phronomy 0.35.1 → 0.35.2
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.
- checksums.yaml +4 -4
- data/CHANGELOG.md +32 -0
- data/README.md +2 -2
- data/SECURITY.md +1 -1
- data/docs/execution-boundaries-preview.md +23 -4
- data/docs/runtime-and-concurrency.md +25 -3
- data/docs/shared-state-sharing.md +17 -7
- data/lib/phronomy/engine/runtime/shutdown_result.rb +2 -1
- data/lib/phronomy/engine/runtime/timer_queue.rb +41 -1
- data/lib/phronomy/engine/runtime/timer_service.rb +14 -1
- data/lib/phronomy/engine/runtime.rb +24 -10
- data/lib/phronomy/multi_agent/shared_state.rb +5 -5
- data/lib/phronomy/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: fd730052ab22e489edccab8719c26d5f25e66f15d798a35e7f6dd35ce2864033
|
|
4
|
+
data.tar.gz: 31f924ae82bfc4206ffe151396c9c6ffed809a68ede9f968a5b6c4607c4d2629
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 8e91585690b00f9566db0143fb56dd34961658c4b3c8c86c0131379b5922dc96458aecadd56f5a6323e36cb5f0041ff2c44030449ca38b26dcdd7d048f2ecc0c
|
|
7
|
+
data.tar.gz: 01cf02a781f981c892c1e4d4b64e2d3b66c9aed0698a55f2546d2afd5aec9bf4107afc70f39a7a0b4a862662037b34bd1f086453e466b7a10d009bb7003dc65f
|
data/CHANGELOG.md
CHANGED
|
@@ -12,6 +12,38 @@ Release history for 0.14.0 and earlier is archived in
|
|
|
12
12
|
|
|
13
13
|
## [Unreleased]
|
|
14
14
|
|
|
15
|
+
## [0.35.2] - 2026-11-18
|
|
16
|
+
|
|
17
|
+
### Fixed
|
|
18
|
+
|
|
19
|
+
- Release completed member Agents in default SharedState coordination through
|
|
20
|
+
the same lifecycle handling used by custom sharing. Normal approval waits stay
|
|
21
|
+
live; invocation and release failures retain their original causes and the
|
|
22
|
+
member handle when cleanup needs attention.
|
|
23
|
+
- Keep Runtime deadline notifications active while accepted work drains during
|
|
24
|
+
shutdown, including queued Blocking operations and standalone fan-out results.
|
|
25
|
+
A delayed worker result cannot win merely because its timer driver stopped
|
|
26
|
+
before the worker pool drained.
|
|
27
|
+
|
|
28
|
+
### Changed
|
|
29
|
+
|
|
30
|
+
- Report incomplete Runtime cleanup if the finite shutdown budget expires with
|
|
31
|
+
accepted timer callbacks still pending. No callback fires early to simulate
|
|
32
|
+
cancellation, and no worker thread is forcibly interrupted. Default Runtime
|
|
33
|
+
replacement still requires complete cleanup.
|
|
34
|
+
- Reconcile P5 progress with the published v0.35.0 and examples acceptance, and
|
|
35
|
+
identify the old execution-boundary proposal as historical documentation.
|
|
36
|
+
|
|
37
|
+
### Compatibility and verification
|
|
38
|
+
|
|
39
|
+
- Public signatures, dependency requirements and current saved formats are
|
|
40
|
+
unchanged. The existing `cleanup_complete?` predicate now remains false when
|
|
41
|
+
the shutdown budget leaves accepted timer callbacks unfinished, so a default
|
|
42
|
+
Runtime cannot be replaced after incomplete cleanup.
|
|
43
|
+
- This core release does not claim new published-gem examples, live LLM or SQL
|
|
44
|
+
acceptance, or resolution of the previously observed LM Studio/gpt-oss
|
|
45
|
+
PEG-format failure root cause. Those checks remain separate follow-up work.
