foldrun 26.3.4 → 26.3.6
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/bin/foldrun.mjs +60 -60
- package/docs/a2a.md +12 -12
- package/docs/agents.md +21 -21
- package/docs/api-usage.md +2 -2
- package/docs/api.md +98 -98
- package/docs/assistant.md +21 -21
- package/docs/backups-and-restore.md +11 -11
- package/docs/budgets-and-billing.md +21 -21
- package/docs/checks.md +19 -19
- package/docs/cli.md +100 -100
- package/docs/coding-agents.md +8 -8
- package/docs/deploying.md +7 -7
- package/docs/evals.md +6 -6
- package/docs/extract.md +1 -1
- package/docs/faq.md +5 -5
- package/docs/feature-flags.md +1 -1
- package/docs/flows.md +14 -14
- package/docs/four-jobs.md +5 -5
- package/docs/getting-started.md +10 -10
- package/docs/glossary.md +9 -9
- package/docs/hooks.md +5 -5
- package/docs/how-it-works.md +1 -1
- package/docs/introduction.md +4 -4
- package/docs/knowledge-and-memory.md +6 -6
- package/docs/mcp.md +15 -15
- package/docs/network.md +9 -9
- package/docs/notifications.md +16 -16
- package/docs/oauth.md +1 -1
- package/docs/providers.md +6 -6
- package/docs/runs.md +28 -28
- package/docs/scheduling.md +1 -1
- package/docs/secrets.md +22 -22
- package/docs/security.md +15 -15
- package/docs/self-hosting.md +18 -18
- package/docs/status.md +1 -1
- package/docs/storage-and-sharing.md +14 -14
- package/docs/team-and-access.md +29 -29
- package/docs/tools.md +20 -20
- package/docs/troubleshooting.md +4 -4
- package/docs/workspaces.md +43 -43
- package/package.json +2 -2
- package/src/commands.mjs +131 -131
- package/src/guide.mjs +1 -1
package/bin/foldrun.mjs
CHANGED
|
@@ -106,14 +106,14 @@ if (command === "--version" || command === "-v") {
|
|
|
106
106
|
const HELP = `foldrun — agents are just folders
|
|
107
107
|
|
|
108
108
|
foldrun init [dir] create an account folder: AGENTS.md, library/ and workspaces/<name>
|
|
109
|
-
foldrun new <name> another
|
|
110
|
-
foldrun agent new <name> one more agent in this
|
|
111
|
-
foldrun agent new <name> --platform make it in the DEPLOYED
|
|
109
|
+
foldrun new <name> another project in this account — blank (--starter for the example researcher, writer and flow)
|
|
110
|
+
foldrun agent new <name> one more agent in this project (--to <workspace> in an account)
|
|
111
|
+
foldrun agent new <name> --platform make it in the DEPLOYED project, as the dashboard's New agent does (--to, --description, --model)
|
|
112
112
|
foldrun flow new <name> one more flow — its first step names an agent you already have
|
|
113
|
-
foldrun flow new <name> --platform make it in the deployed
|
|
114
|
-
foldrun tool new <name> one more tool: a folder with its program beside it (--transport, --language; --platform in the deployed
|
|
115
|
-
foldrun agent ls the agents deployed in a
|
|
116
|
-
foldrun check [dir] validate every
|
|
113
|
+
foldrun flow new <name> --platform make it in the deployed project from a shape (--pattern pipeline|review-loop|fan-out|debate|router, --to)
|
|
114
|
+
foldrun tool new <name> one more tool: a folder with its program beside it (--transport, --language; --platform in the deployed project, --template <gallery entry>)
|
|
115
|
+
foldrun agent ls the agents deployed in a project: model, last run, owner, description (--to, --json, --stale [days]) — flow ls the flows and how each fires
|
|
116
|
+
foldrun check [dir] validate every project here, and the shared library
|
|
117
117
|
foldrun check --to <ws> validate the DEPLOYED copy instead — fetched from the platform, checked here
|
|
118
118
|
foldrun check --security only the security rules: hard-coded secrets, hidden text, agents that can leak, unpinned code — fails on a warning
|
|
119
119
|
foldrun check --rules every rule check knows: id, level, what it guards against (--json)
|
|
@@ -123,8 +123,8 @@ const HELP = `foldrun — agents are just folders
|
|
|
123
123
|
foldrun agent link <agent> add to its team, in its frontmatter: --subagent <worker> (--isolated: sandbox: own on the worker), --consult <agent> or --can-ask (--description for a worker with none)
|
|
124
124
|
foldrun agent unlink <agent> take one away: --subagent <name>, --consult <name> or --can-ask
|
|
125
125
|
foldrun agent network <agent> the sites its sandbox may reach; set the level (open, trusted, none, inherit) and --add / --remove <site> (repeatable)
|
|
126
|
-
foldrun agent import <workspace>/<agent> copy an agent you already have in another
|
|
127
|
-
foldrun agent import --list what could be imported into a deployed
|
|
126
|
+
foldrun agent import <workspace>/<agent> copy an agent you already have in another project into this one — its agent.md, own skills and scripts, not its memory (--as <name>, --workspace <name>; --to <ws> on the platform)
|
|
127
|
+
foldrun agent import --list what could be imported into a deployed project: every other project you can read, and its agents (--to, --json)
|
|
128
128
|
foldrun flow add <flow> <pattern> one canvas block as a markdown edit: chain, parallel, router, fan-out, loop, approval, ask, wait, rescue, subflow — diff shown, checked, --dry-run
|
|
129
129
|
foldrun flow rm-step <flow> --step <n|agent> delete one step (its options too); groups renumber, agent file untouched — says what else changes, diff, checked, asks (--yes), --dry-run
|
|
130
130
|
foldrun flow rm-step <flow> --step 2,4 delete several steps in one revision (one write, or one PATCH with --to), as the canvas's multi-select delete
|
|
@@ -144,17 +144,17 @@ const HELP = `foldrun — agents are just folders
|
|
|
144
144
|
foldrun flow copy-step <flow> --step <n|agent>[,<n>…] the steps' markdown on stdout, as the canvas's Copy
|
|
145
145
|
foldrun flow paste <flow> step markdown from stdin or --file in as new groups (--after <g>, default last) or beside one (--group <g>) — diff, checked, --dry-run
|
|
146
146
|
foldrun flow draft "<what it should do>" Draft with AI on the platform (--to; --flow <name> redrafts one): shows the files and the check, saves on yes (--yes, --dry-run)
|
|
147
|
-
foldrun assistant ["<message>"] the dashboard's assistant (also: foldrun ai): answers from the foldrun docs and the deployed
|
|
147
|
+
foldrun assistant ["<message>"] the dashboard's assistant (also: foldrun ai): answers from the foldrun docs and the deployed project's files, writes agents, flows, tools and skills as diffs with the check, saves on yes (--to, --yes, --dry-run, --json; --page "<what you are looking at>" as the dashboard sends the page it is on); every reply is kept — --conversation <id> carries one on; no message in a terminal is a conversation (/save, /files, /drop, /new, /quit)
