pantheon-opencode 2.0.0-beta.6 → 2.0.0-rc.1

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.
Files changed (58) hide show
  1. package/AGENTS.global.md +6 -1
  2. package/AGENTS.md +1 -1
  3. package/CHANGELOG.md +45 -0
  4. package/README.md +169 -510
  5. package/README.pt-BR.md +177 -149
  6. package/bin/pantheon-init.mjs +1 -1
  7. package/commands/pantheon-deepwork.md +6 -1
  8. package/commands/pantheon.md +10 -5
  9. package/package.json +1 -1
  10. package/plugin.json +2 -2
  11. package/prompts/orchestrate-with-zeus.prompt.md +82 -290
  12. package/prompts/subtask.prompt.md +1 -1
  13. package/pyproject.toml +1 -1
  14. package/scripts/doctor.mjs +27 -11
  15. package/scripts/hooks/format-multi-language.sh +30 -48
  16. package/scripts/jev-live-probe.mjs +1 -1
  17. package/scripts/release-gates.mjs +19 -5
  18. package/scripts/skill-search.mjs +27 -3
  19. package/scripts/test-opencode-sandbox.sh +44 -15
  20. package/scripts/update.mjs +9 -2
  21. package/skills-lock.json +5 -3
  22. package/src/agents/aphrodite.md +2 -0
  23. package/src/agents/apollo.md +8 -206
  24. package/src/agents/athena.md +25 -29
  25. package/src/agents/hermes.md +3 -1
  26. package/src/agents/mnemosyne.md +1 -1
  27. package/src/agents/nyx.md +1 -1
  28. package/src/agents/prometheus.md +0 -203
  29. package/src/agents/talos.md +2 -0
  30. package/src/agents/themis.md +8 -3
  31. package/src/agents/zeus.md +18 -12
  32. package/src/instructions/memory-protocol.instructions.md +4 -0
  33. package/src/instructions/test-economy.instructions.md +1 -0
  34. package/src/instructions/zeus-council-synthesis.instructions.md +13 -1
  35. package/src/pantheon/pantheon-decision-catalog.ts +8 -0
  36. package/src/pantheon/skill-search-tool.ts +193 -0
  37. package/src/pantheon/tools.ts +2 -0
  38. package/src/plugins/tui/dist/tui.d.ts +12 -2
  39. package/src/plugins/tui/dist/tui.d.ts.map +1 -1
  40. package/src/plugins/tui/dist/tui.js +980 -358
  41. package/src/plugins/tui/dist/tui.js.map +1 -1
  42. package/src/plugins/tui/package-lock.json +2 -2
  43. package/src/plugins/tui/package.json +1 -1
  44. package/src/plugins/tui/src/autonomy-state.ts +1 -1
  45. package/src/plugins/tui/src/context-gauge.ts +64 -5
  46. package/src/plugins/tui/src/decision-router-state.ts +49 -2
  47. package/src/plugins/tui/src/index.tsx +25 -3
  48. package/src/plugins/tui/src/pantheon-settings-state.ts +99 -0
  49. package/src/plugins/tui/src/pantheon-settings.tsx +391 -101
  50. package/src/plugins/tui/src/tui-prefs.ts +161 -9
  51. package/src/plugins/tui/src/update-status.ts +27 -8
  52. package/src/routing.yml +9 -0
  53. package/src/skills/README.md +35 -25
  54. package/src/skills/fast-path-execution/SKILL.md +54 -0
  55. package/src/skills/prompt-refinery/SKILL.md +51 -65
  56. package/src/skills/tdd-with-agents/SKILL.md +22 -10
  57. package/src/skills/test-slicing/SKILL.md +56 -0
  58. package/src/skills/verification-planning/SKILL.md +4 -3
@@ -11,55 +11,37 @@ REPO_ROOT="$(cd -- "$SCRIPT_DIR/../.." && pwd)"
11
11
  # Extracts file_path from Edit/Write or file paths from Bash commands.
12
12
  if [ -p /dev/stdin ]; then
13
13
  STDIN_JSON=$(cat)
14
- TOOL_NAME=$(echo "$STDIN_JSON" | python3 -c "
15
- import sys, json
16
- d = json.load(sys.stdin)
17
- print(d.get('tool_name', ''))
18
- " 2>/dev/null || echo "")
19
- # Normalize to lowercase — opencode sends lowercase (edit/write/bash),
20
- # Claude Code protocol may send capitalized (Edit/Write/Bash).
21
- TOOL_NAME_LOWER=$(echo "$TOOL_NAME" | tr '[:upper:]' '[:lower:]')
22
-
23
- case "$TOOL_NAME_LOWER" in
24
- edit|write)
25
- JSON_PATH=$(echo "$STDIN_JSON" | python3 -c "
26
- import sys, json
27
- d = json.load(sys.stdin)
28
- print(d.get('tool_input', {}).get('file_path', ''))
29
- " 2>/dev/null || echo "")
30
- if [ -n "$JSON_PATH" ]; then
31
- FILE_PATH="$JSON_PATH"
32
- fi
33
- ;;
34
- bash)
35
- COMMAND=$(echo "$STDIN_JSON" | python3 -c "
36
- import sys, json
37
- d = json.load(sys.stdin)
38
- print(d.get('tool_input', {}).get('command', ''))
39
- " 2>/dev/null || echo "")
40
- if [ -n "$COMMAND" ]; then
41
- # Extract first file-like path from bash command (supports relative and quoted paths)
42
- CANDIDATE=$(python3 -c "
43
- import re, shlex, sys
44
- command = sys.argv[1]
14
+ EXTRACTED_PATH=$(python3 -c "
15
+ import sys, json, re, shlex
45
16
  try:
46
- tokens = shlex.split(command)
47
- except ValueError:
48
- tokens = command.split()
49
- path_re = re.compile(r'^([^\\n]+\\.[A-Za-z0-9]+)$')
50
- for token in tokens:
51
- if token.startswith('-'):
52
- continue
53
- if path_re.match(token):
54
- print(token)
55
- break
56
- " "$COMMAND" 2>/dev/null || echo "")
57
- if [ -n "$CANDIDATE" ]; then
58
- FILE_PATH="$CANDIDATE"
59
- fi
60
- fi
61
- ;;
62
- esac
17
+ d = json.load(sys.stdin)
18
+ t = str(d.get('tool_name', '')).lower()
19
+ inp = d.get('tool_input', {})
20
+ if not isinstance(inp, dict):
21
+ inp = {}
22
+ fp = ''
23
+ if t in ('edit', 'write', 'hashline_edit'):
24
+ fp = inp.get('file_path', '') or inp.get('filePath', '') or inp.get('path', '')
25
+ elif t == 'bash':
26
+ cmd = inp.get('command', '')
27
+ if cmd:
28
+ try:
29
+ tokens = shlex.split(cmd)
30
+ except ValueError:
31
+ tokens = cmd.split()
32
+ path_re = re.compile(r'^([^\\n]+\\.[A-Za-z0-9]+)$')
33
+ for tok in tokens:
34
+ if not tok.startswith('-') and path_re.match(tok):
35
+ fp = tok
36
+ break
37
+ if fp:
38
+ print(fp)
39
+ except Exception:
40
+ pass
41
+ " <<< "$STDIN_JSON" 2>/dev/null || echo "")
42
+ if [ -n "$EXTRACTED_PATH" ]; then
43
+ FILE_PATH="$EXTRACTED_PATH"
44
+ fi
63
45
  fi
64
46
 