|
|
46
|
+
|
|
15
47
|
## [0.35.1] - 2026-11-18
|
|
16
48
|
|
|
17
49
|
### Fixed
|
data/README.md
CHANGED
|
@@ -37,7 +37,7 @@ tracking `main` directly.
|
|
|
37
37
|
|
|
38
38
|
See [Features and Application Programming Interface (API) stability](docs/features.md) for the full feature matrix.
|
|
39
39
|
|
|
40
|
-
The following table describes the application APIs available in v0.35.
|
|
40
|
+
The following table describes the application APIs available in v0.35.2.
|
|
41
41
|
The public persistence resource catalogs are available starting with v0.35.0.
|
|
42
42
|
The sharing, Tool composition and Context budgeting operations remain
|
|
43
43
|
Experimental; their introduction version is shown below.
|
|
@@ -60,7 +60,7 @@ the current saved representation.
|
|
|
60
60
|
| `Persistence::Migration::InitialFormatMigration` | Removed (v0.34.0) | The pre-S3 conversion API is retired without a replacement. Current domain codecs and the separate Unit4 snapshot migration remain. [Legacy-format cleanup](docs/migrations/legacy-format-removal.md) |
|
|
61
61
|
| `Context::ContextPolicyInput#input_token_limit / #with_input_token_limit` and protected `ContextPolicy#estimate_tokens` | Experimental (since v0.33.0) | Inspect and constrain selection budgets and estimate candidate content through Context-owned operations. [Policy budgeting](docs/context-policy-budgeting.md) |
|
|
62
62
|
| `Agent::Base.with_tools(definitions, id:, version:)` | Experimental (since v0.33.0) | Derive an Agent class with a complete replacement Tool map and explicit definition identity while preserving Phronomy authoring settings and filters. [Tool composition](docs/shared-state-sharing.md#deriving-an-agent-with-a-complete-tool-set) |
|
|
63
|
-
| `MultiAgent::SharedState.sharing(provider, id:, version:)`, `SharedState::Binding` and `SharedState::MemberLifecycleError` | Experimental (since v0.33.0) |
|
|
63
|
+
| `MultiAgent::SharedState.sharing(provider, id:, version:)`, `SharedState::Binding` and `SharedState::MemberLifecycleError` | Experimental (since v0.33.0) | Sequential coordination releases its terminal member Agents in both default and custom modes; an optional invocation-scoped provider supplies application-owned data and Tools. [Sharing and member lifetime contract](docs/shared-state-sharing.md) |
|
|
64
64
|
| `Tool::Base#approval_display(arguments:, facts:)` | Beta (since v0.33.0) | The Tool selects the arguments and derived facts a person can see in an approval request. [Approval display](docs/runtime-and-concurrency.md#tool-approval-display) |
|
|
65
65
|
| `Runtime#shutdown` result predicates `cleanup_complete?` and `clean?` | Beta | Check resource release with `cleanup_complete?`; `clean?` additionally requires a graceful shutdown. The obsolete `success?` alias is removed in v0.34.0. [Cleanup migration](docs/migrations/cleanup-audit.md#runtime-cleanup-completion) |
|
|
66
66
|
| `Phronomy::EventLoopReentrancyError` | Beta | Raised when a synchronous operation would block the EventLoop control thread. The obsolete `SchedulerReentrancyError` subclass is removed in v0.34.0. [Cleanup migration](docs/migrations/cleanup-audit.md#eventloop-reentrancy-errors) |
|
data/SECURITY.md
CHANGED
|
@@ -1,7 +1,22 @@
|
|
|
1
|
-
# Execution boundary
|
|
1
|
+
# Execution boundary prototype (historical)
|
|
2
2
|
|
|
3
|
-
|
|
4
|
-
|
|
3
|
+
This document preserves an earlier source-derived design proposal, including
|
|
4
|
+
its original group names and compatibility decisions. It is not a pending
|
|
5
|
+
implementation plan or the authority for the current source layout.
