Pp Traveloka

<!-- GENERATED FILE — DO NOT EDIT.
     This file is a verbatim mirror of library/travel/traveloka/SKILL.md,
     regenerated post-merge by tools/generate-skills/. Hand-edits here are
     silently overwritten on the next regen. Edit the library/ source instead.
     See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->

Traveloka — Printing Press CLI

Local delivery and scoped session

From the delivered Traveloka project directory, build the local binary with Go 1.26.6 or newer and make this directory visible on PATH:

go build -o traveloka-pp-cli ./cmd/traveloka-pp-cli
export PATH="$PWD:$PATH"
traveloka-pp-cli --version

Continue only when the local binary resolves. Consumer access needs the scoped guest-session workflow in Auth Setup below.

The catalog installer reference below applies after a separate public release. For this local delivery, use the built binary above.

Prerequisites: Install the CLI

This skill drives the traveloka-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:

   npx -y @mvanhorn/printing-press-library install traveloka --cli-only

2. Verify: traveloka-pp-cli --version
3. Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill.

If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead:

go install github.com/mvanhorn/printing-press-library/library/travel/traveloka/cmd/traveloka-pp-cli@latest

If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.

Retrieve Traveloka flight and hotel offers with explicit dates, party, market and currency. Compare selected dates and source-backed snapshots while retaining itinerary details, room policies, price units and canonical booking links.

When to Use This CLI

Use this CLI for explicit-date Traveloka flight and hotel research, detailed room and itinerary inspection, and canonical booking handoff. Use date grids for a small list of acceptable dates and snapshot commands for reproducible comparisons of already retrieved offers.

Anti-triggers

Do not use this CLI for:

• Booking, paying, cancelling or modifying a reservation
• Account/profile changes or loyalty operations
• CAPTCHA bypass, proxy rotation or synthetic clearance tokens
• Tours, buses, packages or other Traveloka products
• Guaranteed final ticket prices or inferred sold-out inventory

Unique Capabilities

These five commands compare explicit dates or retrieved Traveloka offers.

Explicit date comparisons

• flights date-grid — Compare retrieved trip totals across a bounded list of explicit departure and return dates.

  Use this when the traveller can choose among specific dates and needs fresh, comparable offers.

  traveloka-pp-cli flights date-grid --origin SIN --destination CGK --depart-dates 2026-11-20,2026-11-21 --limit 2 --agent

• hotels date-grid — Compare source stay totals for one property across equal-length stays with fixed occupancy.

  Use this to compare specific alternative stays without assuming identical rooms are available.

  traveloka-pp-cli hotels date-grid --property-id 9000000001714 --stays 2027-01-06:2027-01-08,2027-01-13:2027-01-15 --adults 2 --rooms 1 --limit 2 --agent

Retrieved offer comparisons

• flights shortlist — Keep retrieved flight offers that trade price against stops and elapsed time.

  Use this to reduce an existing search to source-backed trade-offs without a subjective score. Offers with missing price, stops or duration remain in unknown_dimensions.

  traveloka-pp-cli flights shortlist --snapshot /private/tmp/traveloka-flight.json --agent

• hotels flexibility — See the stay-price difference between comparable cancellable and nonrefundable room rates.

  Use this when choosing a rate plan for the same room and stay. Unknown or unmatched policies remain unpaired; zero comparable cancellation pairs is a valid result.

  traveloka-pp-cli hotels flexibility --snapshot /private/tmp/traveloka-rooms.json --agent

Retrieval history

• quotes diff — Compare matched-offer price and policy changes between two explicit retrieval snapshots.

  Use this to explain changes between two actual searches without inferring sold-out inventory.

  traveloka-pp-cli quotes diff --before /private/tmp/traveloka-flight-before.json --after /private/tmp/traveloka-flight-after.json --agent

HTTP Transport

This CLI uses Chrome-compatible HTTP transport for browser-facing endpoints. It does not require a resident browser process for normal API calls.

Discovery Signals

This CLI was generated with browser-observed traffic context.