|
|
148
148
|
foldrun assistant history your kept conversations, newest first (--q <text> searches them, --workspace, --limit <n>, --json); show <id> prints one, rm <id> deletes it
|
|
149
149
|
foldrun tool test <name> exercise one tool alone, no model and no run (key=value args, --to)
|
|
150
|
-
foldrun hook ls the hooks in this
|
|
150
|
+
foldrun hook ls the hooks in this project and the account library: on, tool, description — invalid ones with the reason (--json); --to <ws>: the DEPLOYED project's, who turns each on, and what they denied, rewrote or failed lately (--runs <n>, --all)
|
|
151
151
|
foldrun hook add <name> --on <event> a hook folder: hook.md and a run.mjs that allows everything, the contract in its comments (--tool <pattern>, --library, --to)
|
|
152
152
|
foldrun hook test <name> run one hook here on a sample event, as a step would: its answer and how long it took (--event '<json>'|@file; --to <workspace>: the deployed one, on the platform)
|
|
153
153
|
foldrun hook rm <name> delete a hook folder — says which agents still turn it on, asks (--yes, --library)
|
|
154
154
|
foldrun extract [dir] move single-file script tools into folders (tool.md + run.*)
|
|
155
155
|
foldrun run <target> run an agent or flow HERE (target: name, or flow:name) — on the platform: flow run / invoke a flow, agent run one agent
|
|
156
156
|
foldrun eval [name] run one eval, or all of them (--to <workspace>: the deployed evals, run on the platform; --last reads their latest results, --run <id> one run's verdict, running nothing)
|
|
157
|
-
foldrun eval new <name> a new eval in the deployed
|
|
157
|
+
foldrun eval new <name> a new eval in the deployed project, its agent the first one there — edit its cases, then eval <name> --to (--to)
|
|
158
158
|
foldrun eval compare <eval> --models fast,default --to <ws> the cases under 2–4 models side by side (m:effort, --agent, --repeat, --max-usd; --list, --run <id>)
|
|
159
159
|
foldrun eval compare <eval> --models fast@writer,max:high@writer an item's own @agent compares only that agent's steps in that setting (--agent is the default for items without one)
|
|
160
160
|
foldrun eval improve <eval> --to <ws> ask the assistant for a proposed fix from the failures, wait for the draft (--no-wait)
|
|
@@ -164,7 +164,7 @@ const HELP = `foldrun — agents are just folders
|
|
|
164
164
|
foldrun eval trends --to <ws> evals by change, as the Observe page: each eval now against its last run on a different commit, biggest drop first (--json); exit 1 when a change made one worse
|
|
165
165
|
foldrun promote <run-id> keep a finished run as a regression case in evals/ (--eval <name>, --expect "contains: …" repeatable, --case <name>); a run that went wrong takes --should "what it should have done"
|
|
166
166
|
foldrun probe <model> live check: can this model hold a tool loop here?
|
|
167
|
-
foldrun logs [run-id] recent runs in one
|
|
167
|
+
foldrun logs [run-id] recent runs in one project, or one run's full event trail (--local: this machine's)
|
|
168
168
|
foldrun runs what has run lately, across the account — --status, --verdict, --outcome (good, done, quiet, blocked, bad, failed, needs-you, …), --since, --to, --flow <name>, --q <words>, --limit; search with --tool, --tool-error, --agent, --model, --min-tokens 50k, --min-secs, --context <id>, or --view <name>; --limit is one page: --page <n>, --before <cursor> (printed when more match), --all, --json
|
|
169
169
|
foldrun runs outputs <run-id> which files the run archived from its agents' outputs/, with their sizes (--to, --json); report <run-id> get downloads one
|
|
170
170
|
foldrun runs views your saved run searches (--local prints exactly what logs --local prints)
|
|
@@ -172,7 +172,7 @@ const HELP = `foldrun — agents are just folders
|
|
|
172
172
|
foldrun runs views rm <name> delete a saved view (asks; --yes)
|
|
173
173
|
foldrun runs doctor <run-id> the run doctor: the assistant reads a failed run and the files it names, says why (platform, check, work or outside) and proposes the fix as diffs, saved on yes (--to, --yes, --dry-run, --json)
|
|
174
174
|
foldrun runs rm <run-id> delete a run's record and archived outputs (an admin); a live one is stopped first — asks first, --yes means it
|
|
175
|
-
foldrun runs rm <run-id> <run-id>… delete several: lists them, asks once, then deletes them in one runs/bulk call per
|
|
175
|
+
foldrun runs rm <run-id> <run-id>… delete several: lists them, asks once, then deletes them in one runs/bulk call per project, as the dashboard does
|
|
176
176
|
foldrun runs rm --until <30d|date> delete every finished run that started before then — records, captured calls, archived outputs (an admin; --to <workspace>, --dry-run, --yes); live runs are left alone
|
|
177
177
|
foldrun report <run-id> one run, whole: header, every step, what it wrote and what is still waiting
|
|
178
178
|
foldrun report <run-id> get <agent>/<path> download a file the run archived from that agent's outputs/ (--file <path>|-, --force)
|
|
@@ -192,7 +192,7 @@ const HELP = `foldrun — agents are just folders
|
|
|
192
192
|
foldrun mcp clients add <name> a machine client for /api/mcp, signing in with client credentials (no person approves its tokens): --role viewer|editor|admin, --workspaces a,b, --write (else read only), --token-auth basic|post|jwt (jwt with --jwks-file <path>); prints the client id and secret, the secret once
|
|
193
193
|
foldrun issues what went wrong, grouped, open until resolved (--to <workspace>, --all, --status, --json)
|
|
194
194
|
foldrun issues show|ack|snooze|resolve|reopen <id> one issue — snooze --for 1d, --until <ISO time> or --times 5, --note "…"
|
|
195
|
-
foldrun issues doctor <id> the run doctor on the issue's newest run, in its
|
|
195
|
+
foldrun issues doctor <id> the run doctor on the issue's newest run, in its project: why, and the fix as diffs, saved on yes (--yes, --dry-run, --json)
|
|
196
196
|
foldrun approve <run-id> release a waiting gate — asks first, --yes means it, --note "…" steers the step; --payload releases a wait: event step
|
|
197
197
|
foldrun reject <run-id> refuse one, with --note as the reason; --event-wait rejects a step waiting on wait: event (the step fails, the run ends)
|
|
198
198
|
foldrun stop <run-id> kill a run in flight — asks first, --yes means it
|
|
@@ -203,22 +203,22 @@ const HELP = `foldrun — agents are just folders
|
|
|
203
203
|