|
|
6
|
+
|
|
7
|
+
For example, the Workflow phase compiler and neutral execution values are
|
|
8
|
+
present in the current implementation, while later refinements changed the
|
|
9
|
+
prototype's grouping and placement. Use [Phronomy Architecture](architecture.md)
|
|
10
|
+
and the current source diagram for the reconciled responsibilities.
|
|
11
|
+
|
|
12
|
+
Original prototype base: main 653e255a34fe4062d4beca47530e084fdd3a6ba9.
|
|
13
|
+
The proposal below is retained as history, not a current public API guide.
|
|
14
|
+
|
|
15
|
+
## Recorded proposal
|
|
16
|
+
|
|
17
|
+
The prototype separated result values from concrete execution connections.
|
|
18
|
+
For example, Engine and Services could share TaskResult without making those
|
|
19
|
+
values acquire Runtime or invoke operation-submission services.
|
|
5
20
|
|
|
6
21
|
TaskResult, Outcome, result composition, physical completion and ScopeState
|
|
7
22
|
belong to Execution Results. They depend on Contracts and Common, without
|
|
@@ -16,7 +31,11 @@ terminal state. FSMSession retains terminal detection and persistence gating.
|
|
|
16
31
|
TerminalDecision is an execution contract, independent of Workflow and FSM
|
|
17
32
|
state vocabulary.
|
|
18
33
|
|
|
19
|
-
##
|
|
34
|
+
## Compatibility decisions recorded in the prototype
|
|
35
|
+
|
|
36
|
+
The prototype moved execution-control adaptation out of shared values and
|
|
37
|
+
removed obsolete internal entry points. For example, InvocationContext kept
|
|
38
|
+
the supplied deadline value while the invoking service attached its timer.
|
|
20
39
|
|
|
21
40
|
* InvocationContext#effective_timeout_token and #effective_cancellation_token
|
|
22
41
|
are removed. Although annotated private, both occurred in the Stable API
|
|
@@ -637,9 +637,31 @@ been cancelled or timed out. It does not forcefully interrupt worker threads.
|
|
|
637
637
|
See [R8 unit19](architecture/r8-unit19.md) and its
|
|
638
638
|
[migration notes](migrations/r8-unit19.md) for the shutdown budget and result rules.
|
|
639
639
|
|
|
640
|
-
`Runtime#shutdown` is terminal for that Runtime.
|
|
641
|
-
|
|
642
|
-
|
|
640
|
+
`Runtime#shutdown` is terminal for that Runtime. During the drain phase it waits
|
|
641
|
+
for registered owners and pending timer notifications. During the stop phase it
|
|
642
|
+
closes pool admission and waits for workers while EventLoop continues delivering
|
|
643
|
+
existing deadlines. It then stops EventLoop and closes the timer service. Timer
|
|
644
|
+
callbacks continue to run on EventLoop, not on the shutdown caller's thread.
|
|
645
|
+
|
|
646
|
+
For example, a Blocking operation with a 50 ms timeout that takes 200 ms still
|
|
647
|
+
reports `TimeoutError` when shutdown begins immediately after submission, if the
|
|
648
|
+
shutdown budget permits that deadline to be delivered. The worker is allowed to
|
|
649
|
+
finish physically. A queued operation whose timeout settles before it starts is
|
|
650
|
+
skipped, just as during ordinary operation. Standalone fan-out deadlines also
|
|
651
|
+
remain active even when their pending results do not occupy a pool worker.
|
|
652
|
+
|
|
653
|
+
Complete cleanup requires accepted timer notifications to finish or be removed
|
|
654
|
+
by their owners before the timer service closes. If the finite shutdown budget
|
|
655
|
+
expires while notifications remain, Runtime reports incomplete cleanup even
|
|
656
|
+
when no worker thread remains. It does not fire future callbacks early or create
|
|
657
|
+
a background timer service to preserve deadlines after shutdown returns.