65
47
  FILE_PATH="${FILE_PATH:-${1:-}}"
@@ -168,7 +168,7 @@ function main(args = process.argv.slice(2)) {
168
168
  rows.push({ state: scenario.state, expect: scenario.expect, got: `ERROR: ${r.raw}` })
169
169
  continue
170
170
  }
171
- const cost = r.data?.cost ?? 0
171
+ const cost = r.data?.data?.cost ?? r.data?.cost ?? 0
172
172
  totalCost += Number(cost) || 0
173
173
  rows.push({ state: scenario.state, expect: scenario.expect, got: answerChoice(r.data), cost })
174
174
  }
@@ -301,8 +301,22 @@ function hostGate(options) {
301
301
  const tarball = singleTarball(options)
302
302
  const matrix = matrixFromEnv()
303
303
  validateMatrix(matrix)
304
+ // PANTHEON_RELEASE_HOST_ONLY lets the workflow run the matrix CONCURRENTLY
305
+ // (one invocation per host — the sandbox roots and ports are already
306
+ // per-index disjoint). The full matrix is validated first; the filter only
307
+ // chooses which rows THIS invocation executes.
308
+ const only = process.env.PANTHEON_RELEASE_HOST_ONLY ?? ''
309
+ const selected = only ? matrix.filter((row) => row.host === only) : matrix
310
+ if (only && selected.length === 0) {
311
+ throw new Error(`PANTHEON_RELEASE_HOST_ONLY="${only}" matches no matrix row`)
312
+ }
304
313
  const checks = []
305
- matrix.forEach((row, index) => {
314
+ selected.forEach((row) => {
315
+ // Port derives from the ORIGINAL matrix index — the concurrent
316
+ // PANTHEON_RELEASE_HOST_ONLY invocations each re-run this gate, and a
317
+ // filtered forEach index would collide both sandboxes on 49380 (field
318
+ // evidence: MCP-handshake timeout on the split-host CI run).
319
+ const matrixIndex = matrix.indexOf(row)
306
320
  const root = join(runnerTemp(), `pantheon-release-host-${safeName(row.host)}`)
307
321
  rmSync(root, { recursive: true, force: true })
308
322
  checks.push(
@@ -311,12 +325,12 @@ function hostGate(options) {
311
325
  'bash',
312
326
  ['scripts/test-opencode-sandbox.sh', '--prepare', '--run', 'v2'],
313
327
  {
314
- env: sandboxEnv(root, row.host, tarball, 49380 + index),
328
+ env: sandboxEnv(root, row.host, tarball, 49380 + matrixIndex),
315
329
  },
316
330
  ),
317
331
  )
318
332
  })
319
- const measuredFamilies = [...new Set(matrix.map((row) => row.line))]
333
+ const measuredFamilies = [...new Set(selected.map((row) => row.line))]
320
334
  const unmeasuredFamilies = SUPPORTED_FAMILIES.filter(
321
335
  (family) => !measuredFamilies.includes(family),
322
336
  )
@@ -513,7 +527,7 @@ function metadataGate(options) {
513
527
  throw new Error(`--version ${options.version} does not match package.json`)
514
528
  }
515
529
  const stable = /^(0|[1-9]\d*)\.(0|[1-9]\d*)\.(0|[1-9]\d*)$/
516
- const beta = /^(0|[1-9]\d*)\.(0|[1-9]\d*)\.(0|[1-9]\d*)-beta\.[1-9]\d*$/
530
+ const beta = /^(0|[1-9]\d*)\.(0|[1-9]\d*)\.(0|[1-9]\d*)-(?:beta|rc)\.[1-9]\d*$/
517
531
  if (!['stable', 'beta'].includes(options.channel)) {
518
532
  throw new Error(`unknown channel ${options.channel}`)
519
533
  }
@@ -521,7 +535,7 @@ function metadataGate(options) {
521
535
  throw new Error(`stable channel requires X.Y.Z, found ${options.version}`)
522
536
  }
523
537
  if (options.channel === 'beta' && !beta.test(options.version)) {
524
- throw new Error(`beta channel requires X.Y.Z-beta.N, found ${options.version}`)
538
+ throw new Error(`beta channel requires X.Y.Z-beta.N or X.Y.Z-rc.N, found ${options.version}`)
525
539
  }
526
540
  const checks = [
527
541
  run('version-manifests', 'node', ['scripts/version-check.mjs']),
@@ -23,7 +23,7 @@
23
23
  import { spawnSync } from 'node:child_process'
24
24
  import { pathToFileURL } from 'node:url'
25
25
 