foldrun rerun <run-id> run it again from a step (--from <n>) or from an agent's step (--agent <name>); --instruction "…" tells that step something else this once; --wait
|
|
204
204
|
foldrun rerun --status failed [--since 24h] [--until 2h] [--flow f] rerun every run a filter matches, from --from <n> (default 1) — lists, asks (--dry-run, --to)
|
|
205
205
|
foldrun rerun <run-id> <run-id>… rerun several (runs/bulk), from --from <n> (default 1) — lists, asks once (--dry-run, --yes)
|
|
206
|
-
foldrun observe where the account fails, retries and spends, per
|
|
206
|
+
foldrun observe where the account fails, retries and spends, per project, then the window against the one before, why runs went wrong, the agents and tools to watch (--to <workspace> in full, --since <days>, --json)
|
|
207
207
|
foldrun usage what the account consumed, and what it was charged week by week (--days <n>, --json)
|
|
208
208
|
foldrun usage --limit <n> how many rows of by flow and by agent (the most charged; default 10, 0 hides them)
|
|
209
|
-
foldrun usage compute cores, GiB and disk its running steps may hold — the account, each
|
|
209
|
+
foldrun usage compute cores, GiB and disk its running steps may hold — the account, each project, each live run — what they hold now, and the steps waiting for room (--json)
|
|
210
210
|
foldrun usage meters what the period used, meter by meter: vCPU, RAM, step disk, storage, network with quantity, rate and credits, the plan fee, each step size, the two credit pots, and tokens by provider and model — your own key at 0 credits (--since <day>, --until <day>, --json)
|
|
211
211
|
foldrun usage rates what each meter costs this account, its plan and the plans on offer, and the price list for foldrun's models (--json)
|
|
212
|
-
foldrun usage budget spend against each cap — the account's and each
|
|
212
|
+
foldrun usage budget spend against each cap — the account's and each project's budget:, what is spent in its window (today, this week, this month) and how close it is (--to <workspace> for one, --json)
|
|
213
213
|
foldrun schedule every flow that fires on a clock, its cron line and the next times (--to <workspace>)
|
|
214
214
|
foldrun schedule tick fire whatever is due now — Settings' "Run scheduler now"
|
|
215
215
|
foldrun guide write the coding-agent rules: a block in AGENTS.md and CLAUDE.md importing it (--check, --print)
|
|
216
216
|
foldrun docs [page] foldrun's docs, from the copy this CLI ships — what a coding agent should read (--path)
|
|
217
217
|
foldrun triggers why nothing ran: per flow, fired vs started and every reason, then the newest decisions and the deliveries at the hook and inbox URLs (--since <days>, --limit <n> of each, default 10, --to <workspace>, --json)
|
|
218
|
-
foldrun storage <verb> what a
|
|
219
|
-
foldrun storage text <path> a file in a
|
|
220
|
-
foldrun storage ls --all every
|
|
221
|
-
foldrun runtimes the environments a deployed
|
|
218
|
+
foldrun storage <verb> what a project produced: ls [prefix], cat <path> (--preview: a PDF, sheet, deck or zip as text), get <path>, put <file|folder>... (--into <folder/>, --as <path> for one file), rm <path> — and share <path> (--ttl <days>, --forever), shares (--all), unshare <token|id>
|
|
219
|
+
foldrun storage text <path> a file in a project's storage as text, read by the platform (PDF, scan, document, sheet, recording) — printed, and written beside it as <path>.txt unless --no-write (--lang, --ocr, --engine, --wait, --json; --to or --workspace <ws>)
|
|
220
|
+
foldrun storage ls --all every project's storage, as the account's Storage page: a block per project, busiest first ([prefix], --json)
|
|
221
|
+
foldrun runtimes the environments a deployed project's agents need (python, pip and npm packages) and whether each is built — failed ones with the installer's error (--wait holds on while any is building)
|
|
222
222
|
foldrun billing the account's balance and its recent ledger entries (--limit <n>)
|
|
223
223
|
foldrun billing statement [YYYY-MM] a month of the ledger (--csv for the file, --file <path> to save it)
|
|
224
224
|
foldrun billing invoices the plan's tax invoices from Stripe (number, date, amount, status, link) and every credit purchase with its receipt (--json)
|
|
@@ -238,49 +238,49 @@ const HELP = `foldrun — agents are just folders
|
|
|
238
238
|
foldrun account clear compute <vcpu|memory|disk>… drop just those figures of the account's pool · clear notify <email|url>: drop one channel, the other and the events kept
|
|
239
239
|
foldrun account export everything the platform holds about the account as one JSON file (owner only; --file <path>, --force)
|
|
240
240
|
foldrun account model what steps run on — your own key: set <provider> --key <api key> (--key - reads stdin, or asks for it hidden in a terminal; custom --base-url --format; --use runs on it at once, as use own), remove; or foldrun's models (billed in credits): use foldrun --provider <p>, use own, prices
|
|
241
|
-
foldrun workspace one deployed
|
|
241
|
+
foldrun workspace one deployed project's settings (--to) — also set <name|description|timezone|budget|compute|notify|network_enforce|owner|alerts|judge> <value> (compute vcpu <n> memory <GiB> disk <GiB>: this project's pool) (or <job>.<field>), clear <key>, pause [--reason] [--stop] / resume (the kill switch)
|
|
242
242
|
foldrun workspace clear compute <vcpu|memory|disk>… drop just those figures of its pool · clear notify <email|url>: one channel, the rest kept (--to)
|
|
243
|
-
foldrun workspace vocabulary the names the dashboard's editor completes in a
|
|
244
|
-
foldrun notify test send one test notification from a
|
|
245
|
-
foldrun webhooks deliveries the notify: webhooks a
|
|
243
|
+
foldrun workspace vocabulary the names the dashboard's editor completes in a project: agents, flows, skills, tools, secrets, scripts, types, documents (--to, --json)
|
|
244
|
+
foldrun notify test send one test notification from a project and say what happened (--to <workspace>)
|
|
245
|
+
foldrun webhooks deliveries the notify: webhooks a project sent, newest first — status, attempts, last answer (--failed, --status <s>, --event <e>, --limit, --offset, --to)
|
|
246
246
|
foldrun webhooks redeliver <id> send one delivery again now, same X-Foldrun-Delivery id; exits 1 when refused (--to)
|
|
247
247
|
foldrun notifications what mail you get, category by category, and which are always sent (--json)
|
|
248
248
|
