ton/YiemAgent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 8 Wiki Activity

update

Browse Source
This commit is contained in:
narawat
2026-09-12 16:09:00 +07:00
parent 6e53f57707
commit ea6012b2fa
31 changed files with 6897 additions and 5902 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/MCTSexamplePrompt.py
-537
View File
@@ -1,537 +0,0 @@
https://github.com/andyz245/LanguageAgentTreeSearch/blob/main/hotpot/hotpot.py
standard_prompt = '''
Write a coherent passage of 4 short paragraphs. The end sentence of each paragraph must be: {input}
'''
reflection_prompt = '''You are an advanced reasoning agent that can improve based on self refection. You will be given a previous reasoning trial in which you were given access to an Docstore API environment and a question to answer. You were unsuccessful in answering the question either because you guessed the wrong answer with Finish[<answer>], or you used up your set number of reasoning steps. In a few sentences, Diagnose a possible reason for failure and devise a new, concise, high level plan that aims to mitigate the same failure. Use complete sentences.
Here are some examples:
Previous Trial:
Question: The Rome Protocols were signed by three Prime Ministers one of which was assassinated as part of what?
Thought 1: I need to search Rome Protocols, find the three Prime Ministers, then find what they were assassinated as part of.
Action 1: Search[Rome Protocols]
Observation 1: The Rome Protocols were a series of three international agreements concluded in Rome on 17 March 1934 between the governments of Austria, Hungary and Italy. They were signed by Italian Prime Minister Benito Mussolini, Austrian Chancellor Engelbert Dollfuss and Hungarian Prime Minister Gyula Gömbös. All of the protocols went into effect on 12 July 1934 and were registered in League of Nations Treaty Series on 12 December 1934.
Thought 2: The three Prime Ministers were Benito Mussolini, Engelbert Dollfuss, and Gyula Gömbös. I need to search Benito Mussolini and find what he was assassinated as part of.
Action 2: Search[Benito Mussolini]
Observation 2: Benito Amilcare Andrea Mussolini (UK: MU(U)SS-ə-LEE-nee, US: MOOSS-, Italian: [beˈniːto aˈmilkare anˈdrɛːa mussoˈliːni]; 29 July 1883 – 28 April 1945) was an Italian politician and journalist who founded and led the National Fascist Party (PNF). He was Prime Minister of Italy from the March on Rome in 1922 until his deposition in 1943, as well as "Duce" of Italian fascism from the establishment of the Italian Fasces of Combat in 1919 until his summary execution in 1945 by Italian partisans. As dictator of Italy and principal founder of fascism, Mussolini inspired and supported the international spread of fascist movements during the inter-war period.Mussolini was originally a socialist politician and a journalist at the Avanti! newspaper. In 1912, he became a member of the National Directorate of the Italian Socialist Party (PSI), but he was expelled from the PSI for advocating military intervention in World War I, in opposition to the party's stance on neutrality. In 1914, Mussolini founded a new journal, Il Popolo d'Italia, and served in the Royal Italian Army during the war until he was wounded and discharged in 1917. Mussolini denounced the PSI, his views now centering on Italian nationalism instead of socialism, and later founded the fascist movement which came to oppose egalitarianism and class conflict, instead advocating "revolutionary nationalism" transcending class lines. On 31 October 1922, following the March on Rome (28–30 October), Mussolini was appointed prime minister by King Victor Emmanuel III, becoming the youngest individual to hold the office up to that time. After removing all political opposition through his secret police and outlawing labor strikes, Mussolini and his followers consolidated power through a series of laws that transformed the nation into a one-party dictatorship. Within five years, Mussolini had established dictatorial authority by both legal and illegal means and aspired to create a totalitarian state. In 1929, Mussolini signed the Lateran Treaty with the Holy See to establish Vatican City.
Mussolini's foreign policy aimed to restore the ancient grandeur of the Roman Empire by expanding Italian colonial possessions and the fascist sphere of influence. In the 1920s, he ordered the Pacification of Libya, instructed the bombing of Corfu over an incident with Greece, established a protectorate over Albania, and incorporated the city of Fiume into the Italian state via agreements with Yugoslavia. In 1936, Ethiopia was conquered following the Second Italo-Ethiopian War and merged into Italian East Africa (AOI) with Eritrea and Somalia. In 1939, Italian forces annexed Albania. Between 1936 and 1939, Mussolini ordered the successful Italian military intervention in Spain in favor of Francisco Franco during the Spanish Civil War. Mussolini's Italy initially tried to avoid the outbreak of a second global war, sending troops at the Brenner Pass to delay Anschluss and taking part in the Stresa Front, the Lytton Report, the Treaty of Lausanne, the Four-Power Pact and the Munich Agreement. However, Italy then alienated itself from Britain and France by aligning with Germany and Japan. Germany invaded Poland on 1 September 1939, resulting in declarations of war by France and the UK and the start of World War II.
On 10 June 1940, Mussolini decided to enter the war on the Axis side. Despite initial success, the subsequent Axis collapse on multiple fronts and eventual Allied invasion of Sicily made Mussolini lose the support of the population and members of the Fascist Party. As a consequence, early on 25 July 1943, the Grand Council of Fascism passed a motion of no confidence in Mussolini; later that day King Victor Emmanuel III dismissed him as head of government and had him placed in custody, appointing Pietro Badoglio to succeed him as Prime Minister. After the king agreed to an armistice with the Allies, on 12 September 1943 Mussolini was rescued from captivity in the Gran Sasso raid by German paratroopers and Waffen-SS commandos led by Major Otto-Harald Mors. Adolf Hitler, after meeting with the rescued former dictator, then put Mussolini in charge of a puppet regime in northern Italy, the Italian Social Republic (Italian: Repubblica Sociale Italiana, RSI), informally known as the Salò Republic, causing a civil war. In late April 1945, in the wake of near total defeat, Mussolini and his mistress Clara Petacci attempted to flee to Switzerland, but both were captured by Italian communist partisans and summarily executed by firing squad on 28 April 1945 near Lake Como. The bodies of Mussolini and his mistress were then taken to Milan, where they were hung upside down at a service station to publicly confirm their demise.
Thought 3: Benito Mussolini was assassinated as part of the collapse of the Axis powers during World War II. So the Rome Protocols were signed by three Prime Ministers one of which was assassinated as part of World War II.
Action 3: Finish[World War II]
Reflection: I searched one of the prime ministers involved in the signing, then attemted to answer right away. I should have searched each of the prime ministers, then looked up 'death' on each of their pages in order to get more information before answering.
Previous Trial:
Question: Kam Heskin plays Paige Morgan in a 2004 film directed by who?
Thought 1: I need to search Kam Heskin and Paige Morgan, find the 2004 film they are in, then find the director of the film.
Action 1: Search[Kam Heskin]
Observation 1: Kam Erika Heskin (born May 8, 1973) is an American actress. She began her career playing Caitlin Deschanel on the NBC daytime soap opera Sunset Beach (1998–1999), before appearing in films Planet of the Apes (2001) and Catch Me If You Can (2002). Heskin went on in 2003 to play Elizabeth Bennet in an independent film Pride & Prejudice: A Latter-Day Comedy, Robin in Charmed (2004), and Paige Morgan in The Prince and Me film franchise (2006–2010).
Thought 2: Kam Heskin plays Paige Morgan in The Prince and Me film franchise. I need to search The Prince and Me film franchise and find the director of the 2004 film.
Action 2: Search[The Prince and Me film franchise]
Observation 2: Could not find [The Prince and Me film franchise]. Similar: ['Kam Heskin', 'Prince of Persia', 'Harry Potter and the Half-Blood Prince (film)', 'Prince of Persia: The Sands of Time (film)', 'The Chronicles of Narnia (film series)', 'Majestic Prince (franchise)', 'Kingsman (franchise)', 'The Little Prince (2015 film)', 'Shrek (franchise)', 'Harry Potter (film series)']
Thought 3: I need to search The Prince and Me (2004 film) instead.
Action 3: Search[The Prince and Me (2004 film)]
Observation 3: Could not find [The Prince and Me (2004 film)]. Similar: ['The Prince & Me', 'The Prince & Me 2: The Royal Wedding', 'Kam Heskin', 'Prince of Darkness (film)', 'Prince of Persia: The Sands of Time (film)', 'Rob Knox', 'Alexander (2004 film)', 'Prince of Persia', 'Brooklynn Prince', 'Prince (musician)']
Thought 4: I need to search The Prince & Me (2004 film).
Action 4: Search[The Prince & Me (2004 film)]
Observation 4: Could not find [The Prince & Me (2004 film)]. Similar: ['The Prince & Me', 'The Prince & Me 2: The Royal Wedding', 'Prince of Darkness (film)', 'Prince of Persia: The Sands of Time (film)', 'Rob Knox', 'Alexander (2004 film)', 'Prince (musician)', 'Prince of Persia', 'Kam Heskin', 'Brooklynn Prince']
Thought 5: I need to search The Prince & Me (2004 film) instead.
Action 5: Search[The Prince & Me (2004 film)]
Observation 5: Could not find [The Prince & Me (2004 film)]. Similar: ['The Prince & Me', 'The Prince & Me 2: The Royal Wedding', 'Prince of Darkness (film)', 'Prince of Persia: The Sands of Time (film)', 'Rob Knox', 'Alexander (2004 film)', 'Prince (musician)', 'Prince of Persia', 'Kam Heskin', 'Brooklynn Prince']
Thought 6: I need to search The Prince & Me (2004 film).
Action 6: Search[The Prince & Me (2004 film)]
Observation 6: Could not find [The Prince & Me (2004 film)]. Similar: ['The Prince & Me', 'The Prince & Me 2: The Royal Wedding', 'Prince of Darkness (film)', 'Prince of Persia: The Sands of Time (film)', 'Rob Knox', 'Alexander (2004 film)', 'Prince (musician)', 'Prince of Persia', 'Kam Heskin', 'Brooklynn Prince']
Reflection: I got stuck in a loop where I kept trying to search 'The Prince & Me (2004 film)' but the page could not be found. Instead I should have tried to search the similar results that had a similar name to see and they were made in 2004.
Previous Trial:
Question: The Oberoi family is part of a hotel company that has a head office in what city?
Thought 1: I need to search the Oberoi family and find the city where the hotel company's head office is located.
Action 1: Search[Oberoi family]
Observation 1: The Oberoi Group is a luxury hotel group with its head office in New Delhi, India.[2] Founded in 1934, the company owns and operates 32 luxury hotels and two river cruise ships in 7 countries, primarily under its Oberoi Hotels & Resorts and Trident brands.[3] The group also operates The Oberoi Centre for Learning and Development, which is regarded as one of Asia's top institutions for hospitality education.[4]. The foundations of the Oberoi Group date back to 1934 when The Rai Bahadur Mohan Singh Oberoi, the founder of the group, bought two properties: the Maidens in Delhi and the Clarke's in Shimla.[5] In the following years Oberoi, assisted by his two sons, Tilak Raj Singh Oberoi and Prithvi Raj Singh Oberoi (P.R.S. Oberoi
Thought 2: The Oberoi Group has its head office in New Delhi, India. I just need to finish with New Delhi.
Action 2: Finish[New Delhi]
Observation 2: Episode finished, reward = 0
Reflection: I appeared to have retrieved the correct information about The Oberoi Family and the location of it's head office, and provided a corresponding answer. However this answer does not exactly match the ground truth answer so I should try a different wording, such as Delhi.
Previous trial:
{trajectory}Reflection:'''
cot_prompt = '''
Solve a question answering task with interleaving Thought, Action, Observation steps. Thought can reason about the current situation, and Action can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
After each observation, provide the next Thought and next Action. Here are some examples:
Question: What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?
Thought 1: I need to search Colorado orogeny, find the area that the eastern sector of the Colorado orogeny extends into, then find the elevation range of the area.
Action 1: Search[Colorado orogeny]
Observation 1: The Colorado orogeny was an episode of mountain building (an orogeny) in Colorado and surrounding areas. This took place from 1780 to 1650 million years ago (Mya), during the Paleoproterozoic (Statherian Period). It is recorded in the Colorado orogen, a >500-km-wide belt of oceanic arc rock that extends southward into New Mexico. The Colorado orogeny was likely part of the larger Yavapai orogeny.