26
- const FIND_TIMEOUT_MS = 60_000
26
+ const FIND_TIMEOUT_MS = 15_000
27
27
  const DEFAULT_LIMIT = 5
28
28
  /** SGR escape sequences are matched via the ESC codepoint (lint-clean, same semantics). */
29
29
  const ANSI_SGR = new RegExp(`${String.fromCharCode(27)}\\[[0-9;]*m`, 'g')
@@ -119,7 +119,7 @@ export function searchSkills(query, { limit = DEFAULT_LIMIT, owner, spawn = spaw
119
119
  return { ok: true, entries, raw, emptyIsAmbiguous: false }
120
120
  }
121
121
 
122
- const GITHUB_TIMEOUT_MS = 30_000
122
+ const GITHUB_TIMEOUT_MS = 10_000
123
123
  const ANTHROPIC_SKILLS_REPO = 'anthropics/skills'
124
124
 
125
125
  /**
@@ -220,10 +220,26 @@ export function searchGithubSkills(query, { limit = DEFAULT_LIMIT, spawn = spawn
220
220
  */
221
221
  export const SKILL_SEARCH_SOURCES = Object.freeze(['anthropic', 'skills-sh', 'github'])
222
222
 
223
+ const SEARCH_CACHE = new Map()
224
+ const CACHE_TTL_MS = 24 * 60 * 60 * 1000 // 24 hours
225
+
223
226
  export function searchSkillSources(
224
227
  query,
225
228
  { limit = DEFAULT_LIMIT, owner, sources = SKILL_SEARCH_SOURCES, spawn = spawnSync } = {},
226
229
  ) {
230
+ const cacheKey = JSON.stringify({
231
+ query: String(query).toLowerCase().trim(),
232
+ limit,
233
+ owner,
234
+ sources,
235
+ })
236
+ if (spawn === spawnSync && SEARCH_CACHE.has(cacheKey)) {
237
+ const cached = SEARCH_CACHE.get(cacheKey)
238
+ if (Date.now() - cached.timestamp < CACHE_TTL_MS) {
239
+ return cached.result
240
+ }
241
+ }
242
+
227
243
  const perTier = Math.max(1, Math.ceil(limit / sources.length))
228
244
  const out = []
229
245
  const failures = []
@@ -259,7 +275,15 @@ export function searchSkillSources(
259
275
  if (tier !== 0) return tier
260
276
  return installsWeight(left) - installsWeight(right)
261
277
  })
262
- return { ok: failures.length < sources.length, entries: out.slice(0, limit), failures }
278
+ const finalResult = {
279
+ ok: failures.length < sources.length,
280
+ entries: out.slice(0, limit),
281
+ failures,
282
+ }
283
+ if (spawn === spawnSync && finalResult.ok) {
284
+ SEARCH_CACHE.set(cacheKey, { timestamp: Date.now(), result: finalResult })
285
+ }
286
+ return finalResult
263
287
  }
264
288
 