foldrun notifications set <category> on|off turn one off or back on — account-wide, or --to <workspace> for run-alerts and approvals
|
|
249
249
|
foldrun flags the feature flags for this account: each on or off, and why — set for this account, for every account, a staged rollout, or the default (--json). Read-only: the platform's operator changes them
|
|
250
|
-
foldrun history [path] every change to a deployed
|
|
250
|
+
foldrun history [path] every change to a deployed project, newest first (--id <revision> for its diff, --limit, --to)
|
|
251
251
|
foldrun history restore <path> --id <revision> put one file back as that revision left it, as a new revision — diff, asks (--yes, --dry-run, --to)
|
|
252
|
-
foldrun restore <ws> --to <revision|time|age> put a
|
|
252
|
+
foldrun restore <ws> --to <revision|time|age> put a project's source back as it was then — shows the change, asks for the name typed back (--dry-run: the diff only, --yes)
|
|
253
253
|
foldrun backups how the account is backed up (encrypted?), when it last was, the snapshots it is in — also request --what runs|state|storage|everything --at "<when>" [--to <ws>] [--backup <id>] [--note]
|
|
254
254
|
foldrun backups requests every restore asked of the platform team, and where each stands (--json)
|
|
255
255
|
foldrun secrets set NAME store a secret (prompted, never echoed) — also ls, rm, status; --kind file|ssh|api|service-account|m2m|client-cert|identity|token-exchange for the other shapes; --oauth2 for a refresh token; --site <domain> (repeatable) binds it as it is stored; --account --workspaces a,b or --none limits it as it is stored
|
|
256
|
-
foldrun secrets ls the secrets in scope: where each is set, its sites and
|
|
256
|
+
foldrun secrets ls the secrets in scope: where each is set, its sites and projects — and on the platform whether the far end last accepted it, refused it (since when) or nothing has used it yet (--json)
|
|
257
257
|
foldrun secrets rm NAME delete one (asks; --yes) — an oauth2 secret's grant is revoked at the provider; an account secret's saved OAuth client left unused is named, and --with-client deletes it too (asks)
|
|
258
258
|
foldrun secrets sites NAME [site…] bind a secret to sites: the egress proxy fills it for those alone and it never enters a sandbox; no sites lists them, --clear unbinds
|
|
259
|
-
foldrun secrets workspaces NAME [workspace…] limit an account secret to those
|
|
259
|
+
foldrun secrets workspaces NAME [workspace…] limit an account secret to those projects — every other one finds it not set; --all opens it to every project again, --none to no project, no names shows which may use it (an admin over every project; applies to runs that start after it)
|
|
260
260
|
foldrun secrets workspaces NAME … --if-workspaces <a,b|all|none> only if the list is still the one you read — refused otherwise, as Settings does
|
|
261
261
|
foldrun secrets clients the OAuth clients saved on the platform — also add <name> (--authorize-url/--token-url, --client-id, --scopes, --authorize-param name=value), rm <name>
|
|
262
262
|
foldrun connect NAME OAuth sign-in from the terminal, stored as an auto-refreshing secret — --client <saved> runs it from a saved client through the platform
|
|
263
263
|
foldrun deploy [dir] push the whole account, or deploy <workspace> for one of them
|
|
264
264
|
foldrun pull [workspace] bring the platform's account down here (refuses to clobber; --force overrides)
|
|
265
|
-
foldrun export [workspace] a deployed
|
|
266
|
-
foldrun import <file.zip> take a package in: shows what it adds, would replace and still needs, then asks (--to <workspace>; a new name makes a
|
|
265
|
+
foldrun export [workspace] a deployed project as a .zip — agents, flows, tools, skills, scripts, evals, knowledge; never memory, state or secret values (--flow <name> or --agent <name> for one, with what it needs; --file <path>|-, --force)
|
|
266
|
+
foldrun import <file.zip> take a package in: shows what it adds, would replace and still needs, then asks (--to <workspace>; a new name makes a project; --dry-run, --overwrite, --yes, --json)
|
|
267
267
|
foldrun snapshot push [dir] send a git folder for an agent on foldrun to work on: what git would commit, checked for secrets here and on the platform, answers the snapshot id (--to <workspace>; --dry-run, --out <file.tar.gz> (--force over one that is there), --json)
|
|
268
|
-
foldrun status [workspace] per
|
|
268
|
+
foldrun status [workspace] per project: what is added, changed or gone since the last deploy
|
|
269
269
|
foldrun status --platform is the platform up: each component, and any incident or maintenance posted (--json)
|
|
270
270
|
foldrun status --platform --history uptime per component per day and the incidents in the window, as the status page's bars (--days 1-90, default 90; --json)
|
|
271
271
|
foldrun workspaces what exists here and on the platform (--json for a script) — also rm <name> (--platform --yes)
|
|
272
272
|
foldrun workspaces show <name> what is deployed in one: its agents, flows and how each fires, its files by folder (--json)
|
|
273
273
|
foldrun workspaces new <name> --platform make it on the platform: blank (an AGENTS.md), or --starter for the example researcher, writer and flow
|
|
274
|
-
foldrun workspaces demo make the demo pipeline
|
|
274
|
+
foldrun workspaces demo make the demo pipeline project on the platform — "Try the demo pipeline"
|
|
275
275
|
foldrun library the account's shared library on the platform: ls [skills|tools|hooks|scripts|knowledge|memory], cat <kind>/<path>, put <kind>/<path> (--file, else stdin), rm <kind>/<path> (asks)
|
|
276
276
|
foldrun library new <kind>/<name> a new one from the platform's template, as the Library page's New (--template <transport or gallery entry>, --language)
|
|
277
|
-
foldrun find <words> search the account as the dashboard's ⌘K does:
|
|
277
|
+
foldrun find <words> search the account as the dashboard's ⌘K does: projects, agents, flows, tools, skills, knowledge, memory, runs (--json)
|
|
278
278
|
foldrun invoke <flow> start a flow on a running platform (--to <workspace>; --once <key> so a retry never starts a second run; --tag <t> repeatable)
|
|
279
279
|
foldrun source <verb> the files on a platform, one at a time: ls, cat <path>, put <path>, mv, rm (--to <workspace>)
|
|
280
280
|
foldrun source new <kind> <name> the dashboard's New for any document — tools, knowledge, memory, skills, scripts (agents, flows, evals too): the platform writes the template (--agent <a> inside one agent, --template, --language, --to)