• Capture coverage: 15 API entries from 15 total network entries
• Protocols: rest_json (75% confidence)
• Auth signals: browser-clearance-session
• The delivered source operations are the eight read-only airport, flight and hotel endpoints listed above; shopper commands orchestrate these calls.
• Advanced source commands require explicit operation-specific JSON through --data or a bounded --data-file object (maximum 2 MiB). These inputs contain public search fields and fresh source IDs; cookies and request-token envelopes remain in the private session. --data-file cannot be combined with --data or --stdin.

Command Reference

airport — Advanced read-only Traveloka airport source operations. Clean resolve/flights/hotels commands orchestrate the shopper workflows.

• traveloka-pp-cli airport — Resolve ranked airport/city matches; prefer the resolve command.

flight — Advanced read-only Traveloka flight source operations. Clean resolve/flights/hotels commands orchestrate the shopper workflows.

• traveloka-pp-cli flight initial — Start a dated flight search; prefer flights search for the complete workflow.
• traveloka-pp-cli flight poll — Read incremental flight inventory or selected-outbound return options.
• traveloka-pp-cli flight prefetch — Read source-confirmed prices for selected flight journeys; search preparation only.

hotel — Advanced read-only Traveloka hotel source operations. Clean resolve/flights/hotels commands orchestrate the shopper workflows.

• traveloka-pp-cli hotel catalog — Read dated property inventory; prefer hotels search.
• traveloka-pp-cli hotel features — Read hotel autocomplete feature metadata.
• traveloka-pp-cli hotel lookup — Resolve ranked hotel destinations and properties; prefer resolve.
• traveloka-pp-cli hotel rooms — Read dated room/rate plans; prefer hotels rooms.

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

traveloka-pp-cli which "compare flight dates"

which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match — fall back to --help or use a narrower query. --json (and other machine formats) keep that exit-2 contract and write {"matches":[]} on stdout so agents can inspect the envelope without treating a miss as success.

Recipes

Complete return flights

traveloka-pp-cli flights search --origin SIN --destination CGK --depart 2026-11-20 --return-date 2026-11-27 --adults 1 --limit 3 --agent --select offers,query,retrieved_at

Return both itineraries with authoritative combined totals and the matched shopper context.

Explicit flight dates

traveloka-pp-cli flights date-grid --origin SIN --destination CGK --depart-dates 2026-11-20,2026-11-21 --limit 2 --agent

Run a bounded date comparison with an outcome for every requested cell.

Hotel stay alternatives

traveloka-pp-cli hotels date-grid --property-id 9000000001714 --stays 2027-01-06:2027-01-08,2027-01-13:2027-01-15 --adults 2 --rooms 1 --limit 2 --agent

Keep occupancy fixed while retaining returned room and rate identities.

Same-room cancellation price difference

traveloka-pp-cli hotels flexibility --snapshot /private/tmp/traveloka-rooms.json --agent

Pair explicit policies only when room, stay, meal, occupancy and payment match. Unknown or unmatched rates remain unpaired, and no comparable pairs is a valid result.

Auth Setup

Consumer searches require a legitimate anonymous Traveloka browser session. Run auth capture --launch --timeout 2m with an already installed browser-use backend, or auth import-session with Traveloka-only cookie and captured-request JSON files. auth capture without --launch prints its plan. Capture closes its task guest browser before POST airport validation; ordinary searches replay directly over HTTP. Select the private mode-0600 session file with TRAVELOKA_SESSION_FILE or --session-file. Protection/expiry requires explicit normal-browser refresh. Airport validation proves that endpoint at that time; actual flight/hotel access is checked by the intended query. No partner API key, account change, CAPTCHA solving or global installation is performed.

Run traveloka-pp-cli doctor to verify setup.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color.

Global format flags share one contract on promoted, novel, sync, and --deliver paths:

• --json — one JSON document on stdout (sync progress events go to stderr)

• --compact — keep identity/status/timestamp fields; does not change the document vs stream shape

• --csv / --plain — tabular rows (collection envelopes unwrap to the row array)

• --quiet — one identity value per row, no envelope

• Pipeable — JSON on stdout, errors on stderr

• Filterable — --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:

  traveloka-pp-cli resolve --query Singapore --kind airport --agent --select locations

• Previewable — --dry-run shows the request without sending

• Non-interactive — never prompts, every input is a flag

• Read-only — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests

Paths and state

Agents should treat the CLI's path resolver as part of the runtime contract:

• Use --home <dir> for one invocation, or set TRAVELOKA_HOME=<dir> to relocate all four path kinds under one root.