265
289
  function main(args = process.argv.slice(2)) {
@@ -310,7 +310,7 @@ wait_for_v2_mcp_registrations() {
310
310
  print_v2_diagnostics
311
311
  return 1
312
312
  fi
313
- if SERVICE_LOG="$V2_SERVER_LOG" RUNTIME_DIR="$runtime_dir" MCP_PYTHON="$python_bin" \
313
+ if SERVICE_LOG="$V2_SERVER_LOG" RUNTIME_DIR="$runtime_dir" MCP_PYTHON="$python_bin" RUNTIME_LOG="$LOG_PATH" \
314
314
  python3 - <<'PY'
315
315
  import os
316
316
  import re
@@ -319,7 +319,7 @@ from pathlib import Path
319
319
  try:
320
320
  log = Path(os.environ["SERVICE_LOG"]).read_text(encoding="utf-8")
321
321
  except OSError:
322
- raise SystemExit(1)
322
+ log = ""
323
323
  expected = {
324
324
  "code_mode.py",
325
325
  "memory_mcp.py",
@@ -335,8 +335,8 @@ pattern = re.compile(
335
335
  re.DOTALL,
336
336
  )
337
337
  records = list(pattern.finditer(log))
338
- runtime_dir = os.environ["RUNTIME_DIR"]
339
- python_bin = os.environ["MCP_PYTHON"]
338
+ runtime_dir = os.environ.get("RUNTIME_DIR", "")
339
+ python_bin = os.environ.get("MCP_PYTHON", "")
340
340
  registered = set()
341
341
  for record in records:
342
342
  command = record.group("command")
@@ -345,11 +345,24 @@ for record in records:
345
345
  if command != python_bin or cwd != runtime_dir or script not in expected:
346
346
  raise SystemExit(1)
347
347
  registered.add(script)
348
- # OpenCode can initialize the same configured workspace more than once during
349
- # service startup and `mcp list`. Count the logical server set here; the later
350
- # `mcp list` assertion still requires exactly five connected MCP names.
351
- if registered != expected:
352
- raise SystemExit(1)
348
+ if registered == expected:
349
+ raise SystemExit(0)
350
+ runtime_log_path = os.environ.get("RUNTIME_LOG")
351
+ if runtime_log_path and Path(runtime_log_path).is_file():
352
+ try:
353
+ rlog = Path(runtime_log_path).read_text(encoding="utf-8")
354
+ expected_servers = {
355
+ "pantheon-code-mode",
356
+ "pantheon-memory",
357
+ "pantheon-persistence",
358
+ "pantheon-resources",
359
+ "pantheon-vision",
360
+ }
361
+ if all(f'message="mcp connected" server={s}' in rlog for s in expected_servers):
362
+ raise SystemExit(0)
363
+ except OSError:
364
+ pass
365
+ raise SystemExit(1)
353
366
  PY
354
367
  then
355
368
  return 0
@@ -717,7 +730,7 @@ wait_for_v2_mcp_registrations() {
717
730
  print_v2_diagnostics
718
731
  return 1
719
732
  fi
720
- if SERVICE_LOG="$V2_SERVER_LOG" RUNTIME_DIR="$runtime_dir" MCP_PYTHON="$python_bin" \
733
+ if SERVICE_LOG="$V2_SERVER_LOG" RUNTIME_DIR="$runtime_dir" MCP_PYTHON="$python_bin" RUNTIME_LOG="$LOG_PATH" \
721
734
  python3 - <<'PY'
722
735
  import os
723
736
  import re
@@ -726,7 +739,7 @@ from pathlib import Path
726
739
  try:
727
740
  log = Path(os.environ["SERVICE_LOG"]).read_text(encoding="utf-8")
728
741
  except OSError:
729
- raise SystemExit(1)
742
+ log = ""
730
743
  expected = {
731
744
  "code_mode.py",
732
745
  "memory_mcp.py",
@@ -742,8 +755,8 @@ pattern = re.compile(
742
755
  re.DOTALL,
743
756
  )
744
757
  records = list(pattern.finditer(log))
745
- runtime_dir = os.environ["RUNTIME_DIR"]
746
- python_bin = os.environ["MCP_PYTHON"]
758
+ runtime_dir = os.environ.get("RUNTIME_DIR", "")
759
+ python_bin = os.environ.get("MCP_PYTHON", "")
747
760
  registered = set()
748
761
  for record in records:
749
762
  command = record.group("command")
@@ -752,8 +765,24 @@ for record in records:
752
765
  if command != python_bin or cwd != runtime_dir or script not in expected:
753
766
  raise SystemExit(1)
754
767
  registered.add(script)
755
- if len(records) != len(expected) or registered != expected:
756
- raise SystemExit(1)
768
+ if registered == expected:
769
+ raise SystemExit(0)
770
+ runtime_log_path = os.environ.get("RUNTIME_LOG")
771
+ if runtime_log_path and Path(runtime_log_path).is_file():
772
+ try:
773
+ rlog = Path(runtime_log_path).read_text(encoding="utf-8")
774
+ expected_servers = {
775
+ "pantheon-code-mode",
776
+ "pantheon-memory",
777
+ "pantheon-persistence",
778
+ "pantheon-resources",
779
+ "pantheon-vision",
780
+ }
781
+ if all(f'message="mcp connected" server={s}' in rlog for s in expected_servers):
782
+ raise SystemExit(0)
783
+ except OSError:
784
+ pass
785
+ raise SystemExit(1)
757
786
  PY
758
787
  then
759
788
  return 0
@@ -171,9 +171,16 @@ export function runUpdate(
171
171
  }
172
172
 