|
|
281
281
|
foldrun source put <path> --check the editor's checked save: refused with the issues (exit 1, nothing saved) when the file would not check out; --empty writes an empty file
|
|
282
|
-
foldrun source share <path> the dashboard's Move to shared: a skill, tool, script, knowledge or memory file (a skill or folder tool whole) into the account library, then out of the
|
|
283
|
-
foldrun open [page] the dashboard for this
|
|
282
|
+
foldrun source share <path> the dashboard's Move to shared: a skill, tool, script, knowledge or memory file (a skill or folder tool whole) into the account library, then out of the project — asks (--yes), --dry-run, --overwrite (--to)
|
|
283
|
+
foldrun open [page] the dashboard for this project, in the browser
|
|
284
284
|
foldrun api spec the platform's OpenAPI 3.1 document (GET /api/openapi.json) — stdout, or --out <file>
|
|
285
285
|
foldrun api version the API version this account's requests get, the versions served, the rate limits, your last 30 days by version and any deprecated route you still call — also pin <YYYY-MM-DD>, unpin (admin; --json)
|
|
286
286
|
foldrun changelog the platform's release notes, newest first: features, fixes, docs — and the API's versions, breaking changes and deprecations (--limit <n>, --json)
|
|
@@ -292,18 +292,18 @@ Signing in
|
|
|
292
292
|
open a browser, sign in to that site by hand, and store the
|
|
293
293
|
session: cookies, storage and the browser identity it needs
|
|
294
294
|
foldrun logout forget this machine's key, and revoke it where allowed
|
|
295
|
-
foldrun whoami who you are on the platform: account, role,
|
|
295
|
+
foldrun whoami who you are on the platform: account, role, projects
|
|
296
296
|
foldrun signup status can a stranger sign up on the platform: free sign-up, paid sign-up, and the plans sold while paid is in effect — the open /api/signup, no key sent (--url, --json; exits 1 when it does not answer)
|
|
297
297
|
foldrun me the person this machine is signed in as: name, address, timezone (--json)
|
|
298
298
|
foldrun me name <first> [last] set your name (--clear for none) · foldrun me timezone <zone|auto> the zone you read times in
|
|
299
|
-
foldrun team who is in the account: role, the
|
|
299
|
+
foldrun team who is in the account: role, the projects each may open, when they joined (--json)
|
|
300
300
|
foldrun team invite [email] invite someone (--role viewer|editor|admin, default editor; --workspaces a,b or --all; --no-send): prints the link, once. Your own foldrun login, never a key made by hand; an owner's sign-in here acts as admin, so an admin invite is the browser's
|
|
301
301
|
foldrun team role <email|id> <role> change a member's role (viewer, editor, admin); their keys above it stop
|
|
302
|
-
foldrun team access <email|id> which
|
|
302
|
+
foldrun team access <email|id> which projects they may open: --workspaces a,b, --all or --none; never wider than yours
|
|
303
303
|
foldrun team remove <email|id> remove a member — asks first (--yes with no terminal); their keys and pending invites stop. Transfer stays in Settings → Team
|
|
304
|
-
foldrun team invites the account's pending invites — address or "anyone with the link", role,
|
|
304
|
+
foldrun team invites the account's pending invites — address or "anyone with the link", role, projects, who made it, when it expires, its id (--all for accepted, revoked and expired too; --json). Never the link: each works once, shown only to its maker
|
|
305
305
|
foldrun team invites revoke <id> take an invite back: its link stops working at once (an admin's; a key may)
|
|
306
|
-
foldrun onboarding the account's getting-started steps, done or not, the next one first; --to <workspace> adds that
|
|
306
|
+
foldrun onboarding the account's getting-started steps, done or not, the next one first; --to <workspace> adds that project's checklist (--json)
|
|
307
307
|
foldrun preferences your own settings on the platform — the theme; set theme system|light|dark (a key acts for whoever minted it)
|
|
308
308
|
foldrun doctor check the path to the platform: node, CLI, model credential, account, DNS, a timed /api/healthz
|
|
309
309
|
foldrun accounts every account signed in on this machine, and which one is active
|
|
@@ -313,12 +313,12 @@ Signing in
|
|
|
313
313
|
foldrun keys create <label> --a2a --to <ws> --flows a,b a key for an OUTSIDE agent: it opens /a2a for those published flows and no /api route (--max-tasks N open at once, default 10; --expires); shown once
|
|
314
314
|
foldrun keys set <id> --sonnet openai/gpt-6 which model a gateway key runs each Claude Code tier on (--opus, --haiku; - clears one, --clear all)
|
|
315
315
|
foldrun keys set <id> --customer required|optional whether every run (API key) or gateway call (gateway key) with it must name an end customer — create one that requires it with keys create … --require-customer
|
|
316
|
-
foldrun keys create <label> --gateway --cap <usd> [--daily <usd>] a key for a CODING agent (Claude Code: ANTHROPIC_BASE_URL + this key) — it spends the account's credits on foldrun's models through the gateway, up to its own limits, and opens no /api route; an admin of every
|
|
316
|
+
foldrun keys create <label> --gateway --cap <usd> [--daily <usd>] a key for a CODING agent (Claude Code: ANTHROPIC_BASE_URL + this key) — it spends the account's credits on foldrun's models through the gateway, up to its own limits, and opens no /api route; an admin of every project; shown once
|
|
317
317
|
foldrun keys create laptop --gateway --cap 20 --claude-code the same, and Claude Code is set up on this machine: the URL and key go into its settings, and its status line shows the key's spend
|
|
318
318
|
foldrun gateway status-line one line for Claude Code's status line: what the gateway key in ANTHROPIC_AUTH_TOKEN has spent, of its limits (asks the gateway; kept 10 s, --cache <s>)
|
|
319
319
|
foldrun text <file> a local file as text: uploads it to the platform, which reads it — a PDF or scan (OCR in Persian or English), a Word, sheet or slide file, a recording — and prints the text (--lang fa|en|auto, --ocr auto|always|never, --engine docling, --out <path> or -o <path>, --json, --wait <s>); a long job is polled until it ends
|
|
320
320
|
foldrun talk speak a prompt: records the microphone until you stop talking, foldrun's own Whisper turns it into text (Persian with the Persian model), prints the words — Claude Code's /talk runs it (--lang auto|fa|en…, --max <s> up to 120, --silence <s>, --file <audio or video> instead of the mic, --mic <name>, --plain, --json; the gateway key from ANTHROPIC_AUTH_TOKEN or --url/--key)