• Use per-kind env vars only when a specific kind must diverge: TRAVELOKA_CONFIG_DIR, TRAVELOKA_DATA_DIR, TRAVELOKA_STATE_DIR, TRAVELOKA_CACHE_DIR.

• Resolution order is per-kind env var, --home, TRAVELOKA_HOME, XDG (XDG_CONFIG_HOME, XDG_DATA_HOME, XDG_STATE_HOME, XDG_CACHE_HOME), then platform defaults.

• config contains settings like config.toml and profiles. data contains credentials.toml, data.db, cookies, and auth sidecars. state contains persisted queries, jobs, and teach.log. cache contains regenerable HTTP/cache files.

• Traveloka cookie and captured-request secrets live in the private mode-0600 session JSON, defaulting to traveloka-session.json under the resolved state dir. Select another file with --session-file or TRAVELOKA_SESSION_FILE. Generic credential compatibility uses credentials.toml under the data dir; legacy config.toml secrets leave that file on the first generic auth write.

• Run traveloka-pp-cli doctor --fail-on warn to surface path and credential-location warnings. agent-context exposes a schema v4 paths block for agents that need the resolved dirs.

• For MCP, pass relocation through the MCP host config. The MCP binary does not inherit CLI flags:

  {
    "mcpServers": {
      "traveloka": {
        "command": "traveloka-pp-mcp",
        "env": {
          "TRAVELOKA_HOME": "/srv/traveloka"
        }
      }
    }
  }

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use TRAVELOKA_HOME or per-kind vars as durable fleet levers, and use --home only for a single invocation. Relocation is not reversible by unsetting env vars; move files manually before clearing TRAVELOKA_HOME, or doctor will not find credentials left under the former root.

Automatic learning

This CLI ships a self-capturing learning loop. The CLI does its own bookkeeping: every invocation is journaled locally, a failed flag followed by a corrected retry auto-derives a flag_alias candidate, and a teach on a query family without a playbook auto-synthesizes a playbook_candidate from the session's journal. Your job is judgment only: recall first, act on surfaced candidates, teach the final answer, playbook amend when you observe a correction. You never record failures by hand.

Step 1: recall before any discovery

Before list/search/drill commands on a new user question, pass the question as an argv or MCP tool argument to recall --agent. Do not interpolate user-controlled text into a shell command line.

Quoted recall "<question>" breaks on an apostrophe, which is ordinary English. A quoted heredoc breaks when a body line equals the delimiter, and that delimiter is published in these docs. Write the question with a non-shell file-writing tool, then read it back as data:

# Write the question verbatim with your file-writing tool (no shell involved).
# Command substitution on a file only ever yields data — the shell never
# parses the file's bytes as syntax.
QUERY=$(cat /path/to/question.txt)
traveloka-pp-cli recall "$QUERY" --agent

Prefer MCP: pass the question as the tool's query argument. "$QUERY" after a file read is argv-safe; putting the question itself in the command text is not.

The response envelope:

{
  "query": "...",
  "normalized": "<normalized form>",
  "query_entities": ["..."],
  "found": true | false,
  "match_score": 0.0,
  "results": [
    { "resource_id": "...", "resource_type": "...", "venue": "...",
      "confidence": 2, "entity_match": "exact|partial|unknown",
      "source": "taught|preseed|pattern", "warnings": ["..."] }
  ],
  "mismatches": [ /* only when --debug-mismatches */ ],
  "warnings": [ /* top-level */ ],
  "candidates": [
    { "id": 12, "class": "flag_alias | playbook_candidate",
      "summary": "...", "sightings": 3, "last_seen": "...",
      "rationale": "...",
      "next_action": ["<trial command>", "traveloka-pp-cli learnings confirm 12"] }
  ],
  "playbook": {
    "query_family": "...",
    "playbook": {
      "steps": [ { "cmd": "<command with {slot} substitution>", "purpose": "..." } ],
      "entity_slots": ["$ENTITY"],
      "expected_tool_calls": 3
    },
    "slots_resolved": { "$ENTITY": { "token": "<live token>", "canonical": "<canonical>" } },
    "notes": "<workarounds + gotchas for this query family>"
  },
  "notes": "<duplicate surface for non-playbook callers>"
}

Empty-store short-circuit: if the store has no learnings, playbooks, or candidates yet (recall finds nothing and learnings list and learnings candidates are both empty), skip recall for the rest of this session instead of taxing every query; resume recall-first once something has been taught.