173
173
  const globalEntry = path.join(refreshedPackageRoot, 'bin', 'pantheon-init.mjs')
174
+ const forwardedFlags = []
175
+ if (args.includes('--project')) forwardedFlags.push('--project')
176
+ if (args.includes('--no-mcp')) forwardedFlags.push('--no-mcp')
177
+ if (args.includes('--verbose')) forwardedFlags.push('--verbose')
178
+
174
179
  const init = refresh
175
- ? refresh(globalEntry)
176
- : spawnSync(execPath, [globalEntry, 'init', '--yes', '--headless'], { stdio: 'inherit' })
180
+ ? refresh(globalEntry, forwardedFlags)
181
+ : spawnSync(execPath, [globalEntry, 'init', '--yes', '--headless', ...forwardedFlags], {
182
+ stdio: 'inherit',
183
+ })
177
184
  if (init.status !== 0 || init.error) {
178
185
  console.error(
179
186
  '⚠️ Updated, but the config refresh did not complete — run `npx pantheon-opencode init` manually.',
package/skills-lock.json CHANGED
@@ -10,6 +10,7 @@
10
10
  "src/skills/code-review-checklist/SKILL.md": "cdca3dbd7393cd8b379297be8bf68d456e7217b0238eaeea13b35a96d553414f",
11
11
  "src/skills/codemap/SKILL.md": "d21b3fa66b931b29dcf1ec0f0fcf1ec28514642a9f33f96e4b2901a0be74c72d",
12
12
  "src/skills/context-compression/SKILL.md": "4d8368309ec72fefac69ad5cddd43650647d0bc684b6f8bf3cacc004edb56ef5",
13
+ "src/skills/fast-path-execution/SKILL.md": "040bb97ac5d930dcee47d5d0e2fc1ef637a4762998990475d876ec7f17977c69",
13
14
  "src/skills/git-workflow-and-versioning/SKILL.md": "685a94041f1b4ce2a430301f517b89102055696267c369a7e8fb191606659276",
14
15
  "src/skills/incremental-implementation/SKILL.md": "7065ddb45da3c6b6751de07f290e92e6cb072e949a2e3aaae13ee7762f0a70fc",
15
16
  "src/skills/instruction-forge/references/agents-md-doctrine.md": "23623cc40e830ba5f2f11b7b005e85b3f4d260428f1c31cb9840e7b9baa81360",
@@ -22,7 +23,7 @@
22
23
  "src/skills/memory-bank/references/storage-model.md": "728a9e5f2055ce0f74c759405072a6fe57f65587bdb7b9e5e7fa90b60528b085",
23
24
  "src/skills/memory-bank/references/structure-and-frequency.md": "09caedf905870c688401a2e58b2776a9c6187fe724c576019c58c3b80fe1b98f",
24
25
  "src/skills/memory-bank/SKILL.md": "047b3049c27e908b1d79afb14f79336e32f775385ba23956771166d445944f2f",
25
- "src/skills/prompt-refinery/SKILL.md": "b8c5860cd70308144bd7e6bf65e4ddb47c7f29818316fe3ddc6f3886644a7b0a",
26
+ "src/skills/prompt-refinery/SKILL.md": "1efbe6700dbcf357c1eab38662ff9572b163abb262915ce615694829682922c5",
26
27
  "src/skills/reflect/SKILL.md": "297c374f1fbc8e15d3848f51e811e0614d4a008c7d0e1daf88bbb240d605b8a8",
27
28
  "src/skills/security-hardening/SKILL.md": "6d637e122421f7bc3b751f04854ad343a5a5d35249458bc8939233138fd3f20d",
28
29
  "src/skills/session-goal/references/goal-format.md": "071f6f8f12cfbc26d4703cd5f34f839f91e586a3b969bf5f81a74b961c254a83",
@@ -32,8 +33,9 @@
32
33
  "src/skills/spec-driven-development/SKILL.md": "ccfbc0c32116a1d144f5c12a4187c053322ed31625a622a58c59739a57a86743",
33
34
  "src/skills/tdd-with-agents/references/advanced-testing-patterns.md": "4aac82748bb670a61d67732168f8a265d5e66895a9183029e3da03de8e024788",
34
35
  "src/skills/tdd-with-agents/references/testing-by-layer.md": "545291301661e57d846b2db2acca1edb1219a102dce4aad7e0c3cc1a250b570a",
35
- "src/skills/tdd-with-agents/SKILL.md": "10ad9b489df22544d5697ec69dfeaa2c83b565787979bea6e88781556caacd8c",
36
- "src/skills/verification-planning/SKILL.md": "14186446ef51e1ba2c87b337e8d5f86e566d805156ab21fba2a75f8c4a99df3f",
36
+ "src/skills/tdd-with-agents/SKILL.md": "825d5e5eadbe487db382918a2181a4a993d8f722c38bd7f104f89b00004d6223",
37
+ "src/skills/test-slicing/SKILL.md": "ff70cddc66261049250b82f7aeabbfd6bcd00f9abe34cc8d5f20aa35333b1590",
38
+ "src/skills/verification-planning/SKILL.md": "6a3c6cb5bd5076862d369885bf0b3ba086b625495fe7a42f3f5116d07b470f3e",
37
39
  "src/skills/visual-review-pipeline/references/findings-schema.md": "776511757c0d8387fab232fced8ac9ce031a03f62b6ca539e3c38b0d45035c8e",
38
40
  "src/skills/visual-review-pipeline/references/workflow-steps.md": "1f763f39d9218263bfb10f575d739d9eb62d89cd9f00d38c21cd729b078b44c8",
39
41
  "src/skills/visual-review-pipeline/SKILL.md": "7f66f0426868535db891bccd8e21c719b7dcbb16625ea75edbf436ccb1896ac1",
@@ -16,11 +16,13 @@ permission:
16
16
  "*": deny
17
17
  temperature: 0.3
18
18
  skills:
19
+ - fast-path-execution
19
20
  - incremental-implementation
20
21
  - loop-engineering
21
22
  - reflect
22
23
  - simplify
23
24
  - tdd-with-agents
25
+ - test-slicing
24
26
  - visual-review-pipeline
25
27
  - worktrees
26
28
  mcp_tools:
@@ -30,7 +30,7 @@ mcp_tools:
30
30
  pantheon-memory: [memory_search, code_query, code_neighbors]
31
31
  ---
32
32
 