|
|
658
|
+
|
|
659
|
+
For example, a notification scheduled far beyond both shutdown phases is not
|
|
660
|
+
executed early merely to empty the timer queue. Discarding that notification at
|
|
661
|
+
closure makes `cleanup_complete?` false and prevents default Runtime replacement.
|
|
662
|
+
Once shutdown returns incomplete, future deadline delivery is not guaranteed;
|
|
663
|
+
the application must not treat that result as completed work or a safe handoff.
|
|
664
|
+
Repeated shutdown retains the original result rather than silently upgrading it.
|
|
643
665
|
|
|
644
666
|
Internal subsystems can register one shutdown participant per Runtime-local key
|
|
645
667
|
through `Runtime#__register_shutdown_participant`. This is an internal lifecycle
|
|
@@ -185,12 +185,21 @@ and verifies provider cleanup. It uses the real Tool argument-validation path.
|
|
|
185
185
|
It does not exercise the SharedState Agent loop or establish live-model,
|
|
186
186
|
database or multi-process acceptance.
|
|
187
187
|
|
|
188
|
-
In custom
|
|
189
|
-
Agent's public `unload!` operation.
|
|
190
|
-
|
|
191
|
-
|
|
192
|
-
|
|
193
|
-
|
|
188
|
+
In both default and custom sharing modes, SharedState releases terminal member
|
|
189
|
+
instances through the Agent's public `unload!` operation. It owns the lifetime of
|
|
190
|
+
the members it creates, including successful calls, early coordination stops and
|
|
191
|
+
invocation failures. Releasing a member does not delete its saved history.
|
|
192
|
+
|
|
193
|
+
For example, two members running two cycles create four temporary Agents. Each
|
|
194
|
+
Agent is released after its invocation finishes, while the shared findings stay
|
|
195
|
+
available to later members and the final aggregation. Repeated coordination does
|
|
196
|
+
not accumulate completed member owners in the Runtime.
|
|
197
|
+
|
|
198
|
+
A normal Agent approval wait keeps the public `invoke` call pending. In custom
|
|
199
|
+
mode, SharedState consequently stays inside the provider's `open` block and
|
|
200
|
+
retains its resources; it does not return a suspended result or close the
|
|
201
|
+
provider merely because an internal execution reaches an approval wait. The
|
|
202
|
+
application remains responsible for answering or cancelling approvals.
|
|
194
203
|
|
|
195
204
|
For example, when a member waits for approval of `record_issue`, the board stays
|
|
196
205
|
open while that invocation waits. An approval allows the Tool and member to
|
|
@@ -207,7 +216,8 @@ during the wait; after a public approval response, the Tool writes its record,
|
|
|
207
216
|
aggregation runs, the provider closes and the member is released. Fixed
|
|
208
217
|
responses verify the execution path, not a live model's Tool-selection behavior.
|
|
209
218
|
|
|
210
|
-
|
|
219
|
+
In either sharing mode, the lifecycle guard also detects a custom `invoke`
|
|
220
|
+
override that returns a Hash
|
|
211
221
|
with a suspended status before reaching completion. That exceptional early
|
|
212
222
|
return raises `SharedState::MemberLifecycleError` with `reason: :suspended` and
|
|
213
223
|
stops coordination before later members or aggregation. It is not the behavior
|
|
@@ -39,7 +39,8 @@ module Phronomy
|
|
|
39
39
|
freeze
|
|
40
40
|
end
|
|
41
41
|
|
|
42
|
-
# Returns true when
|
|
42
|
+
# Returns true when owned resources stopped and pending timer notifications
|
|
43
|
+
# settled within the shutdown budget rather than being discarded.
|
|
43
44
|
def cleanup_complete?
