xevol 0.12.7 → 0.12.9

package/README.md

@@ -2,7 +2,7 @@
 
 Terminal client for Xevol content execution.
 
-Use it to operate Xevol Work CRM records, Deals, Activities, tasks, and search; ingest content; run analysis; manage prompts; inspect usage; and work across Workspaces.
+Use it to operate Xevol Work Offers, Leads, Contacts, Companies, Deals, Activities, tasks, and search; ingest content; run analysis; manage prompts; inspect usage; and work across Workspaces.
 
 ## Install
 
@@ -53,7 +53,10 @@ xevol workspace switch <workspace-id>
 ### Xevol Work CRM
 - `xevol companies ...` — all Companies reads and commands: list, get, options, create, update, remove, enrich, research, and primary Contact
 - `xevol contacts ...` — all Contacts reads and commands: list, get, create, update, and proposed-fact decisions
-- `xevol leads ...` — every Leads procedure used by Xevol Work Web, including campaigns, review, identity, packets, Deal handoff, outreach, learning, import, insights, and export
+- `xevol offers ...` — every Offers procedure used by Xevol Work Web, including profiles, status, snapshots, audiences, angles, artifacts, revisions, and reviewed generation
+- `xevol leads ...` — every Leads procedure used by Xevol Work Web, including campaigns, manual imported review, identity, packets, Deal handoff, outreach, learning, import, insights, and export
+- `xevol directory ...` — read-only Company/Contact source browsing, identity quality, memberships, and immutable import reports
+- `xevol career ...` — read-only source job browsing and detail, separate from personal Matches and Pursuits
 - `xevol deals ...` — list, get, create, update, and stage management
 - `xevol activities ...` — record timelines, counts, personal tasks, activity creation, and task completion
 - `xevol search [query]` — search Companies, Contacts, and Deals across the selected Workspace
@@ -72,6 +75,7 @@ xevol search Acme --json
 Complex or less common inputs still accept exactly one of `--input`, `--file`, or stdin:
 
 ```bash
+xevol offers create --input '{"offerProfileId":"...","kind":"SERVICE","name":"Fixed package"}' --json
 xevol leads packet-decide --input '{"packetId":"...","action":"QUALIFY"}' --json
 xevol leads packet-decide --file decision.json --json
 cat decision.json | xevol leads packet-decide --json
@@ -79,8 +83,91 @@ cat decision.json | xevol leads packet-decide --json
 
 List commands also accept `--query`, `--page`, `--page-size`, `--sort`, and `--dir`. Deal lists add status, owner, stage, and closing-window facets. Activity commands provide direct timeline anchors, filters, task windows, and limits. `--workspace-id` overrides the selected Workspace for one command while still relying on server-side membership authorization.
 
+Campaign execution commands keep the Work API's reviewed-policy and acknowledgement requirements. In particular, `campaign-execution-activate` can start sending and requires both `expectedEnrollmentCount` and `"acknowledgeSend": true`; the CLI supplies no bypass and the API rechecks current Workspace authority.
+
+### Imported source data
+
+Directory and Career source commands use the same Work API token, selected Workspace,
+active membership, and direct-owner privacy checks as the web. They do not execute bulk
+imports, enrich records, enroll campaigns, send messages, or apply for jobs.
+
+```bash
+xevol directory companies --source explee --query Acme --page-size 25 --json
+xevol directory contacts --source explee --missing email --quality weak --json
+xevol directory company-get <company-id> --json
+xevol directory contact-get <contact-id> --json
+xevol directory sources <record-id> --kind CONTACT --page-size 25 --json
+xevol directory source-options --kind CONTACT --json
+xevol directory imports --state COMPLETED --json
+xevol directory import-get <batch-id> --json
+xevol directory import-rows <batch-id> --kind CONTACT --outcome UNRESOLVED --json
+xevol directory import-row-get <row-id> --batch-id <batch-id> --json
+xevol career source-list --source leadjobs --query engineer --age historical-365 --json
+xevol career source-get <opportunity-id> --json
+```
+
+Directory lists support `--source`, `--snapshot`, `--segment`, `--quality`, `--usage`,
+and `--missing`. Import reports filter by source/state; source rows filter by kind/outcome.
+Career source lists support `--source`, `--availability`, `--age`, and `--work-mode`.
+Searchable lists accept `--query`, `--sort`, and `--dir`; paged reads accept `--page`
+and `--page-size` (1–100). `source-options` returns the accessible filter values.
+Observed job availability is historical evidence, not proof that a job is open now.
+
+### Imported manual Leads review
+
+```bash
+xevol leads list --input '{"view":"all"}' --json
+xevol leads manual-campaign-resolve <source-campaign-id> --json