33
- ## When NOT to Use Apollo
33
+ ## When NOT to Use Apollo
34
34
  - When you already know the exact file path — read it directly
35
35
  - When you need to modify files — Apollo is read-only
36
36
  - When the search can be done with a simple grep/glob — use direct tools instead
@@ -61,209 +61,6 @@ mcp_tools:
61
61
 
62
62
  ## Core Capabilities
63
63
 
64
- ### 1. **Test-Driven Development**
65
- See `skill: tdd-with-agents` for the full TDD cycle.
66
-
67
- ### 2. **Context Conservation**
68
- - Focus ONLY on files you're modifying
69
- - Don't re-read entire project architecture
70
- - Return summaries of your changes
71
- - Ask the Orchestrator only when missing context or a material choice blocks safe progress
72
-
73
- ### 3. **Proper Handoffs**
74
- - Use a supplied plan when one exists; do not require one for bounded work
75
- - Ask a clarifying question only when ambiguity blocks a safe implementation
76
- - Return clear, structured results
77
- - Report readiness for next phase
78
-
79
- ### 4. **Parallel Execution Mode**
80
- - Zeus may dispatch @aphrodite and @demeter in parallel on independent scopes; a Hermes child session works only its assigned scope and reports coordination needs to Zeus
81
- - Your scope: backend files only (routers, services, tests)
82
- - Signal clearly when done; preserve Themis review for security/auth, data/schema, and material changes
83
- - Do NOT wait for other workers to finish before starting your work
84
-
85
- ## Search Policy
86
- - Investigate beyond the assigned context only when necessary to resolve the task or when broader discovery materially reduces risk; verify changed behavior proportionally to its scope and risk, using focused checks for bounded changes and broader checks only when integration boundaries or risk warrant them.
87
- - You do NOT perform web searches directly
88
- - Inspect relevant files directly; only a root Hermes session may delegate discovery to @apollo when broad/unfamiliar discovery materially reduces risk. A child session has a parent and must not dispatch another Pantheon agent; report wider discovery needs to Zeus.
89
- - For library documentation → Context7 is allowed for library documentation (FastAPI, SQLAlchemy, Pydantic)
90
- - For web research → a root Hermes may delegate to @apollo; a child session asks Zeus to route it
91
- - Only use `webfetch` for specific URLs you already know (not for general search)
92
-
93
- ## MCP Security: PostgreSQL
94
-
95
- > **Risk level: HIGH** — Read-only query capability, but injection still possible.
96
-
97
- ### Parameterized Query Mandate
98
- - **NEVER** use f-strings, `format()`, or `+` concatenation for SQL query construction
99
- - **ALWAYS** use parameterized queries:
100
- ```python
101
- # [OK] SAFE — parameterized
102
- psql_query("SELECT * FROM products WHERE id = $1", [product_id])
103
-
104
- # [FAIL] UNSAFE — string interpolation
105
- psql_query(f"SELECT * FROM products WHERE id = {product_id}")
106
- ```
107
-
108
- ### Read-Only Constraint
109
- - `postgresql_query` for SELECT only — NEVER for DDL, INSERT, UPDATE, DELETE, or EXECUTE
110
- - If write access is needed, ask Zeus to route the database work to **@demeter** (they have `postgresql_execute` with stricter controls); a child session does not dispatch it directly.
111
-
112
- ### Verify Query Before Execution
113
- - Check the SQL string for string interpolation patterns (`f"`, `.format(`, `+`)
114
- - If any found, rewrite with parameterized syntax before executing
115
-
116
- ## Core Responsibilities
117
-
118
- ### 1. FastAPI Endpoints & Routers
119
- - Create async endpoints with proper HTTP methods (GET, POST, PUT, PATCH, DELETE)
120
- - Implement routers for domain logic (auth, media, products, offers, etc.)
121
- - Use Pydantic schemas for request/response validation
122
- - Apply dependency injection for database sessions, authentication
123
- - Implement pagination, filtering, sorting in list endpoints
124
-
125
- ### 2. Service Layer Architecture
126
- - Build service classes with business logic isolated from routers
127
- - Implement service methods: `create`, `read`, `update`, `delete`, `list`, `search`
128
- - Use async/await for I/O operations (database, external APIs)
129
- - Handle errors gracefully with FastAPI HTTPException
130
- - Integrate with external services (Gemini AI, R2 storage, Telegram)
131
-
132
- ### 3. Integration Points
133
- - **Database**: SQLAlchemy async sessions via dependency injection
134
- - **Cache**: Caching layer (e.g., Redis) for session management and API caching
135
- - **Storage**: Object storage for media uploads (e.g., S3, R2, GCS)
136
- - **External APIs**: REST/gRPC integrations (AI services, payment, messaging, etc.)
137
-
138
- ### 4. Security & Performance
139
- - JWT authentication with httpOnly cookies
140
- - CSRF protection via middleware
141
- - Rate limiting for public endpoints
142
- - Input validation and sanitization
143
- - Query optimization (avoid N+1 problems)
144
- - Async operations for concurrent requests
145
-
146
- ## Project Context
147
-
148
- > **Adopt this agent for your product:** Replace this section with your project's specific routers, services, and models. Store durable reusable facts through `pantheon-memory` when warranted and when the tool is granted, or reference project documentation under `.pantheon/memory-bank/`, which is read on demand rather than auto-loaded.
149
-
150
- ## Implementation Process
151
-
152
- When creating a new feature:
153
-
154
- 1. **Router First**: Create endpoint in appropriate router file
155
- ```python
156
- @router.post("", response_model=ResponseSchema)
157
- async def create_item(
158