|
|
321
|
-
foldrun a2a ls --to <ws> what a
|
|
321
|
+
foldrun a2a ls --to <ws> what a project serves over A2A: each flow's a2a:, card and endpoint URLs, its A2A keys (admins), recent tasks and the key that asked (--json)
|
|
322
322
|
foldrun a2a publish <flow> set a2a: publish: true in the flow (--to <ws>: the deployed copy, an admin's) — --name, --description, --example "…" (repeatable), --public-card | --private-card; diff, checked, --dry-run
|
|
323
323
|
foldrun a2a publish <flow> --clear-name | --clear-description | --clear-examples drop the card's name, description or examples (also on unpublish)
|
|
324
324
|
foldrun a2a publish <flow> --accept-risk <agent,…> accept that these agents hold a secret while they can run code (a2a: accept_risk, every one named; their answer goes to the caller) — without it such a flow is not published; --clear-accept-risk takes it out
|
|
@@ -332,10 +332,10 @@ Signing in
|
|
|
332
332
|
foldrun --help everything; \`foldrun <command> --help\`, \`-h\` or \`foldrun help <command>\` for one (never runs it)
|
|
333
333
|
|
|
334
334
|
Options
|
|
335
|
-
--workspace <dir> the
|
|
335
|
+
--workspace <dir> the project folder (default: .) — on init, the first project's name
|
|
336
336
|
--flat init: the old single-folder shape, no account around it
|
|
337
337
|
--from <template> init: start from a shipped template, e.g. templates/hello (new takes it too)
|
|
338
|
-
--starter new, workspaces new: include the example researcher, writer and publish flow (a new
|
|
338
|
+
--starter new, workspaces new: include the example researcher, writer and publish flow (a new project is blank)
|
|
339
339
|
--transport <k> tool new: script (default), http or mcp
|
|
340
340
|
--language <l> tool new, source new, library new: the script's language — javascript, python, bash
|
|
341
341
|
--task "<text>" the instruction for a manual run
|
|
@@ -354,10 +354,10 @@ Options
|
|
|
354
354
|
--since <span> audit: entries from 24h, 7d, 30d ago, or a date (default 7d); --until <date> ends the window
|
|
355
355
|
--action <a> audit: one action (apikey.created) or a family (apikey, secret, member, support)
|
|
356
356
|
--actor <who> audit: one person or key — an email, key:<label>, support:<email>
|
|
357
|
-
--since <days> observe, triggers: the window in days (observe default 7 as the account Observe page, observe --to 30 as a
|
|
357
|
+
--since <days> observe, triggers: the window in days (observe default 7 as the account Observe page, observe --to 30 as a project's; triggers 7); observe takes --days too
|
|
358
358
|
--until <span|date> stop, rerun (bulk): only runs started before then — 2h ago, or a date; usage meters: the period's last UTC day (YYYY-MM-DD)
|
|
359
359
|
--verdict <v> runs: only completed runs whose summary leads with it — good, bad, quiet, blocked (comma-separated)
|
|
360
|
-
--q <words> runs: the runs page's text search — every word, any order, across id, flow,
|
|
360
|
+
--q <words> runs: the runs page's text search — every word, any order, across id, flow, project, status, verdict, summary and failure; assistant history: search the conversations
|
|
361
361
|
--flow <name> export: that flow and everything it runs; runs, stop, rerun: only that flow's runs; flow add: the other flow a subflow step runs; flow draft: the existing flow to redraft
|
|
362
362
|
--agent <name> export: that agent and what it grants; flow add: the agent a chain, parallel or router step runs; rerun: from the first step that agent runs; report live: whose browser frame; source new: the agent the document belongs to
|
|
363
363
|
--instruction "<text>" flow add: what a new step (chain, parallel, router) is told to do
|
|
@@ -372,7 +372,7 @@ Options
|
|
|
372
372
|
--on-fail <agent> flow add: who takes the step over when it fails
|
|
373
373
|
--off flow add: take the pattern off the step instead (fan-out, loop, approval, ask, wait, rescue)
|
|
374
374
|
--schedule "<cron>" flow trigger: the cron line a schedule fires on (5 fields, or @daily); --timezone <zone> the zone it is read in
|
|
375
|
-
--team, --started, --mine, --all inbox: which bucket (default: assigned to you and started by you); --workspace <ws> only that
|
|
375
|
+
--team, --started, --mine, --all inbox: which bucket (default: assigned to you and started by you); --workspace <ws> only that project's items; inbox read --all marks every unread one read
|
|
376
376
|
--dismissed, --unread inbox: what you set aside; only what you have not read
|
|
377
377
|
--read-only mcp: offer the AI app only the tools that read — no run, approve, answer, message or stop
|
|
378
378
|
--models <m[:effort],…> eval compare: two to four tiers or model ids to compare, each with an optional :effort
|
|
@@ -430,10 +430,10 @@ Options
|
|
|
430
430
|
--note "<text>" approve, reject: guidance the agent reads — or the reason for a refusal; billing credit: the ledger line's note
|
|
431
431
|
--run <id> eval --to: that eval run's verdict, by the id the run printed; runs nothing
|
|
432
432
|
--stale [days] agent ls: only agents not run in that many days (never run included); bare, those past alerts: stale_days
|
|
433
|
-
--reason "<text>" account pause,
|
|
434
|
-
--stop account pause,
|
|
433
|
+
--reason "<text>" account pause, project pause: why — shown to everyone who opens it
|
|
434
|
+
--stop account pause, project pause: also stop every run going now (asks; --yes to mean it)
|
|
435
435
|
--yes approve, stop, rerun (bulk), pause --stop, flow rotate-hook, flow draft, assistant, history restore, restore <ws>, import, billing plan, workspace set name, team remove, and every rm/revoke/unshare: skip the confirmation, deliberately (required with no terminal)
|
|
436
|
-
--json report: the raw run record instead of the report; runs: { runs, next }; runs outputs: { runId, files, totalBytes }; observe, usage, api version, changelog, find, preferences, workspace vocabulary, flags,
|
|
436
|
+
--json report: the raw run record instead of the report; runs: { runs, next }; runs outputs: { runId, files, totalBytes }; observe, usage, api version, changelog, find, preferences, workspace vocabulary, flags, projects, workspaces show, agent ls, flow ls, agent import --list, backups requests, team, hook ls, secrets ls, triggers, storage ls --all: the raw document; version: {cli, core, platform}
|
|
437
437
|