|
|
44
45
|
@cleanup_status == :complete
|
|
45
46
|
end
|
|
@@ -8,6 +8,8 @@ module Phronomy
|
|
|
8
8
|
@clock = clock
|
|
9
9
|
@heap = []
|
|
10
10
|
@mutex = Mutex.new
|
|
11
|
+
@idle = ConditionVariable.new
|
|
12
|
+
@firing = 0
|
|
11
13
|
@stopped = false
|
|
12
14
|
@wake = nil
|
|
13
15
|
end
|
|
@@ -51,10 +53,26 @@ module Phronomy
|
|
|
51
53
|
@mutex.synchronize do
|
|
52
54
|
before = @heap.length
|
|
53
55
|
@heap.delete_if { |(_, registered)| registered == callback }
|
|
56
|
+
@idle.broadcast if idle_locked?
|
|
54
57
|
before != @heap.length
|
|
55
58
|
end
|
|
56
59
|
end
|
|
57
60
|
|
|
61
|
+
# Wait without driving callbacks on the shutdown caller's thread. Both
|
|
62
|
+
# registrations and callbacks already removed from the heap must finish.
|
|
63
|
+
# @api private
|
|
64
|
+
def wait_until_idle(deadline)
|
|
65
|
+
@mutex.synchronize do
|
|
66
|
+
until idle_locked?
|
|
67
|
+
remaining = deadline - Process.clock_gettime(Process::CLOCK_MONOTONIC)
|
|
68
|
+
return false if remaining <= 0
|
|
69
|
+
|
|
70
|
+
@idle.wait(@mutex, remaining)
|
|
71
|
+
end
|
|
72
|
+
true
|
|
73
|
+
end
|
|
74
|
+
end
|
|
75
|
+
|
|
58
76
|
# Executes all callbacks whose deadline is due. Must be called by EventLoop.
|
|
59
77
|
def fire_due
|
|
60
78
|
callbacks = @mutex.synchronize do
|
|
@@ -62,7 +80,9 @@ module Phronomy
|
|
|
62
80
|
|
|
63
81
|
now = @clock.call
|
|
64
82
|
due_count = @heap.bsearch_index { |(fire_at, _)| fire_at > now } || @heap.length
|
|
65
|
-
@heap.shift(due_count).map(&:last)
|
|
83
|
+
callbacks = @heap.shift(due_count).map(&:last)
|
|
84
|
+
@firing += callbacks.length
|
|
85
|
+
callbacks
|
|
66
86
|
end
|
|
67
87
|
|
|
68
88
|
callbacks.each do |callback|
|
|
@@ -71,6 +91,11 @@ module Phronomy
|
|
|
71
91
|
Phronomy::RuntimeSettings.current.logger&.error do
|
|
72
92
|
"[TimerQueue] callback raised #{error.class}: #{error.message}"
|
|
73
93
|
end
|
|
94
|
+
ensure
|
|
95
|
+
@mutex.synchronize do
|
|
96
|
+
@firing -= 1
|
|
97
|
+
@idle.broadcast if idle_locked?
|
|
98
|
+
end
|
|
74
99
|
end
|
|
75
100
|
callbacks.length
|
|
76
101
|
end
|
|
@@ -82,13 +107,28 @@ module Phronomy
|
|
|
82
107
|
def shutdown
|
|
83
108
|
wake = @mutex.synchronize do
|
|
84
109
|
return self if @stopped
|
|
110
|
+
@drained_on_shutdown = idle_locked?
|
|
85
111
|
@stopped = true
|
|
86
112
|
@heap.clear
|
|
113
|
+
@idle.broadcast if idle_locked?
|
|
87
114
|
@wake
|
|
88
115
|
end
|
|
89
116
|
wake&.call
|
|
90
117
|
self
|
|
91
118
|
end
|
|
119
|
+
|
|
120
|
+
# Capture the first closure rather than a preceding idle observation:
|
|
121
|
+
# a caller holding this queue may register after that observation.
|
|
122
|
+
# @api private
|
|
123
|
+
def drained_on_shutdown?