- data: CreateSchema,
159
- db: AsyncSession = Depends(get_db),
160
- current_user: User = Depends(get_current_user)
161
- ):
162
- service = ItemService(db)
163
- return await service.create(data)
164
- ```
165
-
166
- 2. **Service Layer**: Implement business logic
167
- ```python
168
- class ItemService:
169
- def __init__(self, db: AsyncSession):
170
- self.db = db
171
-
172
- async def create(self, data: CreateSchema) -> Item:
173
- # Validation, business logic, persistence
174
- pass
175
- ```
176
-
177
- 3. **Error Handling**: Use FastAPI exceptions
178
- ```python
179
- if not item:
180
- raise HTTPException(status_code=404, detail="Item not found")
181
- ```
182
-
183
- 4. **Testing**: Write unit tests in `backend/tests/`
184
-
185
- ## Code Quality Standards
186
-
187
- > See instructions/backend-standards.instructions.md for the complete backend standards.
188
-
189
- ## Modern Python & Dependency Hygiene
190
-
191
- ### Obsolete Library Detection
192
- When adding or changing dependencies, check for obsolete/deprecated libraries and audit the affected dependency set. Do not run dependency-audit tools for an unrelated one-line or documentation fix:
193
-
194
- ```bash
195
- # Detect stdlib backports, zombie shims, deprecated packages
196
- pip install dep-audit && dep-audit . --exit-code
197
-
198
- # Scan for known CVEs in dependencies
199
- pip-audit -r requirements.txt
200
- ```
201
-
202
- **Common Python stdlib replacements (use these instead of third-party):**
203
- | Obsolete | Modern stdlib | Since |
204
- |----------|--------------|-------|
205
- | `pytz` | `zoneinfo.ZoneInfo` | Python 3.9 |
206
- | `tomli` | `tomllib` | Python 3.11 |
207
- | `six`, `future` | native Python 3 syntax | Python 3.0+ |
208
- | `dataclasses` backport | `dataclasses` stdlib | Python 3.7+ |
209
- | `typing_extensions` (most) | `typing` stdlib | Python 3.9-3.11+ |
210
- | `importlib_metadata` | `importlib.metadata` | Python 3.8+ |
211
- | `contextlib2` | `contextlib` stdlib | Python 3.7+ |
212
- | `mock` (PyPI) | `unittest.mock` | Python 3.3+ |
213
-
214
- ### LTS & Modern Version Policy
215
- - Always pin dependencies to **LTS-compatible versions**
216
- - Prefer latest **stable major version**: FastAPI ≥0.110, Pydantic ≥2.7, SQLAlchemy ≥2.0
217
- - Never use EOL Python versions (3.8 and below are unsupported)
218
- - Check `pip-audit` output to ensure no vulnerable deps
219
- - Use `ruff check --select UP` to auto-migrate to modern Python syntax
220
- - Prefer `pyproject.toml` over `setup.py` for project metadata
221
-
222
- ## Documentation Policy
223
-
224
- Use artifact-management only for planned multi-phase or materially risky work. A bounded fix needs no IMPL artifact; return the structured summary instead. Never create permanent ADRs directly.
225
-
226
- **Artifact Protocol Reference:** `skill: artifact-management`
227
-
228
- ## Pre-Implementation Recall
229
- Use supplied memory/ADR context when relevant. Do not block a bounded fix on a separate memory-bank recall or repeat searches that do not change the implementation.
230
-
231
- ## When to Delegate
232
-
233
- - **@apollo**: Only a root Hermes session may dispatch Apollo for broad/unfamiliar discovery that materially reduces risk; a child session reports that need to Zeus and inspects assigned context directly otherwise
234
- - **@mnemosyne**: For permanent ADRs or substantial memory-bank artifacts, not routine summaries
235
- - **@themis**: Required for auth/security, data/schema, and material changes; request required review through Zeus, who dispatches Themis from root. Do not create a separate review phase for a trivial isolated fix
236
- - **@aphrodite / @demeter / **: Route through **Zeus** — Hermes cannot directly invoke these agents
237
-
238
- ## Output Format
239
-
240
- When completing a task, provide:
241
- - [OK] Complete router code with all endpoints
242
- - [OK] Service implementation with business logic
243
- - [OK] Pydantic schemas (request/response)
244
- - [OK] Error handling and validation
245
- - [OK] Docstrings explaining functionality
246
- - [OK] Example curl commands for testing
247
- - [OK] Unit test skeleton (optional)
248
-
249
- ---
250
-
251
- **Philosophy**: Clean code, clear error messages, proper async patterns, thorough testing.
252
-
253
- ## Verification Tiers (match the change, not a ritual)
254
-
255
- - **Small bounded fix** (typo, config, copy, single-function tweak): make the change, run the one targeted test or command that proves it, report. No RED→GREEN→REFACTOR ceremony, no extra discovery passes.
256
- - **Material change** (new endpoint, schema, service, auth, public behavior): full TDD cycle via `skill: tdd-with-agents`, then the Themis handoff.
257
- - Auto-continue through the chosen tier for authorized work; stop for required Themis review; stop and diagnose when tests fail unexpectedly; no partial results.
258
-
259
- ## Skills
260
- Implementação: `tdd-with-agents`, `incremental-implementation`, `code-review-checklist`, `git-workflow-and-versioning`
261
-
262
-
263
- - **Code-mode / infrastructure reads** — cheap and on demand; never for decisions the ladder already answers.
264
-
265
- ## Core Capabilities
266
-
267
64
  ### 1. Codebase Discovery
268
65
  - Use direct targeted searches for straightforward questions; batch independent searches only when the discovery scope benefits from it
269
66
  - Search for files, patterns, symbols, imports
@@ -282,13 +79,18 @@ Implementação: `tdd-with-agents`, `incremental-implementation`, `code-review-c
282
79
  - Identify architecture patterns and tech debt signals
283
80
  - Return hierarchical summaries (60-70% token savings vs raw file reads)
284
81
 