Thought 2: It does not mention the eastern sector of the Colorado orogeny. I need to look up eastern sector.
Action 2: Lookup[eastern sector]
Observation 2: (Result 1 / 1) The Colorado orogen, formerly called the Colorado province, is a >500-km-wide belt of oceanic arc rock (1.78\u20131.65 Ga) that extends southward into New Mexico and composes a major part of the Proterozoic provinces of southwestern United States. This transcontinental collisional event occurred during the Paleoproterozoic (Statherian Period).[1] The Wyoming sector of the Colorado orogeny was formerly called the Medicine Bow orogeny. The eastern sector extends into the High Plains and is called the Central Plains orogeny. The boundary between the Colorado orogeny and the Wyoming craton is the Cheyenne belt, a 5-km-wide mylonitic shear zone that verges northward. The Cheyenne belt transects and cuts off the south edge of the older Trans-Hudson orogeny.[2]
Thought 3: The eastern sector of Colorado orogeny extends into the High Plains, so High Plains is the area. I need to search High Plains and find its elevation range.
Action 3: Search[High Plains]Observation 3: High Plains refers to one of two distinct land regions:
Thought 4: I need to search High Plains (United States).
Action 4: Search[High Plains (United States)]
Observation 4: The High Plains are a subregion of the Great Plains, mainly in the Western United States, but also partly in the Midwest states of Nebraska, Kansas, and South Dakota, generally encompassing the western part of the Great Plains before the region reaches the Rocky Mountains. The High Plains are located in eastern Montana, southeastern Wyoming, southwestern South Dakota, western Nebraska, eastern Colorado, western Kansas, eastern New Mexico, western Oklahoma, and to just south of the Texas Panhandle.[4] The southern region of the Western High Plains ecology region contains the geological formation known as Llano Estacado which can be seen from a short distance or on satellite maps.[5] From east to west, the High Plains rise in elevation from around 1,800 to 7,000 ft (550 to 2,130 m).[3]
Thought 5: High Plains rise in elevation from around 1,800 to 7,000 ft, so the answer is 1,800 to 7,000 ft.
Action 5: Finish[1,800 to 7,000 ft]
Question: Guitars for Wounded Warriors is an album that was recorded in the village in which New York county?
Thought 1: I need to search Guitars for Wounded Warriors, then find in which New York county it was recorded.
Action 1: Search[Guitars for Wounded Warriors]
Observation 1: Guitars for Wounded Warriors is the sixth solo studio album by guitarist Brian Tarquin, released in August 2014 by Cleopatra Records. In 2016, it received a Best Compilation Album nomination by the Independent Music Awards. All tracks were recorded at Tarquin's Jungle Room Studios in New Paltz (village), New York. Being moved by the lack of support for returning veterans through his life Tarquin decided to compose a heavy instrumental rock album as a way to show his appreciation to all veterans. So once again he enlisted top notch players to guest with him on the album, Billy Sheehan on Black Hawk, Ron \"Bumblefoot\" Thal and Reb Beach on Taliban Terror, Steve Morse on Freedom, Chris Poland on Charlie Surfs and Hunting, Chuck Loeb on Escape Kabul, Hal Lindes on Sand & Blood, Gary Hoey on 5 Klicks To Hell and Baghdad, Alex De Rosso Dokken on Broken Arrow, and The Flyin' Ryan Brothers on Surgical Strike. The entire album was engineered, produced and composed by Tarquin especially for each one of the guest guitarists. Partial proceeds are donated to the Fisher House Foundation from sales.
Thought 2: Guitars for Wounded Warriors was recorded in New Paltz (village), New York. I need to search New Paltz (village), New York and find which county it is in
Action 2: Search[New Paltz (village), New York]
Observation 2: New Paltz is a village in Ulster County located in the U.S. state of New York. It is approximately 80 miles (130 km) north of New York City and 70 miles (110 km) south of Albany. The population was 7,324 at the 2020 census.[3]
Thought 3: New Paltz (village), New York is in Ulster County, so the answer is Ulster County.
Action 3: Finish[Ulster County]
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
{input}
'''
cot_prompt_short = '''
Solve a question answering task with interleaving Thought, Action, Observation steps. Thought can reason about the current situation, and Action can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
After each observation, provide the next Thought and next Action. Here are some examples:
Question: What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?
Thought 1: I need to search Colorado orogeny, find the area that the eastern sector of the Colorado orogeny extends into, then find the elevation range of the area.
Action 1: Search[Colorado orogeny]
Observation 1: The Colorado orogeny was an episode of mountain building (an orogeny) in Colorado and surrounding areas. This took place from 1780 to 1650 million years ago (Mya), during the Paleoproterozoic (Statherian Period). It is recorded in the Colorado orogen, a >500-km-wide belt of oceanic arc rock that extends southward into New Mexico. The Colorado orogeny was likely part of the larger Yavapai orogeny.
Thought 2: It does not mention the eastern sector of the Colorado orogeny. I need to look up eastern sector.
Action 2: Lookup[eastern sector]
Observation 2: (Result 1 / 1) The Colorado orogen, formerly called the Colorado province, is a >500-km-wide belt of oceanic arc rock (1.78\u20131.65 Ga) that extends southward into New Mexico and composes a major part of the Proterozoic provinces of southwestern United States. This transcontinental collisional event occurred during the Paleoproterozoic (Statherian Period).[1] The Wyoming sector of the Colorado orogeny was formerly called the Medicine Bow orogeny. The eastern sector extends into the High Plains and is called the Central Plains orogeny. The boundary between the Colorado orogeny and the Wyoming craton is the Cheyenne belt, a 5-km-wide mylonitic shear zone that verges northward. The Cheyenne belt transects and cuts off the south edge of the older Trans-Hudson orogeny.[2]
Thought 3: The eastern sector of Colorado orogeny extends into the High Plains, so High Plains is the area. I need to search High Plains and find its elevation range.
Action 3: Search[High Plains]Observation 3: High Plains refers to one of two distinct land regions:
Thought 4: I need to search High Plains (United States).
Action 4: Search[High Plains (United States)]
Observation 4: The High Plains are a subregion of the Great Plains, mainly in the Western United States, but also partly in the Midwest states of Nebraska, Kansas, and South Dakota, generally encompassing the western part of the Great Plains before the region reaches the Rocky Mountains. The High Plains are located in eastern Montana, southeastern Wyoming, southwestern South Dakota, western Nebraska, eastern Colorado, western Kansas, eastern New Mexico, western Oklahoma, and to just south of the Texas Panhandle.[4] The southern region of the Western High Plains ecology region contains the geological formation known as Llano Estacado which can be seen from a short distance or on satellite maps.[5] From east to west, the High Plains rise in elevation from around 1,800 to 7,000 ft (550 to 2,130 m).[3]
Thought 5: High Plains rise in elevation from around 1,800 to 7,000 ft, so the answer is 1,800 to 7,000 ft.
Action 5: Finish[1,800 to 7,000 ft]
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
{input}
'''
cot_prompt_feedback_short = '''You are also an advanced reasoning agent that can improve based on self refection. Solve a question answering task with interleaving Thought, Action, Observation steps. Thought can reason about the current situation, and Action can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
After each observation, provide the next Thought and next Action. Here are some examples:
Question: What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?
Thought 1: I need to search Colorado orogeny, find the area that the eastern sector of the Colorado orogeny extends into, then find the elevation range of the area.
Action 1: Search[Colorado orogeny]
Observation 1: The Colorado orogeny was an episode of mountain building (an orogeny) in Colorado and surrounding areas. This took place from 1780 to 1650 million years ago (Mya), during the Paleoproterozoic (Statherian Period). It is recorded in the Colorado orogen, a >500-km-wide belt of oceanic arc rock that extends southward into New Mexico. The Colorado orogeny was likely part of the larger Yavapai orogeny.
Thought 2: It does not mention the eastern sector of the Colorado orogeny. I need to look up eastern sector.
Action 2: Lookup[eastern sector]
Observation 2: (Result 1 / 1) The Colorado orogen, formerly called the Colorado province, is a >500-km-wide belt of oceanic arc rock (1.78\u20131.65 Ga) that extends southward into New Mexico and composes a major part of the Proterozoic provinces of southwestern United States. This transcontinental collisional event occurred during the Paleoproterozoic (Statherian Period).[1] The Wyoming sector of the Colorado orogeny was formerly called the Medicine Bow orogeny. The eastern sector extends into the High Plains and is called the Central Plains orogeny. The boundary between the Colorado orogeny and the Wyoming craton is the Cheyenne belt, a 5-km-wide mylonitic shear zone that verges northward. The Cheyenne belt transects and cuts off the south edge of the older Trans-Hudson orogeny.[2]
Thought 3: The eastern sector of Colorado orogeny extends into the High Plains, so High Plains is the area. I need to search High Plains and find its elevation range.
Action 3: Search[High Plains]Observation 3: High Plains refers to one of two distinct land regions:
Thought 4: I need to search High Plains (United States).
Action 4: Search[High Plains (United States)]
Observation 4: The High Plains are a subregion of the Great Plains, mainly in the Western United States, but also partly in the Midwest states of Nebraska, Kansas, and South Dakota, generally encompassing the western part of the Great Plains before the region reaches the Rocky Mountains. The High Plains are located in eastern Montana, southeastern Wyoming, southwestern South Dakota, western Nebraska, eastern Colorado, western Kansas, eastern New Mexico, western Oklahoma, and to just south of the Texas Panhandle.[4] The southern region of the Western High Plains ecology region contains the geological formation known as Llano Estacado which can be seen from a short distance or on satellite maps.[5] From east to west, the High Plains rise in elevation from around 1,800 to 7,000 ft (550 to 2,130 m).[3]
Thought 5: High Plains rise in elevation from around 1,800 to 7,000 ft, so the answer is 1,800 to 7,000 ft.
Action 5: Finish[1,800 to 7,000 ft]
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
You have attempted to answer the following question before and failed. The following reflection(s) give a plan to avoid failing to answer the question in the same way you did previously. Use them to improve your strategy of correctly answering the given question.
{trajectories}
{input}
'''
cot_prompt_feedback = '''You are also an advanced reasoning agent that can improve based on self refection. Solve a question answering task with interleaving Thought, Action, Observation steps. Thought can reason about the current situation, and Action can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
After each observation, provide the next Thought and next Action. Here are some examples:
Question: What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?
Thought 1: I need to search Colorado orogeny, find the area that the eastern sector of the Colorado orogeny extends into, then find the elevation range of the area.
Action 1: Search[Colorado orogeny]
Observation 1: The Colorado orogeny was an episode of mountain building (an orogeny) in Colorado and surrounding areas. This took place from 1780 to 1650 million years ago (Mya), during the Paleoproterozoic (Statherian Period). It is recorded in the Colorado orogen, a >500-km-wide belt of oceanic arc rock that extends southward into New Mexico. The Colorado orogeny was likely part of the larger Yavapai orogeny.
Thought 2: It does not mention the eastern sector of the Colorado orogeny. I need to look up eastern sector.
Action 2: Lookup[eastern sector]
Observation 2: (Result 1 / 1) The Colorado orogen, formerly called the Colorado province, is a >500-km-wide belt of oceanic arc rock (1.78\u20131.65 Ga) that extends southward into New Mexico and composes a major part of the Proterozoic provinces of southwestern United States. This transcontinental collisional event occurred during the Paleoproterozoic (Statherian Period).[1] The Wyoming sector of the Colorado orogeny was formerly called the Medicine Bow orogeny. The eastern sector extends into the High Plains and is called the Central Plains orogeny. The boundary between the Colorado orogeny and the Wyoming craton is the Cheyenne belt, a 5-km-wide mylonitic shear zone that verges northward. The Cheyenne belt transects and cuts off the south edge of the older Trans-Hudson orogeny.[2]
Thought 3: The eastern sector of Colorado orogeny extends into the High Plains, so High Plains is the area. I need to search High Plains and find its elevation range.
Action 3: Search[High Plains]Observation 3: High Plains refers to one of two distinct land regions:
Thought 4: I need to search High Plains (United States).