--events <a,b> account set notify: failed, awaiting-approval, completed
|
|
438
438
|
--failed webhooks deliveries: only the ones that gave up
|
|
439
439
|
--limit <n> runs, billing, history, changelog: how many rows; triggers: how many decisions and deliveries (default 10)
|
|
@@ -443,11 +443,11 @@ Options
|
|
|
443
443
|
--value "<text>" secrets set: skip the prompt (careful with shell history)
|
|
444
444
|
--site <domain> secrets set, secrets sites: a site the secret is bound to — the egress proxy fills it for those alone (repeatable, or a,b)
|
|
445
445
|
--clear secrets sites: unbind it; flow compute: no cap of its own; me name: no name
|
|
446
|
-
--all runs: every run that matches, every page; secrets workspaces: every
|
|
447
|
-
--none secrets workspaces, secrets set: no
|
|
446
|
+
--all runs: every run that matches, every page; secrets workspaces: every project may use the account secret again; storage ls: every project's storage; storage shares: expired and revoked links too; mcp connections: the disconnected ones too; team invite, team access: every project
|
|
447
|
+
--none secrets workspaces, secrets set: no project may use the account secret; team access: no projects
|
|
448
448
|
--if-workspaces <a,b|all|none> secrets workspaces: change it only while the list is still this one (refused, 409, when someone changed it since)
|
|
449
449
|
--if-version <n> account model use: change it only while the choice is still that choiceVersion (account model --json; 0: never chosen)
|
|
450
|
-
--workspaces <a,b> secrets set: store an account secret limited to those
|
|
450
|
+
--workspaces <a,b> secrets set: store an account secret limited to those projects, in the same write (with --account); team invite, team access: the projects they may open
|
|
451
451
|
--add <site> agent network: add a site to its network: list (repeatable)
|
|
452
452
|
--remove <site> agent network: take a site off its network: list (repeatable)
|
|
453
453
|
--out <file> api spec: where to write the OpenAPI document (default: stdout); check: where to write the JSON or SARIF report; text: where to write the text (-o <file> too; refused when it exists, --force overwrites)
|
|
@@ -455,12 +455,12 @@ Options
|
|
|
455
455
|
--message "<why>" source put: recorded on the file's revision
|
|
456
456
|
--check source put: refuse the save when the file would not check out (422: the issues printed, nothing written)
|
|
457
457
|
--empty source put: write an empty file on purpose (empty input is refused otherwise)
|
|
458
|
-
--account secrets: account scope instead of the
|
|
458
|
+
--account secrets: account scope instead of the project's
|
|
459
459
|
--wait invoke, agent run: hold on and print the result
|
|
460
460
|
--path <p> tool test: the path an http tool should probe, appended to its base:
|
|
461
461
|
--on <event> hook add: what it listens for — tool.call, tool.result, step.start or step.end
|
|
462
462
|
--tool <pattern> hook add: which tools a tool.call or tool.result hook sees — Bash, Write|Edit, mcp__* (default all)
|
|
463
|
-
--library hook add, hook rm: in the account library (every
|
|
463
|
+
--library hook add, hook rm: in the account library (every project), not this project
|
|
464
464
|
--event <json|@file> hook test: the event the hook reads on stdin (default: a sample for its on:)
|
|
465
465
|
--watch invoke: follow the run's trace here as it happens
|
|
466
466
|
--print open: print the URL only
|
|
@@ -488,7 +488,7 @@ Options
|
|
|
488
488
|
--card <url> a2a status, a2a cancel: the agent card of the agent that holds the task
|
|
489
489
|
|
|
490
490
|
Platform options (deploy, invoke, secrets, logs, keys)
|
|
491
|
-
--to <workspace>
|
|
491
|
+
--to <workspace> project on the platform (deploy default: folder name); flow add/show, agent link: edit or show the deployed copy instead of this folder; hook test: run the deployed hook on the platform; hook ls: list the deployed project's hooks and what they did lately; restore <ws>: the commit, date or age to put it back to (3d, 2026-09-28T14:00)
|
|
492
492
|
--tenant <name> account to deploy into (default: default, local only)
|
|
493
493
|
--data <dir> the installation's data directory
|
|
494
494
|
--url <url> a running platform (or FOLDRUN_URL, or where you last signed in)
|
|
@@ -499,11 +499,11 @@ Platform options (deploy, invoke, secrets, logs, keys)
|
|
|
499
499
|
--quiet leave out the dim "acting as …" line a platform command prints on stderr
|
|
500
500
|
--local deploy: into the installation on this machine, even when signed in
|
|
501
501
|
--commit <sha> deploy: record which commit this is
|
|
502
|
-
--overwrite import: replace files the
|
|
502
|
+
--overwrite import: replace files the project already has with different text (refused otherwise)
|
|
503
503
|
--overwrite source share: replace a library file of the same path (refused otherwise)
|
|
504
504
|
--dry-run source share: list what would move, move nothing
|
|
505
505
|
--dry-run deploy: check and report, change nothing; flow add, flow set, flow trigger, flow compute, flow move-step, flow paste, flow draft, assistant, history restore, agent link, agent unlink: show the diff, write nothing; restore <ws>: the diff only, restore nothing; import: the preview only, write nothing; stop, rerun (bulk): list what matches, touch nothing
|
|
506
|
-
--no-runtimes deploy: do not wait for the
|
|
506
|
+
--no-runtimes deploy: do not wait for the project's environments to be built
|
|
507
507
|
--force deploy: deploy even while runs are in flight; pull, storage get, text: overwrite local files
|
|
508
508
|
--yes deploy: allow deleting files this folder no longer has (asked otherwise; required with no terminal)
|
|
509
509
|
--platform --yes workspaces rm: delete it on the platform, deliberately
|
package/docs/a2a.md
CHANGED
|
@@ -49,7 +49,7 @@ a2a:
|
|
|
49
49
|
| `accept_risk` | a list of this flow's agents that an admin accepts **holding a secret while they can run code** ([below](#secret-and-code-accept_risk)). Up to 50 names |
|
|
50
50
|
|
|
51
51
|
A block `foldrun check` cannot read publishes nothing — a typo never opens a
|
|
52
|
-
flow nobody meant to open. Whether a flow is published is the
|
|
52
|
+
flow nobody meant to open. Whether a flow is published is the project's
|
|
53
53
|
policy, so changing `a2a:` needs the **admin** role (`workspace:manage`) by
|
|
54
54
|
every door: the editor, a deploy, `PATCH /flows/<f>`, `PUT /source`. An
|
|
55
55
|
editor's change that leaves `a2a:` as it was goes through.