285
- ## TOOLS NOT AVAILABLE
82
+ ## TOOLS NOT AVAILABLE
286
83
  - bash - forbidden (cannot run commands)
287
84
  - edit - forbidden (read-only agent)
288
85
  - Web search by default - no search MCP is bundled or pre-configured. Use one
289
86
  ONLY if the user's own config exposes it; otherwise state that external search
290
87
  was unavailable instead of improvising.
291
88
 
89
+ ## Pragmatism and Non-Destructive Inspection
90
+ - Diagnostic operations (reading files, targeted webfetch for documentation/status, symbol search) are inherently safe and non-destructive.
91
+ - Do not debate hypothetical side-effects (e.g. click counting, redirect chains) or invent reasons to avoid inspecting what was requested.
92
+ - Focus on returning objective findings directly, without paralysis over capabilities.
93
+
292
94
  ## MCP Security
293
95
  - Never embed credentials in URLs (grep for token=, key=, secret=)
294
96
  - Use environment variables for auth
@@ -302,7 +104,7 @@ Return structured findings with:
302
104
  - **summary:** What was found
303
105
  - **confidence:** high | medium | low
304
106
 
305
- ## Auto-Continue (Embedded: Discovery)
107
+ ## Auto-Continue (Embedded: Discovery)
306
108
 
307
109
  - Continue through independent discovery queries when more evidence is needed; use only the breadth justified by the request
308
110
  - Partial results OK on timeout — return whatever is found