Action 4: Search[High Plains (United States)]
Observation 4: The High Plains are a subregion of the Great Plains, mainly in the Western United States, but also partly in the Midwest states of Nebraska, Kansas, and South Dakota, generally encompassing the western part of the Great Plains before the region reaches the Rocky Mountains. The High Plains are located in eastern Montana, southeastern Wyoming, southwestern South Dakota, western Nebraska, eastern Colorado, western Kansas, eastern New Mexico, western Oklahoma, and to just south of the Texas Panhandle.[4] The southern region of the Western High Plains ecology region contains the geological formation known as Llano Estacado which can be seen from a short distance or on satellite maps.[5] From east to west, the High Plains rise in elevation from around 1,800 to 7,000 ft (550 to 2,130 m).[3]
Thought 5: High Plains rise in elevation from around 1,800 to 7,000 ft, so the answer is 1,800 to 7,000 ft.
Action 5: Finish[1,800 to 7,000 ft]
Question: Guitars for Wounded Warriors is an album that was recorded in the village in which New York county?
Thought 1: I need to search Guitars for Wounded Warriors, then find in which New York county it was recorded.
Action 1: Search[Guitars for Wounded Warriors]
Observation 1: Guitars for Wounded Warriors is the sixth solo studio album by guitarist Brian Tarquin, released in August 2014 by Cleopatra Records. In 2016, it received a Best Compilation Album nomination by the Independent Music Awards. All tracks were recorded at Tarquin's Jungle Room Studios in New Paltz (village), New York. Being moved by the lack of support for returning veterans through his life Tarquin decided to compose a heavy instrumental rock album as a way to show his appreciation to all veterans. So once again he enlisted top notch players to guest with him on the album, Billy Sheehan on Black Hawk, Ron \"Bumblefoot\" Thal and Reb Beach on Taliban Terror, Steve Morse on Freedom, Chris Poland on Charlie Surfs and Hunting, Chuck Loeb on Escape Kabul, Hal Lindes on Sand & Blood, Gary Hoey on 5 Klicks To Hell and Baghdad, Alex De Rosso Dokken on Broken Arrow, and The Flyin' Ryan Brothers on Surgical Strike. The entire album was engineered, produced and composed by Tarquin especially for each one of the guest guitarists. Partial proceeds are donated to the Fisher House Foundation from sales.
Thought 2: Guitars for Wounded Warriors was recorded in New Paltz (village), New York. I need to search New Paltz (village), New York and find which county it is in
Action 2: Search[New Paltz (village), New York]
Observation 2: New Paltz is a village in Ulster County located in the U.S. state of New York. It is approximately 80 miles (130 km) north of New York City and 70 miles (110 km) south of Albany. The population was 7,324 at the 2020 census.[3]
Thought 3: New Paltz (village), New York is in Ulster County, so the answer is Ulster County.
Action 3: Finish[Ulster County]
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
You have attempted to answer the following question before and failed, either because your reasoning for the answer was incorrect or the phrasing of your response did not exactly match the answer. The following reflection(s) give a plan to avoid failing to answer the question in the same way you did previously. Use them to improve your strategy of correctly answering the given question.
{trajectories}
When providing the thought and action for the current trial, that into account these failed trajectories and make sure not to repeat the same mistakes and incorrect answers.
{input}
'''
vote_prompt = '''Analyze the trajectories of a solution to a question answering task. The trajectories are labeled by pairs of thoughts that can reason about the current situation and actions that can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Given a question and a list of trajectories, decide which trajectory is most promising. Analyze each trajectory in detail and consider possible errors, then conclude in the last line "The best trajectory is {s}", where s the integer id of the trajectory.
'''
compare_prompt = '''Analyze the trajectories of a solution to a question answering task. The trajectories are labeled by pairs of thoughts that can reason about the current situation and actions that can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Briefly analyze the correctness of the following two trajectories. Conclude in the last line "The more correct trajectory is 1", "The more correct trajectory is 2", or "The two trajectories are similarly correct".
'''
score_prompt = '''Analyze the trajectories of a solution to a question answering task. The trajectories are labeled by pairs of thoughts that can reason about the current situation and actions that can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Given a question and a trajectory, analyze the following trajectory, then at the last line conclude "Thus the correctness score is {s}", where s is an integer from 1 to 10.
'''
value_prompt = '''Analyze the trajectories of a solution to a question answering task. The trajectories are labeled by environmental observations about the situation, thoughts that can reason about the current situation and actions that can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Given a question and a trajectory, evaluate its correctness and provide your reasoning and analysis in detail. Focus on the latest thought, action, and observation. Incomplete trajectories can be correct if the thoughts and actions so far are correct, even if the answer is not found yet. Do not generate additional thoughts or actions. Then at the last line conclude "Thus the correctness score is {s}", where s is an integer from 1 to 10.
Question: Which other Mexican Formula One race car driver has held the podium besides the Force India driver born in 1990?
Thought 1: I need to search for a list of Mexican Formula One race car drivers, then eliminate the one who drove for Force India and was born in 1990.
Action 1: Search[Formula One drivers from Mexico]
Observation 1: There have been six Formula One drivers from Mexico who have taken part in races since the championship began in 1950. Sergio P\u00e9rez is the most successful, having won six Grands Prix. Since 2021, P\u00e9rez drives for the Red Bull team.. P\u00e9rez is the only Mexican F1 driver to achieve a pole position. He took his first pole position at the 2022 Saudi Arabian Grand Prix, in his 219th Grand Prix meeting (a record for the most Grands Prix before a pole).
Thought 2: Sergio P\u00e9rez, born in 1990 and drove for Force India, is not the Mexican driver we are looking for. The passage does not give me enough information about other Mexican drivers who have achieved a podium finish. I need to look up more information.
Action 2: Lookup[Formula One drivers from Mexico]
Observation 2: No more results.
Thought 3: The available information doesn't allow me to determine which other Mexican Formula One race car driver, besides Sergio P\u00e9rez, has held the podium. With the search function failing to provide a full list of Mexican Formula One drivers, I need to return different search results. Let's try searching for Mexican Grand Prix winners, as they would have held the podium.
Action 3: Search[Mexican Grand Prix winners]
Observation 3: Could not find Mexican Grand Prix winners. Similar: ['Mexican Grand Prix', 'List of Formula One Grand Prix winners', '1990 Mexican Grand Prix', '2018 Mexican Grand Prix', '2019 Mexican Grand Prix'].
Thought 4: Given the difficulties in finding a direct list of Mexican Grand Prix winners, I should search for the Mexican Grand Prix to get a broader picture of the race's history. This might include winners.
Action 4: Search[Mexican Grand Prix]
Thus the correctness score is 3
Question: The football manager who recruited David Beckham managed Manchester United during what timeframe?Question: The football manager who recruited David Beckham managed Manchester United during what timeframe?
Thought 1: I need to search for the football manager who recruited David Beckham, and then find out the timeframe in which he managed Manchester United.
Action 1: Search[David Beckham's football manager]
Observation 1: Could not find David Beckham's football manager. Similar: ['David Beckham', 'Inter Miami CF (redirect from Miami Beckham United)', 'Victoria Beckham', 'The Beckham Experiment', 'Miami Freedom Park'].
Thought 2: I couldn't find the information on David Beckham's football manager. I need to search Manchester United and find out the timeframe of the manager.
Action 2: Search[Manchester United]
Observation 2: Manchester United Football Club, commonly referred to as Man United (often stylised as Man Utd), or simply United, is a professional football club based in Old Trafford, Greater Manchester, England. The club competes in the Premier League, the top division in the English football league system. Nicknamed the Red Devils, they were founded as Newton Heath LYR Football Club in 1878, but changed their name to Manchester United in 1902. After a spell playing in Clayton, Manchester, the club moved to their current stadium, Old Trafford, in 1910.. Domestically, Manchester United have won a record 20 league titles, 12 FA Cups, six League Cups and a record 21 FA Community Shields.
Thought 3: The information about David Beckham's football manager is not available. I will search for Manchester United's managers to find the timeframe.
Action 3: Search[Manchester United managers]
Observation 3: Manchester United Football Club is a professional football club based in Old Trafford, Greater Manchester, England. The club was formed in Newton Heath in 1878 as Newton Heath LYR F.C., and played their first competitive match in October 1886, when they entered the First Round of the 1886–87 FA Cup. The club was renamed Manchester United F.C. in 1902, and moved to Old Trafford in 1910.. From the beginning of the club's official managerial records in 1892 to the start of the 2022–23 season, Manchester United have had 23 full-time managers.
Thought 4: The information about David Beckham's football manager is not available. The question asks for the timeframe when the manager managed Manchester United, so I need to find a list of Manchester United managers.
Action 4: Search[list of Manchester United managers]
Observation 4: Manchester United Football Club is a professional football club based in Old Trafford, Greater Manchester, England. The club was formed in Newton Heath in 1878 as Newton Heath LYR F.C., and played their first competitive match in October 1886, when they entered the First Round of the 1886–87 FA Cup. The club was renamed Manchester United F.C. in 1902, and moved to Old Trafford in 1910.. From the beginning of the club's official managerial records in 1892 to the start of the 2022–23 season, Manchester United have had 23 full-time managers.
Thus the correctness score is 4
Question: Which magazine was started first Arthur's Magazine or First for Women?
Thought 1: I need to search Arthur's Magazine and First for Women, and find which was started first.
Action 1: Search[Arthur's Magazine]
Observation 1: Arthur's Magazine (1844\u00e2\u0080\u00931846) was an American literary periodical published in Philadelphia in the 19th century. Edited by Timothy Shay Arthur, it featured work by Edgar A. Poe, J.H. Ingraham, Sarah Josepha Hale, Thomas G. Spear, and others.[1][2] In May 1846 it was merged into Godey's Lady's Book.[3]
Thus the correctness score is 10
{input}
'''
value_prompt_feedback = '''Analyze the trajectories of a solution to a question answering task. The trajectories are labeled by environmental observations about the situation, thoughts that can reason about the current situation and actions that can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Given a question and a trajectory, evaluate its correctness and provide your reasoning and analysis in detail. Focus on the latest thought, action, and observation. Incomplete trajectories can be correct if the thoughts and actions so far are correct, even if the answer is not found yet. Do not generate additional thoughts or actions. Then at the last line conclude "Thus the correctness score is {s}", where s is an integer from 1 to 10.
Question: Which other Mexican Formula One race car driver has held the podium besides the Force India driver born in 1990?
Thought 1: I need to search for a list of Mexican Formula One race car drivers, then eliminate the one who drove for Force India and was born in 1990.
Action 1: Search[Formula One drivers from Mexico]
Observation 1: There have been six Formula One drivers from Mexico who have taken part in races since the championship began in 1950. Sergio P\u00e9rez is the most successful, having won six Grands Prix. Since 2021, P\u00e9rez drives for the Red Bull team.. P\u00e9rez is the only Mexican F1 driver to achieve a pole position. He took his first pole position at the 2022 Saudi Arabian Grand Prix, in his 219th Grand Prix meeting (a record for the most Grands Prix before a pole).
Thought 2: Sergio P\u00e9rez, born in 1990 and drove for Force India, is not the Mexican driver we are looking for. The passage does not give me enough information about other Mexican drivers who have achieved a podium finish. I need to look up more information.
Action 2: Lookup[Formula One drivers from Mexico]
Observation 2: No more results.
Thought 3: The available information doesn't allow me to determine which other Mexican Formula One race car driver, besides Sergio P\u00e9rez, has held the podium. With the search function failing to provide a full list of Mexican Formula One drivers, I need to return different search results. Let's try searching for Mexican Grand Prix winners, as they would have held the podium.
Action 3: Search[Mexican Grand Prix winners]
Observation 3: Could not find Mexican Grand Prix winners. Similar: ['Mexican Grand Prix', 'List of Formula One Grand Prix winners', '1990 Mexican Grand Prix', '2018 Mexican Grand Prix', '2019 Mexican Grand Prix'].
Thought 4: Given the difficulties in finding a direct list of Mexican Grand Prix winners, I should search for the Mexican Grand Prix to get a broader picture of the race's history. This might include winners.
Action 4: Search[Mexican Grand Prix]
Thus the correctness score is 3
Question: Which magazine was started first Arthur's Magazine or First for Women?
Thought 1: I need to search Arthur's Magazine and First for Women, and find which was started first.