Step 2: decision tree

Read candidates, playbook, notes, results[0], and warnings in that order:

if Candidates present (warnings include "candidates_present"):
    -> candidates are try-then-confirm, never facts. Follow each candidate's
       two-step next_action verbatim: run the trial command first, then run
       `learnings confirm <id>` only after the trial verified the behavior.
       Reject a wrong candidate with `learnings reject <id>`.
    -> NEVER re-teach something recall surfaced as a candidate; confirm or
       reject that candidate instead of teaching a duplicate.
    -> candidates ride alongside playbooks and resource hits, not instead of
       them; continue with the branches below after acting on them.

if Playbook present:
    -> READ Playbook.notes verbatim FIRST (workarounds + gotchas the CLI surface doesn't expose)
    -> replay Playbook.steps in order, substituting Playbook.slots_resolved entries
       for the entity slot tokens. If a step's slot is unresolved, fall back to
       discovery for that step only.
    -> the Playbook's expected_tool_calls is a budget; if you find yourself running
       materially more, record the divergence via `traveloka-pp-cli playbook amend`
       at end-of-session.

elif Notes present (no Playbook):
    -> read Notes verbatim before any discovery step; they carry known gotchas
       for this query family even when no structured choreography exists yet.

elif Found AND Results[0].EntityMatch == "exact" AND Results[0].Confidence >= 2:
    -> skip discovery; fetch live data for Results[*].ResourceID in parallel

elif Found AND Results[0].EntityMatch == "partial":
    -> candidate hint, NOT a hit; read the resource title to validate before trusting

elif (any row in Mismatches[] when --debug-mismatches was passed):
    -> treat as cold start; the stored learning is for a different entity
       (different canonical resolved from query_entities)

else:  // Found == false, no playbook, no notes
    -> cold start; run discovery normally; teach the answer afterward (Step 4).
       If the family has no playbook yet, that teach auto-synthesizes a
       playbook candidate from this session's journal - you do not need to
       record one by hand.

Playbook and Notes are orthogonal to the per-resource path. A recall response can carry both a Playbook AND a Results[] hit - use both: the Playbook tells you which choreography to run; the resource hits short-circuit specific steps. Default to skipping mismatches; pass --debug-mismatches only when investigating cold-start surprises.

Candidate judgment details: learnings confirm SIN prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. learnings reject SIN tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; traveloka-pp-cli learnings candidates lists the full open set.

Graceful degradation: if learnings confirm is an unknown command, you are driving an older binary - ignore the candidates guidance and follow the rest of the protocol.

Step 3: always read warnings

• low_confidence: row exists at confidence<2. Treat as a hint, not a skip-discovery hit.
• resource_not_in_store: the local store doesn't have the resource the learning points at. The match validator couldn't classify entities — direct-fetch and re-evaluate.
• cross_alias_match (per-result): the row was taught under a different alias and matched the live query's canonical via entity_lookups (e.g., a "USA" teach satisfying a "United States" recall). Trust the resource_id.
• similar_shape_different_entity:<canonical> (top-level): a structurally matching row exists but its canonical entity differs from the live query's. Treated as cold start; the warning carries the conflicting canonical as a hint, but the row is NOT promoted into Results.
• ambiguous_alias (top-level): a single query entity resolved to multiple canonicals (e.g., "Cards" → Arizona Cardinals + St. Louis Cardinals). Surface the ambiguity from context before committing to a resource.
• candidates_present (top-level): the envelope carries a candidates section. Handle it via the candidates branch in Step 2 before anything else.
• Top-level no_learnings_for_query_family: the table had no rows above the Jaccard floor. Pure cold start.