|
|
124
|
+
@mutex.synchronize { @stopped && @drained_on_shutdown }
|
|
125
|
+
end
|
|
126
|
+
|
|
127
|
+
private
|
|
128
|
+
|
|
129
|
+
def idle_locked?
|
|
130
|
+
@heap.empty? && @firing.zero?
|
|
131
|
+
end
|
|
92
132
|
end
|
|
93
133
|
end
|
|
94
134
|
end
|
|
@@ -27,7 +27,20 @@ module Phronomy
|
|
|
27
27
|
end
|
|
28
28
|
|
|
29
29
|
def shutdown
|
|
30
|
-
@mutex.synchronize
|
|
30
|
+
@mutex.synchronize do
|
|
31
|
+
return true unless @timer
|
|
32
|
+
|
|
33
|
+
@timer.shutdown
|
|
34
|
+
@timer.drained_on_shutdown?
|
|
35
|
+
end
|
|
36
|
+
end
|
|
37
|
+
|
|
38
|
+
# Capture the timer without holding the service lock during callbacks:
|
|
39
|
+
# an admitted continuation may acquire this same service while draining.
|
|
40
|
+
# @api private
|
|
41
|
+
def wait_until_idle(deadline)
|
|
42
|
+
timer = @mutex.synchronize { @timer }
|
|
43
|
+
!timer || timer.wait_until_idle(deadline)
|
|
31
44
|
end
|
|
32
45
|
end
|
|
33
46
|
end
|
|
@@ -210,6 +210,7 @@ module Phronomy
|
|
|
210
210
|
loop_instance&.begin_draining
|
|
211
211
|
|
|
212
212
|
participants_idle = wait_for_participants(participants, drain_deadline)
|
|
213
|
+
@timer_service.wait_until_idle(drain_deadline)
|
|
213
214
|
loop_idle = !loop_instance || loop_instance.wait_until_idle(drain_deadline)
|
|
214
215
|
|
|
215
216
|
@lifecycle_mutex.synchronize do
|
|
@@ -217,13 +218,8 @@ module Phronomy
|
|
|
217
218
|
end
|
|
218
219
|
|
|
219
220
|
stop_deadline = monotonic_now + [cancel_grace.to_f, 0.2].max
|
|
220
|
-
event_loop_status
|
|
221
|
-
loop_instance
|
|
222
|
-
else
|
|
223
|
-
:not_started
|
|
224
|
-
end
|
|
225
|
-
|
|
226
|
-
pools_stopped, subsystem_error = shutdown_pools_and_timer(deadline: stop_deadline)
|
|
221
|
+
event_loop_status, pools_stopped, timers_idle, subsystem_error =
|
|
222
|
+
shutdown_resources(loop_instance, deadline: stop_deadline)
|
|
227
223
|
participant_error = @lifecycle_mutex.synchronize { @shutdown_participant_error }
|
|
228
224
|
cleanup_complete = participants_idle && participant_error.nil? &&
|
|
229
225
|
loop_idle &&
|
|
@@ -231,6 +227,7 @@ module Phronomy
|
|
|
231
227
|
event_loop_status != :cancel_timeout &&
|
|
232
228
|
(!loop_instance || loop_instance.__receiver_cleanup_complete?) &&
|
|
233
229
|
pools_stopped &&
|
|
230
|
+
timers_idle &&
|
|
234
231
|
subsystem_error.nil?