|
|
@@ -67,9 +67,9 @@ foldrun a2a ls --to sales # what the workspace serves, and it
|
|
|
67
67
|
foldrun a2a unpublish lead-finder --to sales
|
|
68
68
|
```
|
|
69
69
|
|
|
70
|
-
The
|
|
70
|
+
The project's **Triggers** page, section **Outside agents (A2A)** (and
|
|
71
71
|
`GET /api/workspaces/<ws>/a2a`), lists every
|
|
72
|
-
flow that says `a2a:`, its card and endpoint URLs, the
|
|
72
|
+
flow that says `a2a:`, its card and endpoint URLs, the project's A2A keys and
|
|
73
73
|
the newest tasks with the key that asked.
|
|
74
74
|
|
|
75
75
|
`foldrun check` warns on a published flow that is risky to open
|
|
@@ -134,9 +134,9 @@ or delete, a deploy, an import, a restore, a proposed fix:
|
|
|
134
134
|
- a new tool (a `{Bash: ask}` turned into a plain grant counts), secret, API,
|
|
135
135
|
MCP server, outside agent (`remotes:`), script or sub-agent; a changed API,
|
|
136
136
|
MCP or remote spec;
|
|
137
|
-
- a wider network — the agent's, or the
|
|
137
|
+
- a wider network — the agent's, or the project's `network:` in AGENTS.md
|
|
138
138
|
(a higher level, or a new site);
|
|
139
|
-
- a hook gone (the agent's own, or the
|
|
139
|
+
- a hook gone (the agent's own, or the project's `hooks:`),
|
|
140
140
|
`permissionMode: plan` dropped, `sandbox: own` added;
|
|
141
141
|
- a new agent behind the flow — a step, rescuer, delegate, sub-agent or
|
|
142
142
|
subflow that was not there.
|
|
@@ -158,13 +158,13 @@ secret-and-code agent it creates.
|
|
|
158
158
|
## A2A keys
|
|
159
159
|
|
|
160
160
|
A caller needs an **A2A key**: a key of its own kind, minted by an admin of
|
|
161
|
-
the
|
|
161
|
+
the project, for one project and the flows it names.
|
|
162
162
|
|
|
163
163
|
```sh
|
|
164
164
|
foldrun keys create "Partner CRM" --a2a --to sales --flows lead-finder,quote --max-tasks 5
|
|
165
165
|
```
|
|
166
166
|
|
|
167
|
-
or **Settings → API keys**, kind **A2A key**: the
|
|
167
|
+
or **Settings → API keys**, kind **A2A key**: the project, the published
|
|
168
168
|
flows it may call, and how many tasks it may have open at once. The key is
|
|
169
169
|
shown once.
|
|
170
170
|
|
|
@@ -326,7 +326,7 @@ request foldrun cannot take **now** is `-32000` with a foldrun reason:
|
|
|
326
326
|
| reason | |
|
|
327
327
|
|---|---|
|
|
328
328
|
| `BUSY` | the flow is `overlap: skip` and a run is live — send the same message later |
|
|
329
|
-
| `PAUSED` | the
|
|
329
|
+
| `PAUSED` | the project or account is paused |
|
|
330
330
|
| `UNAVAILABLE` | out of budget or funds, or otherwise not taking work |
|
|
331
331
|
| `RATE_LIMITED` | the key's rate limit (`429` from the proxy carries `Retry-After`) |
|
|
332
332
|
| `TOO_MANY_TASKS` | the key has `maxTasks` open |
|
|
@@ -335,7 +335,7 @@ request foldrun cannot take **now** is `-32000` with a foldrun reason:
|
|
|
335
335
|
| `PERMISSION_DENIED` | a key that is not an A2A key (HTTP `403`) |
|
|
336
336
|
| `AGENT_NOT_FOUND` | the flow is not published, not named by the key, or not there — all alike (HTTP `404`) |
|
|
337
337
|
|
|
338
|
-
A task of another key, flow or
|
|
338
|
+
A task of another key, flow or project is `TaskNotFoundError` (`-32001`),
|
|
339
339
|
never "not yours".
|
|
340
340
|
|
|
341
341
|
A run started over A2A goes through the same admission as one started from
|
|
@@ -412,14 +412,14 @@ Ended tasks are kept 90 days.
|
|
|
412
412
|
[`security/published-flow-secret-code`](checks#security-published-flow-secret-code)
|
|
413
413
|
— one that holds a secret and can run code (info once accepted); and
|
|
414
414
|
[`security/published-flow-ungated`](checks#security-published-flow-ungated)
|
|
415
|
-
— a step that acts outside the
|
|
415
|
+
— a step that acts outside the project with no approval or `ask:` before
|
|
416
416
|
it, which any key holder starts. Put a gate (`2!.`) on it, or take a leg
|
|
417
417
|
away.
|
|
418
418
|
- **Left as they are** (FOL-112 N7, N8): one key can hold up to its
|
|
419
419
|
`maxTasks` runs waiting in the approvals queue — `maxTasks` bounds it; give
|
|
420
|
-
a partner's key a small one. A card URL carries the account and
|
|
420
|
+
a partner's key a small one. A card URL carries the account and project
|
|
421
421
|
names (`/a2a/<account>/<ws>/…`) — treat them as disclosed to every key
|
|
422
|
-
holder, and to everyone when `public_card: true`; name a
|
|
422
|
+
holder, and to everyone when `public_card: true`; name a project you
|
|
423
423
|
publish from accordingly.
|
|
424
424
|
- **A public card is metadata only**: the name, description and examples you
|
|
425
425
|
wrote, the endpoint and the auth scheme — never steps, agents or files.
|