+xevol leads manual-campaign-detail <campaign-id> --json
+xevol leads manual-prospect-list <campaign-id> --disposition HELD --json
+xevol leads manual-lead-detail <lead-id> --campaign-id <campaign-id> --json
+xevol leads manual-draft-list <lead-id> --campaign-id <campaign-id> --json
+xevol leads manual-draft-detail <draft-id> --campaign-id <campaign-id> --lead-id <lead-id> --json
+xevol leads manual-source-catalog --json
+xevol leads manual-source-rows --source-table DRAFTS --page-size 25 --json
+xevol leads manual-source-record <row-id> --json
+```
+
+`leads list` defaults to submissions; use `view: all` when counting the full Lead corpus.
+Manual review mutations are **content-only**: approval never schedules or sends a message.
+They reuse the API's version, campaign, owner, archive, and replay checks without bypasses:
+
+```bash
+xevol leads manual-lead-review <lead-id> --file review.json --json
+xevol leads manual-draft-revise <draft-id> --file revision.json --json
+xevol leads manual-draft-decide <draft-id> --file content-decision.json --json
+```
+
+All three input files must supply `campaignId`, the exact observed `expectedVersion`, and
+an explicit `operationKey`. Review additionally needs `disposition` and `reason`.
+Revision needs `leadId`, `parentRevision`, `subject`, and `body`. Decision needs `leadId`,
+`revision`, and `decision` (`APPROVE` or `REJECT`); rejection requires `note`.
+IDs supplied positionally cannot conflict with JSON input. Context can also be provided
+with `--campaign-id`, `--lead-id` (draft commands), `--expected-version`, and `--operation-key`.
+No version or approval is inferred. Retain exact draft revisions and read server results
+before issuing another command. Bulk migration and provider actions remain separate operations.
+
+### Bounded system workflow
+
+A strict `xevol.system/v1` JSON manifest can manage one Offer profile, up to two reviewed Offers, up to two manual campaigns, and up to five reviewed Leads:
+
+```bash
+xevol system plan -f system.json --json
+xevol system approve -f system.json --plan-hash <hash> --confirm "APPROVE_SYSTEM_PLAN:<hash>" --operation-key <key> --json
+xevol system apply -f system.json --approval-id <id> --approval-token <token> --operation-key <key> --json
+xevol system verify -f system.json --json
+```
+
+Planning and verification are read-only. Approval is bound to the exact manifest and observed state. Apply is atomic and replay-safe. V1 permits no campaign run, outreach, provider write, publication, or external cost, and provides no `--yes` or `--force` bypass.
+
+Work and system commands return `xevol.cli/v1` envelopes in `--json` mode and keep normal handled errors off stderr.
+
 ### Ingestion & content
 - `xevol add [url]` — URL ingestion (YouTube + non-YouTube); omit URL when using `--batch`
+- `xevol add --file source.pdf --lang en` — upload PDF, UTF-8 text, audio, or video
+- `xevol retry <id> --regenerate --lang en` — regenerate saved content on the same transcription
+
+Add, upload, status, and retry use the selected Work Workspace's Creator gateway. Retained authority still routes to Creator; exclusive Native authority uses canonical Work ingestion. Use `--operation-id <id>` on a single add/upload/retry to repeat an uncertain response without starting another import. Audio/video requires the Agent's optional ASR configuration.
 - `xevol create [text]` — create from text/file/url/stdin/editor
 - `xevol list` — list transcriptions
 - `xevol view <id>` — view summary/content
@@ -101,6 +188,16 @@ List commands also accept `--query`, `--page`, `--page-size`, `--sort`, and `--d
 - `xevol coordinates locations` — Xevol Coordinates history
 - `xevol whereami` / `xevol locations` — legacy convenience aliases
 
+### Workspace Agent skills
+- `xevol skills list` — list accessible active reviewed skill revisions
+- `xevol skills search <query>` — search accessible skill names and descriptions
+- `xevol skills get <skill-id> --revision <revision-id>` — read one exact revision
+- `xevol skills export <skill-id> --revision <revision-id> --output <directory>` — create a local text-only Agent Skills package without overwriting files
+
+Use `--agent-id` and `--agent-revision` together only when reading a legitimately pinned archived revision. Skill instructions do not grant tools, data access, or permission to act. Exported Workspace material cannot be recalled and may be private.
+
+These commands require a Work API release that provides `agentSkills.discover` and `agentSkills.readRevision`. An older server returns `UNSUPPORTED_SERVER`; the CLI never falls back to the administrative skill-history surface.
+
 ### Interface
 - `xevol agent-help` — machine-oriented guide for agents/scripts using xevol-cli
 - `xevol agent-help --json` — structured command/workflow guide for agents