|
|
235
232
|
|
|
236
233
|
cleanup_complete = finalize_participants(participants) if cleanup_complete
|
|
@@ -306,21 +303,38 @@ module Phronomy
|
|
|
306
303
|
"Runtime is #{current_state}; new work is not accepted"
|
|
307
304
|
end
|
|
308
305
|
|
|
309
|
-
|
|
306
|
+
# EventLoop must keep delivering existing deadlines while accepted pool
|
|
307
|
+
# operations drain. Its thread remains the only timer callback executor.
|
|
308
|
+
# Future registrations beyond the shared budget make cleanup incomplete.
|
|
309
|
+
def shutdown_resources(loop_instance, deadline:)
|
|
310
310
|
error = nil
|
|
311
311
|
pools_stopped = false
|
|
312
|
+
timers_idle = false
|
|
313
|
+
event_loop_status = :not_started
|
|
312
314
|
begin
|
|
313
315
|
pools_stopped = @pool_registry.shutdown(deadline: deadline)
|
|
314
316
|
rescue => caught
|
|
315
317
|
error ||= caught
|
|
318
|
+
end
|
|
319
|
+
begin
|
|
320
|
+
timers_idle = @timer_service.wait_until_idle(deadline)
|
|
321
|
+
rescue => caught
|
|
322
|
+
error ||= caught
|
|
323
|
+
end
|
|
324
|
+
begin
|
|
325
|
+
event_loop_status = loop_instance.stop_and_join(deadline: deadline) if loop_instance
|
|
326
|
+
rescue => caught
|
|
327
|
+
event_loop_status = :failed
|
|
328
|
+
error ||= caught
|
|
316
329
|
ensure
|
|
317
330
|
begin
|
|
318
|
-
@timer_service.shutdown
|
|
331
|
+
timers_drained_on_shutdown = @timer_service.shutdown
|
|
332
|
+
timers_idle &&= timers_drained_on_shutdown
|
|
319
333
|
rescue => caught
|
|
320
334
|
error ||= caught
|
|
321
335
|
end
|
|
322
336
|
end
|
|
323
|
-
[pools_stopped, error]
|
|
337
|
+
[event_loop_status, pools_stopped, timers_idle, error]
|
|
324
338
|
end
|
|
325
339
|
|
|
326
340
|
def validate_timeout!(value, name)
|
|
@@ -221,11 +221,11 @@ module Phronomy
|
|
|
221
221
|
definitions = shared_tool_definitions(member, binding, cycle)
|
|
222
222
|
instrumented = build_shared_researcher(member, definitions, sharing)
|
|
223
223
|
prompt = shared_prompt(input, member_config[:instruction])
|
|
224
|
-
|
|
224
|
+
invoke_member_agent(instrumented, prompt)
|
|
225
225
|
end
|
|
226
226
|
end
|
|
227
227
|
|
|
228
|
-
def
|
|
228
|
+
def invoke_member_agent(instrumented, prompt)
|
|
229
229
|
agent = instrumented.new
|
|
230
230
|
suspended = false
|
|
231
231
|
result = agent.invoke(prompt)
|
|
@@ -235,10 +235,10 @@ module Phronomy
|
|
|
235
235
|
end
|
|
236
236
|
result
|
|
237
237
|
ensure
|
|
238
|
-
|
|
238
|
+
release_member_agent(agent, result, $!) if agent && !suspended
|
|
239
239
|
end
|
|
240
240
|
|
|
241
|
-
def
|
|
241
|
+
def release_member_agent(agent, result, primary_error)
|
|
242
242
|
agent.unload!
|
|
243
243
|
rescue => release_error
|
|
244
244
|
error = MemberLifecycleError.new(agent: agent, result: result, reason: :release_failed,
|
|
@@ -298,7 +298,7 @@ module Phronomy
|
|
|
298
298
|
extra_tools: extra_tools,
|
|
299
299
|
per_agent_instruction: per_agent_instruction
|
|
300
300
|
)
|
|
301
|
-
instrumented
|
|
301
|
+
invoke_member_agent(instrumented, prompt)
|
|
302
302
|
end
|
|
303
303
|
|
|
304
304
|
def build_instrumented_researcher(researcher_class, store, cycle)
|
data/lib/phronomy/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: phronomy
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.35.
|
|
4
|
+
version: 0.35.2
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Raizo T.C.S
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2026-11-
|
|
11
|
+
date: 2026-11-18 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: ruby_llm
|