Action 1: Search[Arthur's Magazine]
Observation 1: Arthur's Magazine (1844\u00e2\u0080\u00931846) was an American literary periodical published in Philadelphia in the 19th century. Edited by Timothy Shay Arthur, it featured work by Edgar A. Poe, J.H. Ingraham, Sarah Josepha Hale, Thomas G. Spear, and others.[1][2] In May 1846 it was merged into Godey's Lady's Book.[3]
Thus the correctness score is 10
{trajectories}
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
Thus the correctness score is 10
{input}
'''
value_prompt_reasoning = '''You are an advanced reasoning agent that can improve based on self refection. Analyze the trajectories of your previous solutions to a question answering task. The trajectories are labeled by environmental observations about the situation, thoughts that can reason about the current situation and actions that can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Given a question and a trajectory, evaluate its correctness and provide your reasoning and analysis in detail. Focus on the latest thought, action, and observation. Incomplete trajectories can be correct if the thoughts and actions so far are correct, even if the answer is not found yet. Do not generate additional thoughts or actions. Then at the last line conclude "Thus the correctness score is {s}", where s is an integer from 1 to 10.
Question: Which other Mexican Formula One race car driver has held the podium besides the Force India driver born in 1990?
Thought 1: I need to search for a list of Mexican Formula One race car drivers, then eliminate the one who drove for Force India and was born in 1990.
Action 1: Search[Formula One drivers from Mexico]
Observation 1: There have been six Formula One drivers from Mexico who have taken part in races since the championship began in 1950. Sergio P\u00e9rez is the most successful, having won six Grands Prix. Since 2021, P\u00e9rez drives for the Red Bull team.. P\u00e9rez is the only Mexican F1 driver to achieve a pole position. He took his first pole position at the 2022 Saudi Arabian Grand Prix, in his 219th Grand Prix meeting (a record for the most Grands Prix before a pole).
Thought 2: Sergio P\u00e9rez, born in 1990 and drove for Force India, is not the Mexican driver we are looking for. The passage does not give me enough information about other Mexican drivers who have achieved a podium finish. I need to look up more information.
Action 2: Lookup[Formula One drivers from Mexico]
Observation 2: No more results.
Thought 3: The available information doesn't allow me to determine which other Mexican Formula One race car driver, besides Sergio P\u00e9rez, has held the podium. With the search function failing to provide a full list of Mexican Formula One drivers, I need to return different search results. Let's try searching for Mexican Grand Prix winners, as they would have held the podium.
Action 3: Search[Mexican Grand Prix winners]
Observation 3: Could not find Mexican Grand Prix winners. Similar: ['Mexican Grand Prix', 'List of Formula One Grand Prix winners', '1990 Mexican Grand Prix', '2018 Mexican Grand Prix', '2019 Mexican Grand Prix'].
Thought 4: Given the difficulties in finding a direct list of Mexican Grand Prix winners, I should search for the Mexican Grand Prix to get a broader picture of the race's history. This might include winners.
Action 4: Search[Mexican Grand Prix]
This trajectory is incorrect as my search should be related to Mexican Formula One race car drivers, not winners of the Mexican Grand Prix, a seperate event. A better search would have been for the List of Formula One Grand Prix winners, as suggested.
Thus the correctness score is 3
Question: Which magazine was started first Arthur's Magazine or First for Women?
Thought 1: I need to search Arthur's Magazine and First for Women, and find which was started first.
Action 1: Search[Arthur's Magazine]
Observation 1: Arthur's Magazine (1844\u00e2\u0080\u00931846) was an American literary periodical published in Philadelphia in the 19th century. Edited by Timothy Shay Arthur, it featured work by Edgar A. Poe, J.H. Ingraham, Sarah Josepha Hale, Thomas G. Spear, and others.[1][2] In May 1846 it was merged into Godey's Lady's Book.[3]
This trajectory is correct as it is reasonable to search for the first magazine provided in the question. It is also better to have simple searches corresponding to a single entity, making this the best action.
Thus the correctness score is 10
Question: The football manager who recruited David Beckham managed Manchester United during what timeframe?Question: The football manager who recruited David Beckham managed Manchester United during what timeframe?
Thought 1: I need to search for the football manager who recruited David Beckham, and then find out the timeframe in which he managed Manchester United.
Action 1: Search[David Beckham's football manager]
Observation 1: Could not find David Beckham's football manager. Similar: ['David Beckham', 'Inter Miami CF (redirect from Miami Beckham United)', 'Victoria Beckham', 'The Beckham Experiment', 'Miami Freedom Park'].
Thought 2: I couldn't find the information on David Beckham's football manager. I need to search Manchester United and find out the timeframe of the manager.
Action 2: Search[Manchester United]
Observation 2: Manchester United Football Club, commonly referred to as Man United (often stylised as Man Utd), or simply United, is a professional football club based in Old Trafford, Greater Manchester, England. The club competes in the Premier League, the top division in the English football league system. Nicknamed the Red Devils, they were founded as Newton Heath LYR Football Club in 1878, but changed their name to Manchester United in 1902. After a spell playing in Clayton, Manchester, the club moved to their current stadium, Old Trafford, in 1910.. Domestically, Manchester United have won a record 20 league titles, 12 FA Cups, six League Cups and a record 21 FA Community Shields.
Thought 3: The information about David Beckham's football manager is not available. I will search for Manchester United's managers to find the timeframe.
Action 3: Search[Manchester United managers]
Observation 3: Manchester United Football Club is a professional football club based in Old Trafford, Greater Manchester, England. The club was formed in Newton Heath in 1878 as Newton Heath LYR F.C., and played their first competitive match in October 1886, when they entered the First Round of the 1886–87 FA Cup. The club was renamed Manchester United F.C. in 1902, and moved to Old Trafford in 1910.. From the beginning of the club's official managerial records in 1892 to the start of the 2022–23 season, Manchester United have had 23 full-time managers.
Thought 4: The information about David Beckham's football manager is not available. The question asks for the timeframe when the manager managed Manchester United, so I need to find a list of Manchester United managers.
Action 4: Search[list of Manchester United managers]
Observation 4: Manchester United Football Club is a professional football club based in Old Trafford, Greater Manchester, England. The club was formed in Newton Heath in 1878 as Newton Heath LYR F.C., and played their first competitive match in October 1886, when they entered the First Round of the 1886–87 FA Cup. The club was renamed Manchester United F.C. in 1902, and moved to Old Trafford in 1910.. From the beginning of the club's official managerial records in 1892 to the start of the 2022–23 season, Manchester United have had 23 full-time managers.
This trajectory is mostly incorrect as I was not able to retrieve the relevant information to answer the question. The searches are too broad and not relevant to the specific player recruited, David Beckham. The last two actions are also too similar. It would be better to first search for David Beckham and lookup information related to his manager.
Thus the correctness score is 4
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
This trajectory is correct as all of my thoughts and actions are correct. It makes sense to search for Milhouse first as it is the central subject of the question. It is also correct to directly look up the relevant information in the article, instead of trying another search.
Thus the correctness score is 10
{input}
'''
value_prompt_reasoning_feedback = '''Analyze the trajectories of a solution to a question answering task. The trajectories are labeled by environmental observations about the situation, thoughts that can reason about the current situation and actions that can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Given a question and a trajectory, evaluate its correctness and provide your reasoning and analysis in detail. Focus on the latest thought, action, and observation. Incomplete trajectories can be correct if the thoughts and actions so far are correct, even if the answer is not found yet. Do not generate additional thoughts or actions. Then at the last line conclude "Thus the correctness score is {s}", where s is an integer from 1 to 10.
Question: Which other Mexican Formula One race car driver has held the podium besides the Force India driver born in 1990?
Thought 1: I need to search for a list of Mexican Formula One race car drivers, then eliminate the one who drove for Force India and was born in 1990.
Action 1: Search[Formula One drivers from Mexico]
Observation 1: There have been six Formula One drivers from Mexico who have taken part in races since the championship began in 1950. Sergio P\u00e9rez is the most successful, having won six Grands Prix. Since 2021, P\u00e9rez drives for the Red Bull team.. P\u00e9rez is the only Mexican F1 driver to achieve a pole position. He took his first pole position at the 2022 Saudi Arabian Grand Prix, in his 219th Grand Prix meeting (a record for the most Grands Prix before a pole).
Thought 2: Sergio P\u00e9rez, born in 1990 and drove for Force India, is not the Mexican driver we are looking for. The passage does not give me enough information about other Mexican drivers who have achieved a podium finish. I need to look up more information.
Action 2: Lookup[Formula One drivers from Mexico]
Observation 2: No more results.
Thought 3: The available information doesn't allow me to determine which other Mexican Formula One race car driver, besides Sergio P\u00e9rez, has held the podium. With the search function failing to provide a full list of Mexican Formula One drivers, I need to return different search results. Let's try searching for Mexican Grand Prix winners, as they would have held the podium.
Action 3: Search[Mexican Grand Prix winners]
Observation 3: Could not find Mexican Grand Prix winners. Similar: ['Mexican Grand Prix', 'List of Formula One Grand Prix winners', '1990 Mexican Grand Prix', '2018 Mexican Grand Prix', '2019 Mexican Grand Prix'].
Thought 4: Given the difficulties in finding a direct list of Mexican Grand Prix winners, I should search for the Mexican Grand Prix to get a broader picture of the race's history. This might include winners.
Action 4: Search[Mexican Grand Prix]
This trajectory is incorrect as my search should be related to Mexican Formula One race car drivers, not winners it is reasonable to checkof the Mexican Grand Prix, a seperate event. A better search would have been for the List of Formula One Grand Prix winners, as suggested.
Thus the correctness score is 3
Question: Which magazine was started first Arthur's Magazine or First for Women?
Thought 1: I need to search Arthur's Magazine and First for Women, and find which was started first.
Action 1: Search[Arthur's Magazine]
Observation 1: Arthur's Magazine (1844\u00e2\u0080\u00931846) was an American literary periodical published in Philadelphia in the 19th century. Edited by Timothy Shay Arthur, it featured work by Edgar A. Poe, J.H. Ingraham, Sarah Josepha Hale, Thomas G. Spear, and others.[1][2] In May 1846 it was merged into Godey's Lady's Book.[3]
This trajectory is correct as it is reasonable to search for the first magazine provided in the question. It is also better to have simple searches corresponding to a single entity, making this the best action.
Thus the correctness score is 10
Question: The football manager who recruited David Beckham managed Manchester United during what timeframe?Question: The football manager who recruited David Beckham managed Manchester United during what timeframe?
Thought 1: I need to search for the football manager who recruited David Beckham, and then find out the timeframe in which he managed Manchester United.
Action 1: Search[David Beckham's football manager]
Observation 1: Could not find David Beckham's football manager. Similar: ['David Beckham', 'Inter Miami CF (redirect from Miami Beckham United)', 'Victoria Beckham', 'The Beckham Experiment', 'Miami Freedom Park'].
Thought 2: I couldn't find the information on David Beckham's football manager. I need to search Manchester United and find out the timeframe of the manager.
Action 2: Search[Manchester United]
Observation 2: Manchester United Football Club, commonly referred to as Man United (often stylised as Man Utd), or simply United, is a professional football club based in Old Trafford, Greater Manchester, England. The club competes in the Premier League, the top division in the English football league system. Nicknamed the Red Devils, they were founded as Newton Heath LYR Football Club in 1878, but changed their name to Manchester United in 1902. After a spell playing in Clayton, Manchester, the club moved to their current stadium, Old Trafford, in 1910.. Domestically, Manchester United have won a record 20 league titles, 12 FA Cups, six League Cups and a record 21 FA Community Shields.
Thought 3: The information about David Beckham's football manager is not available. I will search for Manchester United's managers to find the timeframe.
Action 3: Search[Manchester United managers]
Observation 3: Manchester United Football Club is a professional football club based in Old Trafford, Greater Manchester, England. The club was formed in Newton Heath in 1878 as Newton Heath LYR F.C., and played their first competitive match in October 1886, when they entered the First Round of the 1886–87 FA Cup. The club was renamed Manchester United F.C. in 1902, and moved to Old Trafford in 1910.. From the beginning of the club's official managerial records in 1892 to the start of the 2022–23 season, Manchester United have had 23 full-time managers.
