npm test`
+7. run `npm run smoke:test`
+8. run `npm run pack:dry-run`
+
+## Known Follow-Up Areas
+
+- broader integration coverage against real GitHub/GitLab test repositories
+- richer PR/MR template controls if teams need provider-specific conventions beyond prompt tuning

package/docs/roadmap.md

@@ -27,7 +27,7 @@ Focus:
 
 Expected stability:
 
-- `schemaVersion: "1.0.0"` machine contracts should remain stable unless there is a strong reason to break them
+- `schemaVersion: "1.1.0"` machine contracts should remain stable unless there is a strong reason to break them
 - `smartCommitCli` remains the canonical config namespace
 - legacy `smartCommit.*` remains compatibility-only