Thought 4: The information about David Beckham's football manager is not available. The question asks for the timeframe when the manager managed Manchester United, so I need to find a list of Manchester United managers.
Action 4: Search[list of Manchester United managers]
Observation 4: Manchester United Football Club is a professional football club based in Old Trafford, Greater Manchester, England. The club was formed in Newton Heath in 1878 as Newton Heath LYR F.C., and played their first competitive match in October 1886, when they entered the First Round of the 1886–87 FA Cup. The club was renamed Manchester United F.C. in 1902, and moved to Old Trafford in 1910.. From the beginning of the club's official managerial records in 1892 to the start of the 2022–23 season, Manchester United have had 23 full-time managers.
This trajectory is mostly incorrect as I was not able to retrieve the relevant information to answer the question. The searches are too broad and not relevant to the specific player recruited, David Beckham. The last two actions are also too similar. It would be better to first search for David Beckham and lookup information related to his manager.
Thus the correctness score is 4
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
This trajectory is correct as all of my thoughts and actions are correct. It makes sense to search for Milhouse first as it is the central subject of the question. It is also correct to directly look up the relevant information in the article, instead of trying another search.
Thus the correctness score is 10
{trajectories}
{input}
'''
value_prompt_reasoning_feedback_short = '''Analyze the trajectories of a solution to a question answering task. The trajectories are labeled by environmental observations about the situation, thoughts that can reason about the current situation and actions that can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Given a question and a trajectory, evaluate its correctness and provide your reasoning and analysis in detail. Focus on the latest thought, action, and observation. Incomplete trajectories can be correct if the thoughts and actions so far are correct, even if the answer is not found yet. Do not generate additional thoughts or actions. Then at the last line conclude "Thus the correctness score is {s}", where s is an integer from 1 to 10.
Question: Which other Mexican Formula One race car driver has held the podium besides the Force India driver born in 1990?
Thought 1: I need to search for a list of Mexican Formula One race car drivers, then eliminate the one who drove for Force India and was born in 1990.
Action 1: Search[Formula One drivers from Mexico]
Observation 1: There have been six Formula One drivers from Mexico who have taken part in races since the championship began in 1950. Sergio P\u00e9rez is the most successful, having won six Grands Prix. Since 2021, P\u00e9rez drives for the Red Bull team.. P\u00e9rez is the only Mexican F1 driver to achieve a pole position. He took his first pole position at the 2022 Saudi Arabian Grand Prix, in his 219th Grand Prix meeting (a record for the most Grands Prix before a pole).
Thought 2: Sergio P\u00e9rez, born in 1990 and drove for Force India, is not the Mexican driver we are looking for. The passage does not give me enough information about other Mexican drivers who have achieved a podium finish. I need to look up more information.
Action 2: Lookup[Formula One drivers from Mexico]
Observation 2: No more results.
Thought 3: The available information doesn't allow me to determine which other Mexican Formula One race car driver, besides Sergio P\u00e9rez, has held the podium. With the search function failing to provide a full list of Mexican Formula One drivers, I need to return different search results. Let's try searching for Mexican Grand Prix winners, as they would have held the podium.
Action 3: Search[Mexican Grand Prix winners]
Observation 3: Could not find Mexican Grand Prix winners. Similar: ['Mexican Grand Prix', 'List of Formula One Grand Prix winners', '1990 Mexican Grand Prix', '2018 Mexican Grand Prix', '2019 Mexican Grand Prix'].
Thought 4: Given the difficulties in finding a direct list of Mexican Grand Prix winners, I should search for the Mexican Grand Prix to get a broader picture of the race's history. This might include winners.
Action 4: Search[Mexican Grand Prix]
This trajectory is incorrect as my search should be related to Mexican Formula One race car drivers, not winners of the Mexican Grand Prix, a seperate event. A better search would have been for the List of Formula One Grand Prix winners, as suggested.
Thus the correctness score is 3
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
This trajectory is correct as all of my thoughts and actions are correct. It makes sense to search for Milhouse first as it is the central subject of the question. It is also correct to directly look up the relevant information in the article, instead of trying another search.
Thus the correctness score is 10
{trajectories}
{input}
'''
rap_prompt = '''
Solve a question answering task with interleaving Thought and Action steps. Thought can reason about the current situation, and Action can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Provide the next Thought and next Action. Here are some examples:
Question: What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?
Thought 1: I need to search Colorado orogeny, find the area that the eastern sector of the Colorado orogeny extends into, then find the elevation range of the area.
Action 1: Search[Colorado orogeny]
Thought 2: Then I need to look up eastern sector.
Action 2: Lookup[eastern sector]
Thought 3: The eastern sector of Colorado orogeny extends into the High Plains, so High Plains is the area. I need to search High Plains and find its elevation range.
Action 3: Search[High Plains]
Thought 4: I need to search High Plains (United States).
Action 4: Search[High Plains (United States)]
Thought 5: High Plains rise in elevation from around 1,800 to 7,000 ft, so the answer is 1,800 to 7,000 ft.
Action 5: Finish[1,800 to 7,000 ft]
Question: Guitars for Wounded Warriors is an album that was recorded in the village in which New York county?
Thought 1: I need to search Guitars for Wounded Warriors, then find in which New York county it was recorded.
Action 1: Search[Guitars for Wounded Warriors]
Thought 2: I need to search New Paltz (village), New York and find which county it is in
Action 2: Search[New Paltz (village), New York]
Thought 3: New Paltz (village), New York is in Ulster County, so the answer is Ulster County.
Action 3: Finish[Ulster County]
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Thought 2: I can look up "named after" for finding the specific individual Milhouse is named after.
Action 2: Lookup[named after]
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
{input}
'''
src/YiemAgent.jl
+30 -47
View File
@@ -1,47 +1,30 @@
module YiemAgent
# export agent
""" Order by dependencies of each file. The 1st included file must not depend on any other
files and each file can only depend on the file included before it.
"""
include("type.jl")
using .type
include("util.jl")
using .util
include("llmfunction.jl")
using .llmfunction
include("interface.jl")
using .interface
# ---------------------------------------------- 100 --------------------------------------------- #
end # module YiemAgent_v1
module YiemAgent
"""Order by dependencies of each file. The 1st included file must not depend on any other
files and each file can only depend on the file included before it."""
include("type.jl")
using .type
include("utils.jl")
using .utils
include("toolRegistry.jl")
using .toolRegistry
include("agentCore.jl")
using .agentCore
include("api.jl")
using .api
export promptAgent, takeResponse, followUp, stopAgent
# ---------------------------------------------- 100 --------------------------------------------- #
end # end module
src/agentCore.jl
+1623
View File
File diff suppressed because it is too large Load Diff
src/api.jl
+410
View File
@@ -0,0 +1,410 @@
module api
export promptAgent, takeResponse, followUp, stopAgent
using JSON, DataStructures, Dates, UUIDs, HTTP, Random, PrettyPrinting, Serialization,
DataFrames
using GeneralUtils
using ..type, ..utils, ..agentCore, ..toolRegistry
# ---------------------------------------------- 100 --------------------------------------------- #
"""
Send a message to the agent's input channel.
Blocks if the input channel buffer is full (capacity 16 by default).
The agent processes messages from `inputChannel` in the background task.
# Arguments
- `agent::yiemAgent`: The agent instance to send a message to
- `msg`: The message to send, in OpenAI message format (e.g. `Dict("role" => "user", "content" => "Hello!")`)
# Returns
- The same `agent` instance for chaining
# Notes
- Use `takeResponse(agent)` to receive the agent's response after sending a message.
- Use `followUp(agent, msg)` to send messages while the agent is still processing.
# Examples
```jldoctest
julia> promptAgent(agent, Dict("role" => "user", "content" => "Hello!"))
yiemAgent(...)
```
"""
function promptAgent(agent::yiemAgent, msg::AbstractDict{String, Any})
put!(agent.inputChannel, msg)
return agent
end
function promptAgent(agent::yiemAgent, text::String)
put!(agent.inputChannel, Dict("role" => "user", "content" => [Dict("type" => "text", "text" => text)]))
return agent
end
"""
Take a response from the agent's output channel.
Blocks until the agent sends a response.
# Arguments
- `agent::yiemAgent`: The agent instance to receive a response from
# Returns
- An `assistantMessage` instance representing the agent's response
# Notes
- Use `promptAgent(agent, msg)` to send a message before calling this function.
# Examples
```jldoctest
julia> response = takeResponse(agent)
assistantMessage(...)
```
"""
function takeResponse(agent::yiemAgent)
return take!(agent.outputChannel)
end
"""
Send a follow-up message while the agent is still processing.
Follow-up messages are queued and processed after all `inputChannel` messages
and before any tool call results are sent.
# Arguments
- `agent::yiemAgent`: The agent instance to send a follow-up message to
- `msg`: The follow-up message to send, in OpenAI message format (e.g. `Dict("role" => "user", "content" => "Also consider red wines")`)
# Returns
- The same `agent` instance for chaining
# Notes
- Use `promptAgent(agent, msg)` for the primary message and `followUp(agent, msg)` for additional
messages while the agent is processing.
- Follow-up messages are buffered in a separate channel (capacity 32 by default).
# Examples
```jldoctest
julia> followUp(agent, Dict("role" => "user", "content" => "Also consider red wines"))
yiemAgent(...)
```
"""
function followUp(agent::yiemAgent, msg::AbstractDict{String, Any})
put!(agent.followUpChannel, msg)
return agent
end
function followUp(agent::yiemAgent, text::String)
put!(agent.followUpChannel, Dict("role" => "user", "content" => [Dict("type" => "text", "text" => text)]))
return agent
end
"""
Gracefully stop the agent.
Sends a `:shutdown` signal to the input channel, waits for the background task to finish,
then closes all channels (`inputChannel`, `outputChannel`, `followUpChannel`).
# Arguments
- `agent::yiemAgent`: The agent instance to stop
# Returns
- `nothing`
# Notes
- After calling `stopAgent`, the agent is no longer usable. A new agent must be created
for further interaction.
- If the background task throws a `TaskFailedException`, it is rethrown.
# Examples
```jldoctest
julia> stopAgent(agent)
```
"""
function stopAgent(agent::yiemAgent)
put!(agent.inputChannel, :shutdown)
try
fetch(agent._agentLoop)
catch e
if e isa TaskFailedException
rethrow(e)
end
end
close(agent.inputChannel)
close(agent.outputChannel)
close(agent.followUpChannel)
return nothing
end
""" Recursively convert dictionary-like variable (e.g. JSON.Object) into an OrderedDict.
The function walks any nested structure composed of `AbstractDict` (e.g., `JSON.Object`,
`Dict`, `OrderedDict`) and `AbstractArray` and produces a new tree where
every dictionary-like node is an `OrderedDict` and every array-like node is a `Vector{Any}`.
Scalar values (numbers, strings, booleans, `nothing`, etc.) are returned unchanged.
Does **not** mutate the input; it always allocates new containers.
# Arguments
- `x`
Any Julia value. If `x` is an `AbstractDict` it will be converted to an `OrderedDict`;
if it is an `AbstractArray` its elements will be processed recursively.
# Keyword Arguments
- `keytype::Type=Any`
The key type for the output OrderedDict. Use `String` for `OrderedDict{String,Any}`,
`Symbol` for `OrderedDict{Symbol,Any}`, or `Any` to preserve original key types.
- `sort_order::Union{Nothing, Vector}=nothing`
Vector of keys specifying the desired order. Keys are arranged in the specified order
first, followed by any remaining keys.
# Return
- A newly allocated nested structure composed of `OrderedDict{keytype,Any}` and `Vector{Any}`
that mirrors the input shape but uses ordered Julia containers.
# Notes
- The function treats any `AbstractDict` as a mapping source, so it works with
`JSON.Object`, `Dict`, `OrderedDict`, etc.
- Arrays are returned as `Vector{Any}` with their elements processed recursively.
# Examples
```jldoctest
julia> using JSON, DataStructures
julia> d = Dict(
"a" => 4,
"b" => 6,
"c" => Dict(
"d"=>7,
:e=>Dict(
"f"=>"hey",
"g"=>Dict(
"world"=>[1, "2", 3, Dict(:dd=>4.7)]
)
)
)
)
julia> jsonstring = JSON.json(d)
julia> A1 = JSON.parse(jsonstring) # A1 type is JSON.Object
julia> A2 = dictify(A1; keytype=String)
OrderedDict{String,Any} with 3 entries:
"a" => 4
"b" => 6
"c" => OrderedDict("d"=>7, "e"=>Dict("f"=>"hey", "g"=>Dict("world"=>[1, "2", 3, 4.7])))
julia> A3 = dictify(A1; keytype=Symbol)
OrderedDict{Symbol,Any} with 3 entries:
:a => 4
:b => 6
:c => OrderedDict(:d=>7, :e=>Dict("f"=>"hey", "g"=>Dict("world"=>[1, "2", 3, 4.7])))
julia> B1 = dictify(d; keytype=String)
OrderedDict{String, Any} with 3 entries:
```
**With sort_order:**
```jldoctest
julia> d = Dict("a"=>1, "b"=>2, "c"=>3)
julia> dictify(d; sort_order=["c", "a"])
OrderedDict{String,Int} with 3 entries:
"c" => 3
"a" => 1
"b" => 2
```
"""
function dictify(x::T; keytype::Type=Any, sort_order::Union{Nothing, Vector}=nothing
)::OrderedDict where {T<:AbstractDict}
# this function is example
end
end # module interface
src/interface.jl
-1356
View File
File diff suppressed because it is too large Load Diff
src/llmfunction.jl
-1646
View File
File diff suppressed because it is too large Load Diff
src/toolRegistry.jl
+291
View File
@@ -0,0 +1,291 @@
module toolRegistry
export registerTool, registerAllTools, clearTools, listTool
using Dates
using JSON, DataStructures
using ..type
# ── MCP helper functions ────────────────────────────────────────────
"""
Extract text from MCP tool result content array.
Handles JSON-RPC 2.0 result content format:
{"content": [{"type": "text", "text": "..."}], "isError": false}
"""
function _extract_text_content(result::AbstractDict)::String
content = get(result, "content", Any[])
if content isa Vector && !isempty(content)
lines = String[]
for block in content
if block isa Dict && get(block, "type", "") == "text"
push!(lines, string(get(block, "text", "")))
end
end
if !isempty(lines)
return join(lines, "\n")
end
end
return JSON.json(result)
end
"""
Wrap an MCP tool definition as an `agentTool`.
The returned tool's `execute` function calls the MCP server's "tools/call"
method with the validated arguments.
"""
function _wrap_mcp_tool(mcpserver, tool_def::AbstractDict{String, Any}; eventSink=nothing, sessionId=nothing)::agentTool
name = tool_def["name"]
title = get(tool_def, "title", get(tool_def, "label", name))
desc = get(tool_def, "description", "")
input_schema = get(tool_def, "inputSchema", Dict{String,Any}())
# Normalize inputSchema to OpenAI function format
if haskey(input_schema, "properties") && input_schema["type"] == "object"
params = Dict(
"type" => "object",
"properties" => input_schema["properties"],
"required" => get(input_schema, "required", Any[]),
)
else
params = Dict(
"type" => "object",
"properties" => Dict{String,Any}(),
"required" => Any[],
)
end
return agentTool(
name=name,
label=title,
description=desc,
inputSchema=params,
execute=(toolCallId::String, args::AbstractDict{String, Any},
signal::Union{Nothing,abortSignal},
eventSink) -> begin
try
response = mcpserver("tools/call", name, args, sessionId; eventSink=eventSink)
# Parse JSON-RPC 2.0 response envelope
if haskey(response, "error")
rpc_error = response["error"]
err_msg = get(rpc_error, "message", "Unknown MCP error")
return agentToolResult(
[textContent("MCP error: $err_msg")],
Dict{Any,Any}("error" => err_msg),
nothing, false
)
end
result_data = get(response, "result", response)
content_text = _extract_text_content(result_data)
is_error = get(result_data, "isError", false)
return agentToolResult(
[textContent(content_text)],
Dict{Any,Any}("isError" => is_error),
nothing, false
)
catch e
errMsg = sprint(showerror, e)
return agentToolResult(
[textContent("MCP call error: $errMsg")],
Dict{Any,Any}("error" => errMsg),
nothing, false
)
end
end,
prepareArguments=nothing,
validateRequiredArgs=nothing,
parallelToolExecute=false,
)
end
"""
Discover and register MCP tools into `store.tools`.
Queries the MCP server via `mcpserver("tools/list")` (JSON-RPC 2.0 format),
parses the response envelope, and registers each discovered tool.
Handles pagination via `nextCursor`. Skips tools already registered.
# Returns
- `Int`: number of new tools registered
"""
function register_mcp_tools(tools::OrderedDict{String, agentTool}, mcpserver; eventSink=nothing, sessionId=nothing)::Int
if mcpserver === nothing
return 0
end
new_count = 0
try
eventSink("register_mcp_tools 1")
response = mcpserver("tools/list", sessionId; eventSink=eventSink)
eventSink("register_mcp_tools 2")
# Parse JSON-RPC 2.0 response envelope
if haskey(response, "error")
rpc_error = response["error"]
err_msg = get(rpc_error, "message", "Unknown MCP error")
println("[toolRegistry] MCP tools/list failed: $err_msg")
return 0
end
if haskey(response, "result")
response = response["result"]
end
tools_array = response["tools"]
cursor = get(response, "nextCursor", nothing)
for tool_def in tools_array
name = tool_def["name"]
if haskey(tools, name)
continue
end
wrapped = _wrap_mcp_tool(mcpserver, tool_def, eventSink=eventSink, sessionId=sessionId)
tools[name] = wrapped
new_count += 1
end
# Paginate: fetch remaining tools if nextCursor is present
while cursor !== nothing && cursor !== ""
response = sessionId !== nothing ? mcpserver("tools/list", sessionId; eventSink=eventSink) : mcpserver("tools/list"; eventSink=eventSink)
if haskey(response, "result")
response = response["result"]
end
tools_array = get(response, "tools", Any[])
cursor = get(response, "nextCursor", nothing)
for tool_def in tools_array
name = tool_def["name"]
if haskey(tools, name)
continue
end
wrapped = _wrap_mcp_tool(mcpserver, tool_def, eventSink=eventSink, sessionId=sessionId)
tools[name] = wrapped
new_count += 1
end
end
println("[toolRegistry] Discovered $new_count MCP tools. Total: $(length(tools))")
catch e
bt = catch_backtrace()
err_msg = sprint() do io
showerror(io, e, bt)
println(io)
end
eventSink(err_msg)
errMsg = sprint(showerror, e)
println("[toolRegistry] MCP tools/list failed: $errMsg")
end
return new_count
end
"""
registerTool(tools::OrderedDict{String, agentTool}, tool::agentTool) -> OrderedDict{String, agentTool}
Add `tool` to `tools`, overwriting any existing tool with the same name.
# Arguments
- `tools`: Tool dict to modify
- `tool`: The `agentTool` to register
# Returns
- The same `tools` dict (modified in place)
"""
function registerTool(tools::OrderedDict{String, agentTool}, tool::agentTool; eventSink=nothing
)::OrderedDict{String, agentTool}
tools[tool.name] = tool
println("[toolRegistry] Registered tool: $(tool.name)")
return tools
end
"""
Remove all tools from the dict.
# Arguments
- `tools`: Tool dict to clear
# Returns
- `nothing`
"""
function clearTools(tools::OrderedDict{String, agentTool})::Nothing
empty!(tools)
println("[toolRegistry] Registry cleared")
return nothing
end
# ── listTools tool (auto-discover new MCP tools at runtime) ─────────
"""
listTool(tools::OrderedDict{String, agentTool}, mcpserver) -> agentTool
MCP-aware listTools tool (JSON-RPC 2.0 protocol).
First call: queries the MCP server via `mcpserver("tools/list")`, registers
all discovered tools into `tools` (in-place mutation, with
pagination via nextCursor), then returns the full tool list.
Subsequent calls: returns the current list (tools remain registered).
"""
function listTool(tools::OrderedDict{String, agentTool}, mcpserver; eventSink=nothing, sessionId=nothing)::agentTool
return agentTool(
name="listTools",
label="List Tools",
description="List all available tools. First call discovers and registers all tools from the MCP server. After discovery, new tools become immediately available for use.",
inputSchema=Dict{String,Any}(
"type" => "object",
"properties" => Dict{String,Any}(),
"required" => Any[]
),
execute=(toolCallId::String, args::AbstractDict{String, Any},
signal::Union{Nothing,abortSignal},
eventSink) -> begin
# Discover and register MCP tools (idempotent — skips already registered)
new_count = register_mcp_tools(tools, mcpserver; eventSink=eventSink, sessionId=sessionId)
eventSink("tools dump: " * sprint(show, tools))
# Always include listTools itself in the count
total = length(tools)
lines = String[
"- $(t.name): $(t.label) — $(t.description)"
for (k, t) in tools
]
result_text = "Available tools ($total):\n" * join(lines, "\n")
return agentToolResult(
[textContent(result_text)],
Dict{Any,Any}("count" => total),
nothing, false
)
end,
prepareArguments=nothing,
validateRequiredArgs=nothing,
parallelToolExecute=false,
)
end
# ── High-level API ──────────────────────────────────────────────────
"""
registerAllTools(tools::OrderedDict{String, agentTool}, mcpserver)
Register all tools for an agent:
1. Auto-discover existing tools from the MCP server
2. Register the `listTools` tool so the agent can discover new tools at runtime
# Arguments
- `tools`: The tool dict to populate
- `mcpserver`: A callable struct that communicates with the MCP server
"""
function registerAllTools(tools::OrderedDict{String, agentTool}, mcpserver=nothing; eventSink=nothing, sessionId=nothing)
list_t = listTool(tools, mcpserver; eventSink=eventSink, sessionId=sessionId)
registerTool(tools, list_t; eventSink=eventSink)
end
end # module
src/type.jl
+829 -375
View File
File diff suppressed because it is too large Load Diff
src/util.jl
-457
View File
@@ -1,457 +0,0 @@
module util
export clearhistory, addNewMessage, chatHistoryToText, eventdict, noises, createTimeline,
availableWineToText, createEventsLog, createChatLog, checkAgentResponse_JSON,
checkAgentResponse_text
using UUIDs, Dates, DataStructures, HTTP, JSON
using GeneralUtils
using ..type
# ---------------------------------------------- 100 --------------------------------------------- #
""" Clear agent chat history.
# Arguments
- `a::agent`
an agent
# Return
- nothing
# Example
```jldoctest
julia> using YiemAgent, MQTTClient, GeneralUtils
julia> client, connection = MakeConnection("test.mosquitto.org", 1883)
julia> connect(client, connection)
julia> msgMeta = GeneralUtils.generate_msgMeta("testtopic")
julia> agentConfig = Dict(
"receiveprompt"=>Dict(
"mqtttopic"=> "testtopic/receive",
),
"receiveinternal"=>Dict(
"mqtttopic"=> "testtopic/internal",
),
"text2text"=>Dict(
"mqtttopic"=> "testtopic/text2text",
),
)
julia> a = YiemAgent.sommelier(
client,
msgMeta,
agentConfig,
)
julia> YiemAgent.addNewMessage(a, "user", "hello")
julia> YiemAgent.clearhistory(a)
```
# TODO
- [PENDING] clear memory
# Signature
"""
function clearhistory(a::T) where {T<:agent}
empty!(a.chathistory)
empty!(a.memory["shortmem"])
empty!(a.memory["events"])
a.memory["chatbox"] = ""
end
""" Add new message to agent.
messages => Dict(
"role" => "user",
"content" => [
Dict("type" => "text", "text" => "Describe this image for me"),
Dict(
"type" => "image_url",
"image_url" => Dict("url" => data_uri)
)
]
)
Arguments\n
-----
a::agent
an agent
role::String
message sender role i.e. system, user or assistant
text::String
message text
Return\n
-----
nothing
Example\n
-----
```jldoctest
```
Signature\n
-----
"""
function addNewMessage(a::T1, name::String, userinput::T2;
maximumMsg::Integer=30) where {T1<:agent, T2<:AbstractDict}
# if name ∉ ["system", "user", "assistant"] # guard against typo
# error("name is not in agent.availableRole $(@__LINE__)")
# end
#TODO summarize the oldest 10 message
if length(a.chathistory) > maximumMsg
summarize(a.chathistory)
else
# userinput["timestamp"] = Dates.now()
push!(a.chathistory, userinput)
end
end
""" Converts a vector of dictionaries to a formatted string.
This function takes in a vector of dictionaries and outputs a single string where each dictionary's keys are prefixed by their values.
# Arguments
- `vecd::Vector`
A vector of dictionaries containing chat messages
- `withkey::Bool`
Whether to include the name as a prefix in the output text. Default is true
- `range::Union{Nothing,UnitRange,Int}`
Optional range of messages to include. If nothing, includes all messages
# Returns
A formatted string where each line contains either:
- If withkey=true: "name> message\n"
- If withkey=false: "message\n"
# Example
julia> using Revise
julia> using GeneralUtils
julia> vecd = [Dict("name" => "John", "text" => "Hello"), Dict("name" => "Jane", "text" => "Goodbye")]
julia> GeneralUtils.vectorOfDictToText(vecd, withkey=true)
"John> Hello\nJane> Goodbye\n"
```
"""
function chatHistoryToText(vecd::Vector; withkey=true, range=nothing)::String
# Initialize an empty string to hold the final text
text = ""
# Get the elements within the specified range, or all elements if no range provided
elements = isnothing(range) ? vecd : vecd[range]
# Determine whether to include the key in the output text or not
if withkey
# Loop through each dictionary in the input vector
for d in elements
# Extract the 'name' and 'text' keys from the dictionary
name = titlecase(d[:name])
_text = d[:text]
# Append the formatted string to the text variable
text *= "$name> $_text \n"
end
else
# Loop through each dictionary in the input vector
for d in elements
# Iterate over all key-value pairs in the dictionary
for (k, v) in d
# Append the formatted string to the text variable
text *= "$v \n"
end
end
end
# Return the final text
return text
end
function availableWineToText(vecd::Vector)::String
# Initialize an empty string to hold the final text
rowtext = ""
# Loop through each dictionary in the input vector
for (i, d) in enumerate(vecd)
# Iterate over all key-value pairs in the dictionary
temp = []
for (k, v) in d
# Append the formatted string to the text variable
t = "$k:$v"
push!(temp, t)
end
_rowtext = join(temp, ',')
rowtext *= "$i) $_rowtext "
end
return rowtext
end
""" Create a dictionary representing an event with optional details.
# Arguments
- `event_description::Union{String, Nothing}`
A description of the event
- `timestamp::Union{DateTime, Nothing}`
The time when the event occurred
- `subject::Union{String, Nothing}`
The subject or entity associated with the event
- `thought::Union{AbstractDict, Nothing}`
Any associated thoughts or metadata
- `action_name::Union{String, Nothing}`
The name of the action performed (e.g., "CHAT", "CHECKINVENTORY")
- `action_input::Union{String, Nothing}`
Input or parameters for the action
- `location::Union{String, Nothing}`
Where the event took place
- `equipment_used::Union{String, Nothing}`
Equipment involved in the event
- `material_used::Union{String, Nothing}`
Materials used during the event
- `outcome::Union{String, Nothing}`
The result or consequence of the event after action execution
- `note::Union{String, Nothing}`
Additional notes or comments
# Returns
A dictionary with event details as symbol-keyed key-value pairs
"""
function eventdict(;
event_description::Union{String, Nothing}=nothing,
timestamp::Union{DateTime, Nothing}=nothing,
subject::Union{String, Nothing}=nothing,
thought::Union{AbstractDict, Nothing}=nothing,
action_name::Union{String, Nothing}=nothing, # "CHAT", "CHECKINVENTORY", "PRESENT_WINE_GUIDELINE", etc
action_input::Union{String, Nothing}=nothing,
location::Union{String, Nothing}=nothing,
equipment_used::Union{String, Nothing}=nothing,
material_used::Union{String, Nothing}=nothing,
observation::Union{String, Nothing}=nothing,
note::Union{String, Nothing}=nothing,
)
d = Dict{String, Any}(
"event_description"=> event_description,
"timestamp"=> timestamp,
"subject"=> subject,
"thought"=> thought,
"action_name"=> action_name,
"action_input"=> action_input,
"location"=> location,
"equipment_used"=> equipment_used,
"material_used"=> material_used,
"observation"=> observation,
"note"=> note,
)
return d
end
""" Create a formatted timeline string from a sequence of events.
# Arguments
- `events::T1`
Vector of event dictionaries containing subject, action_input and optional outcome fields
Each event dictionary should have the following keys:
- :subject - The subject or entity performing the action
- :action_input - The action or input performed by the subject
- :observation - (Optional) The result or outcome of the action
# Returns
- `timeline::String`
A formatted string representing the events with their subjects, actions, and optional outcomes
Format: "{index}) {subject}> {action_input} {outcome}\n" for each event
# Example
events = [
Dict("subject" => "User", "action_input" => "Hello", "observation" => nothing),
Dict("subject" => "Assistant", "action_input" => "Hi there!", "observation" => "with a smile")
]
timeline = createTimeline(events)
# 1) User> Hello
# 2) Assistant> Hi there! with a smile
"""
function createTimeline(events::T1; eventindex::Union{UnitRange, Nothing}=nothing
) where {T1<:AbstractVector}
# Initialize empty timeline string
timeline = ""
# Determine which indices to use - either provided range or full length
ind =
if eventindex !== nothing
[eventindex...]
else
1:length(events)
end
# Iterate through events and format each one
for i in ind
event = events[i]
# If no outcome exists, format without outcome
# if event["action_name"] == "CHAT_BOX"
# timeline *= "Event_$i $(event["subject"])> action_name: $(event["action_name"]), action_input: $(event["action_input"])\n"
# elseif event["action_name"] == "CHECKINVENTORY" && event["observation"] === nothing
# timeline *= "Event_$i $(event["subject"])> action_name: $(event["action_name"]), action_input: $(event["action_input"]), observation: Not done yet.\n"
if event["action_name"] == "SEARCH_WINE_DATABASE"
timeline *= "Event_$i $(event["subject"])> action_name: $(event["action_name"]), action_input: $(event["action_input"]), observation: $(event["observation"])\\n"
else
timeline *= "Event_$i $(event["subject"])> action_name: $(event["action_name"]), action_input: $(event["action_input"])\\n"
end
end
# Return formatted timeline string
return timeline
end
function createEventsLog(events::T1; index::Union{UnitRange, Nothing}=nothing
) where {T1<:AbstractVector}
# Initialize empty log array
log = Dict{String, String}[]
# Determine which indices to use - either provided range or full length
ind =
if index !== nothing
[index...]
else
1:length(events)
end
# Iterate through events and format each one
for i in ind
event = events[i]
# If no outcome exists, format without outcome
if event["observation"] === nothing
subject = event["subject"]
action_name = event["action_name"]
action_input = event["action_input"]
str = "action_name: $action_name, action_input: $action_input"
d = Dict{String, String}("name"=>subject, "text"=>str)
push!(log, d)
else
subject = event["subject"]
action_name = event["action_name"]
action_input = event["action_input"]
observation = event["observation"]
str = "action_name: $action_name, action_input: $action_input, observation: $observation"
d = Dict{String, String}("name"=>subject, "text"=>str)
push!(log, d)
end
end
return log
end
function createChatLog(chatdict::T1; index::Union{UnitRange, Nothing}=nothing
) where {T1<:AbstractVector}
# Initialize empty log array
log = Dict{String, String}[]
# Determine which indices to use - either provided range or full length
ind =
if index !== nothing
[index...]
else
1:length(chatdict)
end
# Iterate through events and format each one
for i in ind
event = chatdict[i]
subject = event["name"]
text = event["text"]
d = Dict{String, String}("name"=>subject, "text"=>text)
push!(log, d)
end
return log
end
function checkAgentResponse_text(response::String, requiredHeader::T
)::Tuple where {T<:Array{String}}
detected_kw = GeneralUtils.detectKeywordVariation(requiredHeader, response)
missingkeys = [k for (k, v) in detected_kw if v === nothing]
ispass = false
errormsg = nothing
if !isempty(missingkeys)
errormsg = "$missingkeys are missing from your previous response"
ispass = false
elseif sum([length(i) for i in values(detected_kw)]) > length(requiredHeader)
errormsg = "Your previous attempt has duplicated points according to the required response format"
ispass = false
else
ispass = true
end
return (ispass, errormsg)
end
end # module util
src/utils.jl
+603
View File
@@ -0,0 +1,603 @@
module utils
export clearhistory, availableWineToText, prepareContext, formatMsgForLLM, validateRequiredArgs,
validateToolArguments, _userMessageToOpenAI,
_assistantMessageToOpenAI, _toolResultMessageToOpenAI, _messageContentToBlocks,
_toolsToOpenAI, beforeToolCall, afterToolCall
using UUIDs, Dates, DataStructures, HTTP, JSON, NATS
using GeneralUtils
using ..type
# ---------------------------------------------- 100 --------------------------------------------- #
"""
Clear agent chat history.
Empties the conversation history, short-term memory, events log, and chatbox.
# Arguments
- `a::T`: An agent instance (subtype of `agent`)
# Returns
- `nothing`
# Notes
- Does not clear long-term memory; use `[PENDING] clear memory` when implemented.
# Examples
```jldoctest
julia> YiemAgent.clearhistory(agent)
```
"""
function clearhistory(a::T) where {T<:agent}
# empty!(a.chathistory)
# empty!(a.memory["shortmem"])
# empty!(a.memory["events"])
# a.memory["chatbox"] = ""
end
"""
Convert a vector of wine dictionaries to a formatted text string.
# Arguments
- `vecd::Vector`: A vector of dictionaries, each representing a wine with key-value pairs
# Returns
- A formatted string where each wine is numbered and each key-value pair is comma-separated
in the format: `"1) key1:value1,key2:value2 key3:value3 2) ..."`
# Examples
```jldoctest
julia> vecd = [Dict("wine_name" => "Chateau A", "price" => "50")]
julia> YiemAgent.availableWineToText(vecd)
"1) wine_name:Chateau A,price:50 "
```
"""
function availableWineToText(vecd::Vector)::String
# Initialize an empty string to hold the final text
rowtext = ""
# Loop through each dictionary in the input vector
for (i, d) in enumerate(vecd)
# Iterate over all key-value pairs in the dictionary
temp = []
for (k, v) in d
# Append the formatted string to the text variable
t = "$k:$v"
push!(temp, t)
end
_rowtext = join(temp, ',')
rowtext *= "$i) $_rowtext "
end
return rowtext
end
"""
prepareContext(state::agentState) -> agentContext
Prepares an `agentContext` from the given `agentState` for sending to
the LLM. By default, it deep copies the system prompt, messages, and
tools from `state` into a new `agentContext`.
Override this function to customize the context — such as filtering
tools based on the user's intent, modifying the system prompt, injecting
additional context (retrieved documents, current time, user preferences),
or pruning and reordering messages before formatting and calling the LLM.
# Arguments
- `state::agentState`: The current agent state containing conversation history,
system prompt, tools, and other configuration
# Returns
- `agentContext`: An `agentContext` containing the prepared system prompt,
messages, and tools to be sent to the LLM
# Examples
```jldoctest
# Default: returns an agentContext with deep copies of system prompt, messages, and tools
prepareContext(state).messages == deepcopy(state.messages)
# Override to filter tools and inject system context:
# function prepareContext(state::agentState)
# msgs = deepcopy(state.messages)
# sysPrompt = state.systemPrompt * "\\nCurrent time: $(now())"
# tools = filter(t -> contains(t.description, "wine"), state.tools)
# return agentContext(sysPrompt, msgs, tools)
# end
```
"""
function prepareContext(state::agentState, eventSink)::agentContext
#TODO filter tools from state.tools based on user intend in user message and tool description
filteredTools = state.tools
#TODO add filtered tools to the current system prompt / modify systemPrompt here
preparedSystemPrompt = state.systemPrompt
#TODO add system prompt, adjust/modify and inject additional context into messages
preparedMessages = deepcopy(state.messages) # messages that will be send to LLM
agentCtx = agentContext(preparedSystemPrompt, preparedMessages, filteredTools)
return agentCtx
end
"""
formatMsgForLLM(ctx::agentContext) -> Dict{String, Any}
Converts an `agentContext` into OpenAI-compatible message format
ready to be sent to the LLM. The system prompt is converted into
a system role message, followed by user, assistant, and tool result
messages.
This function can be overridden in `yiemAgent` to produce custom
LLM message formats for different APIs/providers.
# Arguments
- `ctx::agentContext`: The prepared context containing system prompt,
messages, and tools
# Returns
- `Dict{String, Any}`: A dictionary with `"messages"` key containing
an array of OpenAI-format message dicts
# Examples
```jldoctest
# Default output:
formatMsgForLLm(ctx) == Dict("messages" => [
Dict("role" => "system", "content" => [...]),
Dict("role" => "user", "content" => [...]),
Dict("role" => "assistant", "content" => [...]),
Dict("role" => "tool", "tool_call_id" => "...", "content" => [...]),
])
```
"""
function formatMsgForLLM(ctx::agentContext, eventSink)::Dict{String, Any}
""" openai message format example
msg = Dict(
"model" => "gemma-4-E4B-it-UD-Q4_K_XL",
"messages" => [
Dict(
"role" => "system",
"content" => [
Dict("type" => "text", "text" => systemmsg),
]
),
Dict(
"role" => "user",
"content" => [
Dict("type" => "text", "text" => "Do you have something similar to the one in the image?"),
Dict(
"type" => "image_url",
"image_url" => Dict("url" => data_uri)
)
]
),
Dict(
"role" => "assistant",
"content" => [
Dict("type" => "text", "text" => "let me check."),
]
),
],
"tools"=> [
Dict(
"type" => "function",
"function" => Dict(
"name" => "getWeather",
"description" => "Get current weather",
"parameters" => Dict(
"type" => "object",
"properties" => Dict(
"city" => Dict("type" => "string")
),
"required" => ["city"]
)
)
)
],
"temperature" => 0.7
)
"""
openaiReadyMsg = Dict{String, Any}()
# openaiReadyMsg["model"] = "gemma-4-E4B-it-UD-Q4_K_XL"
messages = Vector{Dict{String, Any}}()
eventSink("formatMsgForLLM 1")
# System prompt as system message
if !isempty(ctx.systemPrompt)
push!(messages, Dict(
"role" => "system",
"content" => [Dict("type" => "text", "text" => ctx.systemPrompt)]
))
end
eventSink("formatMsgForLLM 2")
# Conversation messages
for msg in ctx.messages
if msg isa userMessage
push!(messages, _userMessageToOpenAI(msg))
elseif msg isa assistantMessageToolCall
push!(messages, _assistantMessageToolCallToOpenAI(msg))
elseif msg isa assistantMessage
push!(messages, _assistantMessageToOpenAI(msg))
elseif msg isa toolResultMessage
push!(messages, _toolResultMessageToOpenAI(msg))
end
end
eventSink("formatMsgForLLM 3")
# Convert ctx.tools into OpenAI tools format
tools_array = _toolsToOpenAI(ctx.tools, eventSink)
eventSink("formatMsgForLLM 4")
openaiReadyMsg["messages"] = messages
openaiReadyMsg["temperature"] = 0.7
if !isempty(tools_array)
openaiReadyMsg["tools"] = tools_array
end
return openaiReadyMsg
end
"""
beforeToolCall(context::beforeToolCallContext, signal::abortSignal) -> beforeToolCallResult
Callback invoked before executing a tool call. Use this hook to inspect
the tool call and decide whether to allow, block, or modify it.
Common use cases:
- Request user approval via UI before running destructive tools.
- Validate business rules that cannot be expressed in the JSON schema.
- Check final context (e.g. session state, rate limits, permissions).
# Arguments
- `context::beforeToolCallContext`: Contains the assistant message, tool call,
validated arguments, and current conversation context.
- `signal::abortSignal`: Signal that may be set to abort the operation.
# Returns
- `beforeToolCallResult(false, "N/A")` to allow the call to proceed.
- `beforeToolCallResult(true, "Reason")` to block the call with a reason.
- `nothing` is treated as allow (equivalent to `beforeToolCallResult(false, "N/A")`).
# Example
```jldoctest
function beforeToolCall(context::beforeToolCallContext, signal::abortSignal)
if context.toolCall.name == "deleteFile"
# Block file deletion unless explicitly approved
return beforeToolCallResult(true, "User must approve file deletion")
end
return beforeToolCallResult(false, "N/A")
end
```
"""
function beforeToolCall(context::beforeToolCallContext, signal::abortSignal, eventSink
)::beforeToolCallResult
eventSink("beforeToolCall: $(context.toolCall.name) args=$(context.args)")
return beforeToolCallResult(false, "N/A")
end
"""
afterToolCall(context::afterToolCallContext, signal::abortSignal) -> Union{agentToolResult, Nothing}
Callback invoked after a tool call finishes executing (before and after errors).
Use this hook to post-process the tool result before it is fed back to the LLM.
Common use cases:
- Mask sensitive data (API keys, tokens) from result content.
- Normalize usage tracking data into a consistent format.
- Inspect the result and set `terminate: true` based on business logic
(e.g. "if deployment failed, stop the agent rather than retrying").
- Wrap error results in friendlier messages for the LLM to understand.
# Arguments
- `context::afterToolCallContext`: Contains the assistant message, tool call,
arguments, raw result, error status, and current conversation context.
- `signal::abortSignal`: Signal that may be set to abort the operation.
# Returns
- `nothing` to pass the result through unchanged.
- `agentToolResult(...)` to return a modified result (content, details, usage,
terminate flag can all be overridden).
""" #WORKING arrange result from searchWine tool
function afterToolCall(context::afterToolCallContext, signal::abortSignal, eventSink
)::Union{agentToolResult, Nothing}
eventSink("afterToolCall: $(context.toolCall.name) result=$(context.result) error=$(context.isError)")
return nothing
end
"""
Convert a userMessage to OpenAI message format.
"""
function _userMessageToOpenAI(msg::userMessage)::Dict{String, Any}
return Dict(
"role" => "user",
"content" => _messageContentToBlocks(msg.content)
)
end
"""
Convert an assistantMessageToolCall to OpenAI message format.
Produces a message with role="assistant", content=null, and a tool_calls array:
{
"role": "assistant",
"content": null,
"tool_calls": [
{
"id": "call_1",
"type": "function",
"function": {
"name": "get_weather",
"arguments": "{\"location\": \"San Francisco, CA\"}"
}
}
]
}
"""
function _assistantMessageToolCallToOpenAI(msg::assistantMessageToolCall)::Dict{String, Any}
tool_calls = Dict{String, Any}[]
for tc in msg.toolCalls
push!(tool_calls, Dict(
"id" => tc.id,
"type" => tc.type,
"function" => Dict(
"name" => tc.name,
"arguments" => JSON.json(tc.arguments)
)
))
end
return Dict(
"role" => "assistant",
"content" => nothing,
"tool_calls" => tool_calls
)
end
"""
Convert an assistantMessage to OpenAI message format.
"""
function _assistantMessageToOpenAI(msg::assistantMessage)::Dict{String, Any}
return Dict(
"role" => "assistant",
"content" => _messageContentToBlocks(msg.content)
)
end
"""
Convert a toolResultMessage to OpenAI message format.
"""
function _toolResultMessageToOpenAI(msg::toolResultMessage)::Dict{String, Any}
return Dict(
"role" => "tool",
"tool_call_id" => msg.toolCallId,
"content" => _messageContentToBlocks(msg.content)
)
end
"""
Convert a vector of messageContent to OpenAI content blocks.
Each textContent becomes a text block, each imageContent becomes
an image_url block.
"""
function _messageContentToBlocks(contents::Vector{messageContent})::Vector{Dict{String, Any}}
blocks = Vector{Dict{String, Any}}()
for c in contents
if c isa textContent
push!(blocks, Dict("type" => "text", "text" => c.text))
elseif c isa imageContent
push!(blocks, Dict(
"type" => "image_url",
"image_url" => Dict(
"url" => "data:$(c.mimeType);base64,$(c.data)"
)
))
end
end
return blocks
end
"""
_toolsToOpenAI(tools::Union{OrderedDict{String, agentTool}, Nothing}) -> Vector{Dict{String, Any}}
Convert an OrderedDict of agentTool definitions into OpenAI function tool format.
Returns an empty vector when `tools` is `nothing` or empty.
# Examples
```jldoctest
_toolsToOpenAI(nothing) # => Dict{String, Any}[]
_toolsToOpenAI(tools) # => [Dict("type" => "function", "function" => Dict("name" => "getWeather", ...))]
```
"""
function _toolsToOpenAI(tools::Union{OrderedDict{String, agentTool}, Nothing}, eventSink)::Vector{Dict{String, Any}}
tools_array = Vector{Dict{String, Any}}()
eventSink("_toolsToOpenAI 1")
eventSink(string(typeof(tools)))
if tools !== nothing
for (_, tool) in tools
push!(tools_array, Dict(
"type" => "function",
"function" => Dict(
"name" => tool.name,
"description" => tool.description,
"parameters" => tool.inputSchema
)
))
end
end
eventSink("_toolsToOpenAI 2")
return tools_array
end
"""
validateRequiredArgs(args::AbstractDict{String, Any}, inputSchema::AbstractDict{String, Any}) -> Union{Nothing,String}
Validates that all required fields listed in the tool's JSON Schema are present
in `args`. Returns `nothing` if validation passes, or a descriptive error string
listing the missing required fields.
This is the default `validateRequiredArgs` hook. Tool authors can override it
with a custom validation function that performs additional checks (e.g. type
coercion, format validation, cross-field constraints).
# Arguments
- `args::AbstractDict{String, Any}`: The arguments provided by the LLM
- `inputSchema::AbstractDict{String, Any}`: The tool's `inputSchema` (JSON Schema format)
# Returns
- `nothing` if all required args are present
- `String` error message listing missing fields otherwise
# Examples
```jldoctest
schema = Dict("required" => ["city"])
args = Dict{String,Any}()
validateRequiredArgs(args, schema) # => "Missing required arguments: city"
args2 = Dict("city" => "Tokyo")
validateRequiredArgs(args2, schema) # => nothing
```
"""
function validateRequiredArgs(args::AbstractDict{String, Any}, inputSchema::AbstractDict{String, Any})::Union{Nothing,String}
required = get(inputSchema, "required", Any[])
if isempty(required)
return nothing
end
missing = String[]
for field in required
if !(field in keys(args))
push!(missing, field)
end
end
if !isempty(missing)
return "Missing required arguments: $(join(missing, ", "))"
end
return nothing
end
"""
validateToolArguments(tool::agentTool, prepared::agentToolCall) -> Dict{String,Any}
Validates the prepared tool call arguments by calling the tool's
`validateRequiredArgs` hook (or the default implementation). If validation
fails, returns a modified `agentToolCall` with an empty arguments dict
so downstream code can detect the failure. If the hook exists on the tool
and returns an error string, that error is returned.
This runs **before** the `beforeToolCall` hook, allowing the agent to
reject invalid calls without invoking lifecycle callbacks or logging
false `toolExecutionStart` events.
# Arguments
- `tool::agentTool`: The resolved tool definition
- `prepared::agentToolCall`: The prepared tool call with potentially transformed arguments
# Returns
- `Dict{String,Any}`: The validated arguments if successful
# Errors
- Throws `ArgumentError` if validation fails — this is caught by `prepareToolCall`
and converted to an `immediateOutcome`
# Examples
```jldoctest
# With validateRequiredArgs hook set on the tool
validateToolArguments(toolWithHook, tc) # => validated args or throws
# With default validation (nothing on tool)
validateToolArguments(toolDefault, tc) # => args or throws
```
"""
function validateToolArguments(tool::agentTool, prepared::agentToolCall)::AbstractDict{String, Any}
# Use default (2-arg: args + schema) or tool-specific hook (1-arg: args only)
if isnothing(tool.validateRequiredArgs)
result = validateRequiredArgs(prepared.arguments, tool.inputSchema)
else
result = tool.validateRequiredArgs(prepared.arguments)
end
if result !== nothing
throw(ArgumentError(result))
end
return prepared.arguments
end
end # module util